dr-claw 1.1.2 → 1.1.4

package/server/data/news-results-huggingface.json

@@ -0,0 +1,817 @@
+{
+  "top_papers": [
+    {
+      "id": "2604.05091",
+      "title": "MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a Single GPU",
+      "authors": "Zhengqing Yuan, Hanchi Sun, Lichao Sun, Yanfang Ye",
+      "abstract": "We present MegaTrain, a memory-centric system that efficiently trains 100B+ parameter large language models at full precision on a single GPU. Unlike traditional GPU-centric systems, MegaTrain stores parameters and optimizer states in host memory (CPU memory) and treats GPUs as transient compute engines. For each layer, we stream parameters in and compute gradients out, minimizing persistent device state. To battle the CPU-GPU bandwidth bottleneck, we adopt two key optimizations. 1) We introduce a pipelined double-buffered execution engine that overlaps parameter prefetching, computation, and gradient offloading across multiple CUDA streams, enabling continuous GPU execution. 2) We replace persistent autograd graphs with stateless layer templates, binding weights dynamically as they stream in, eliminating persistent graph metadata while providing flexibility in scheduling. On a single H200 GPU with 1.5TB host memory, MegaTrain reliably trains models up to 120B parameters. It also achieves 1.84times the training throughput of DeepSpeed ZeRO-3 with CPU offloading when training 14B models. MegaTrain also enables 7B model training with 512k token context on a single GH200.",
+      "published": "2026-04-06T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 2.22,
+      "quality_score": 1.6,
+      "final_score": 6.09,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.05091",
+      "pdf_link": "https://arxiv.org/pdf/2604.05091.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05091.png"
+      ],
+      "engagement": {
+        "likes": 37,
+        "comments": 2
+      },
+      "submitted_by": "Zhengqing Yuan",
+      "organization": ""
+    },
+    {
+      "id": "2604.01591",
+      "title": "ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement",
+      "authors": "Difan Jiao, Qianfeng Wen, Blair Yang, Zhenwei Tang, Ashton Anderson",
+      "abstract": "We introduce ThinkTwice, a simple two-phase framework that jointly optimizes LLMs to solve reasoning problems and refine the answers, based on Group Relative Policy Optimization (GRPO). In each pair of training steps, ThinkTwice first optimizes the model on solving reasoning problems, then optimizes it on refining its own solutions to the same problems, using the same binary correctness reward in both phases without correctness signals or critique annotations. Across five mathematical reasoning benchmarks and two model families including Qwen3-4B and Olmo3-7B, ThinkTwice substantially improves both reasoning and refinement performance over competitive online policy optimization baselines. Specifically, on Qwen3-4B, ThinkTwice outperforms GRPO on AIME by 5 percentage points before refinement and by 11.5 points after one self-refinement step, measured by pass@4. Analysis of the training dynamics of ThinkTwice reveals an implicit rectify-then-fortify curriculum: refinement predominantly corrects errors early in training and naturally shifts toward preserving already-correct solutions as the model improves, yielding a more rectified reward signal. Our work establishes joint training of reasoning and self-refinement as a principled and effective methodology for RLVR.",
+      "published": "2026-04-02T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 1.98,
+      "quality_score": 2.3,
+      "final_score": 6.08,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.01591",
+      "pdf_link": "https://arxiv.org/pdf/2604.01591.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.01591.png"
+      ],
+      "engagement": {
+        "likes": 33,
+        "comments": 4
+      },
+      "submitted_by": "Difan Jiao",
+      "organization": "UofTCSSLab"
+    },
+    {
+      "id": "2604.02648",
+      "title": "GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers",
+      "authors": "Shufan Jiang, Chios Chen, Zhiyang Chen",
+      "abstract": "The autonomous discovery of bugs remains a significant challenge in modern software development. Compared to code generation, the complexity of dynamic runtime environments makes bug discovery considerably harder for large language models (LLMs). In this paper, we take game development as a representative domain and introduce the Game Benchmark for Quality Assurance (GBQA), a benchmark containing 30 games and 124 human-verified bugs across three difficulty levels, to evaluate whether LLMs can autonomously detect software bugs. The benchmark is constructed using a multi-agent system that develops games and injects bugs in a scalable manner, with human experts in the loop to ensure correctness. Moreover, we provide a baseline interactive agent equipped with a multi-round ReAct loop and a memory mechanism, enabling long-horizon exploration of game environments for bug detection across different LLMs. Extensive experiments on frontier LLMs demonstrate that autonomous bug discovery remains highly challenging: the best-performing model, Claude-4.6-Opus in thinking mode, identifies only 48.39% of the verified bugs. We believe GBQA provides an adequate testbed and evaluation criterion, and that further progress on it will help close the gap in autonomous software engineering.",
+      "published": "2026-04-03T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 2.34,
+      "quality_score": 1.2,
+      "final_score": 6.07,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.02648",
+      "pdf_link": "https://arxiv.org/pdf/2604.02648.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.02648.png"
+      ],
+      "engagement": {
+        "likes": 39,
+        "comments": 2
+      },
+      "submitted_by": "Shufan Jiang",
+      "organization": ""
+    },
+    {
+      "id": "2604.06268",
+      "title": "RAGEN-2: Reasoning Collapse in Agentic RL",
+      "authors": "Zihan Wang, Chi Gui, Xing Jin, Qineng Wang, Licheng Liu, Kangrui Wang, Shiqi Chen, Linjie Li, Zhengyuan Yang, Pingyue Zhang, Yiping Lu, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, Manling Li",
+      "abstract": "RL training of multi-turn LLM agents is inherently unstable, and reasoning quality directly determines task performance. Entropy is widely used to track reasoning stability. However, entropy only measures diversity within the same input, and cannot tell whether reasoning actually responds to different inputs. In RAGEN-2, we find that even with stable entropy, models can rely on fixed templates that look diverse but are input-agnostic. We call this template collapse, a failure mode invisible to entropy and all existing metrics. To diagnose this failure, we decompose reasoning quality into within-input diversity (Entropy) and cross-input distinguishability (Mutual Information, MI), and introduce a family of mutual information proxies for online diagnosis. Across diverse tasks, mutual information correlates with final performance much more strongly than entropy, making it a more reliable proxy for reasoning quality. We further explain template collapse with a signal-to-noise ratio (SNR) mechanism. Low reward variance weakens task gradients, letting regularization terms dominate and erase cross-input reasoning differences. To address this, we propose SNR-Aware Filtering to select high-signal prompts per iteration using reward variance as a lightweight proxy. Across planning, math reasoning, web navigation, and code execution, the method consistently improves both input dependence and task performance.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 2.4,
+      "quality_score": 0.8,
+      "final_score": 6.0,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.06268",
+      "pdf_link": "https://arxiv.org/pdf/2604.06268.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06268.png"
+      ],
+      "engagement": {
+        "likes": 40,
+        "comments": 1
+      },
+      "submitted_by": "Zihan Wang",
+      "organization": "MLL-Lab"
+    },
+    {
+      "id": "2604.04934",
+      "title": "Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision",
+      "authors": "Hyunsoo Cha, Wonjung Woo, Byungjun Kim, Hanbyul Joo",
+      "abstract": "We present Vanast, a unified framework that generates garment-transferred human animation videos directly from a single human image, garment images, and a pose guidance video. Conventional two-stage pipelines treat image-based virtual try-on and pose-driven animation as separate processes, which often results in identity drift, garment distortion, and front-back inconsistency. Our model addresses these issues by performing the entire process in a single unified step to achieve coherent synthesis. To enable this setting, we construct large-scale triplet supervision. Our data generation pipeline includes generating identity-preserving human images in alternative outfits that differ from garment catalog images, capturing full upper and lower garment triplets to overcome the single-garment-posed video pair limitation, and assembling diverse in-the-wild triplets without requiring garment catalog images. We further introduce a Dual Module architecture for video diffusion transformers to stabilize training, preserve pretrained generative quality, and improve garment accuracy, pose adherence, and identity preservation while supporting zero-shot garment interpolation. Together, these contributions allow Vanast to produce high-fidelity, identity-consistent animation across a wide range of garment types.",
+      "published": "2026-04-06T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 2.1,
+      "quality_score": 1.6,
+      "final_score": 5.97,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.04934",
+      "pdf_link": "https://arxiv.org/pdf/2604.04934.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04934.png"
+      ],
+      "engagement": {
+        "likes": 35,
+        "comments": 5
+      },
+      "submitted_by": "Hyunsoo Cha",
+      "organization": "SeoulNatlUniv"
+    },
+    {
+      "id": "2604.04746",
+      "title": "Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning",
+      "authors": "Lei Zhang, Junjiao Tian, Zhipeng Fan, Kunpeng Li, Jialiang Wang, Weifeng Chen, Markos Georgopoulos, Felix Juefei-Xu, Yuxiang Bao, Julian McAuley, Manling Li, Zecheng He",
+      "abstract": "Humans paint images incrementally: they plan a global layout, sketch a coarse draft, inspect, and refine details, and most importantly, each step is grounded in the evolving visual states. However, can unified multimodal models trained on text-image interleaved datasets also imagine the chain of intermediate states? In this paper, we introduce process-driven image generation, a multi-step paradigm that decomposes synthesis into an interleaved reasoning trajectory of thoughts and actions. Rather than generating images in a single step, our approach unfolds across multiple iterations, each consisting of 4 stages: textual planning, visual drafting, textual reflection, and visual refinement. The textual reasoning explicitly conditions how the visual state should evolve, while the generated visual intermediate in turn constrains and grounds the next round of textual reasoning. A core challenge of process-driven generation stems from the ambiguity of intermediate states: how can models evaluate each partially-complete image? We address this through dense, step-wise supervision that maintains two complementary constraints: for the visual intermediate states, we enforce the spatial and semantic consistency; for the textual intermediate states, we preserve the prior visual knowledge while enabling the model to identify and correct prompt-violating elements. This makes the generation process explicit, interpretable, and directly supervisable. To validate proposed method, we conduct experiments under various text-to-image generation benchmarks.",
+      "published": "2026-04-08T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 2.28,
+      "quality_score": 0.7,
+      "final_score": 5.85,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.04746",
+      "pdf_link": "https://arxiv.org/pdf/2604.04746.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04746.png"
+      ],
+      "engagement": {
+        "likes": 38,
+        "comments": 1
+      },
+      "submitted_by": "Lei Zhang",
+      "organization": "facebook"
+    },
+    {
+      "id": "2604.05117",
+      "title": "Watch Before You Answer: Learning from Visually Grounded Post-Training",
+      "authors": "Yuxuan Zhang, EunJeong Hwang, Huaisong Zhang, Penghui Du, Yiming Jia, Dongfu Jiang, Xuan He, Shenhui Zhang, Ping Nie, Peter West, Kelsey R. Allen",
+      "abstract": "It is critical for vision-language models (VLMs) to comprehensively understand visual, temporal, and textual cues. However, despite rapid progress in multimodal modeling, video understanding performance still lags behind text-based reasoning. In this work, we find that progress is even worse than previously assumed: commonly reported long video understanding benchmarks contain 40-60% of questions that can be answered using text cues alone. Furthermore, we find that these issues are also pervasive in widely used post-training datasets, potentially undercutting the ability of post-training to improve VLM video understanding performance. Guided by this observation, we introduce VidGround as a simple yet effective solution: using only the actual visually grounded questions without any linguistic biases for post-training. When used in tandem with RL-based post-training algorithms, this simple technique improves performance by up to 6.2 points relative to using the full dataset, while using only 69.1% of the original post-training data. Moreover, we show that data curation with a simple post-training algorithm outperforms several more complex post-training techniques, highlighting that data quality is a major bottleneck for improving video understanding in VLMs. These results underscore the importance of curating post-training data and evaluation benchmarks that truly require visual grounding to advance the development of more capable VLMs. Project page: http://vidground.etuagi.com.",
+      "published": "2026-04-06T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 1.62,
+      "quality_score": 2.0,
+      "final_score": 5.62,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.05117",
+      "pdf_link": "https://arxiv.org/pdf/2604.05117.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05117.png"
+      ],
+      "engagement": {
+        "likes": 27,
+        "comments": 2
+      },
+      "submitted_by": "Perry the Platypus",
+      "organization": "NAIL-Group"
+    },
+    {
+      "id": "2604.04323",
+      "title": "How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings",
+      "authors": "Yujian Liu, Jiabao Ji, Li An, Tommi Jaakkola, Yang Zhang, Shiyu Chang",
+      "abstract": "Agent skills, which are reusable, domain-specific knowledge artifacts, have become a popular mechanism for extending LLM-based agents, yet formally benchmarking skill usage performance remains scarce. Existing skill benchmarking efforts focus on overly idealized conditions, where LLMs are directly provided with hand-crafted, narrowly-tailored task-specific skills for each task, whereas in many realistic settings, the LLM agent may have to search for and select relevant skills on its own, and even the closest matching skills may not be well-tailored for the task. In this paper, we conduct the first comprehensive study of skill utility under progressively challenging realistic settings, where agents must retrieve skills from a large collection of 34k real-world skills and may not have access to any hand-curated skills. Our findings reveal that the benefits of skills are fragile: performance gains degrade consistently as settings become more realistic, with pass rates approaching no-skill baselines in the most challenging scenarios. To narrow this gap, we study skill refinement strategies, including query-specific and query-agnostic approaches, and we show that query-specific refinement substantially recovers lost performance when the initial skills are of reasonable relevance and quality. We further demonstrate the generality of retrieval and refinement on Terminal-Bench 2.0, where they improve the pass rate of Claude Opus 4.6 from 57.7% to 65.5%. Our results, consistent across multiple models, highlight both the promise and the current limitations of skills for LLM-based agents. Our code is available at https://github.com/UCSB-NLP-Chang/Skill-Usage.",
+      "published": "2026-04-06T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 1.74,
+      "quality_score": 1.6,
+      "final_score": 5.61,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.04323",
+      "pdf_link": "https://arxiv.org/pdf/2604.04323.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04323.png"
+      ],
+      "engagement": {
+        "likes": 29,
+        "comments": 2
+      },
+      "submitted_by": "Yujian Liu",
+      "organization": "Shiyu-Lab"
+    },
+    {
+      "id": "2604.06169",
+      "title": "In-Place Test-Time Training",
+      "authors": "Guhao Feng, Shengjie Luo, Kai Hua, Ge Zhang, Di He, Wenhao Huang, Tianle Cai",
+      "abstract": "The static ``train then deploy\" paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real-world tasks. Test-Time Training (TTT) offers a compelling alternative by updating a subset of model parameters (fast weights) at inference time, yet its potential in the current LLM ecosystem is hindered by critical barriers including architectural incompatibility, computational inefficiency and misaligned fast weight objectives for language modeling. In this work, we introduce In-Place Test-Time Training (In-Place TTT), a framework that seamlessly endows LLMs with Test-Time Training ability. In-Place TTT treats the final projection matrix of the ubiquitous MLP blocks as its adaptable fast weights, enabling a ``drop-in\" enhancement for LLMs without costly retraining from scratch. Furthermore, we replace TTT's generic reconstruction objective with a tailored, theoretically-grounded objective explicitly aligned with the Next-Token-Prediction task governing autoregressive language modeling. This principled objective, combined with an efficient chunk-wise update mechanism, results in a highly scalable algorithm compatible with context parallelism. Extensive experiments validate our framework's effectiveness: as an in-place enhancement, it enables a 4B-parameter model to achieve superior performance on tasks with contexts up to 128k, and when pretrained from scratch, it consistently outperforms competitive TTT-related approaches. Ablation study results further provide deeper insights on our design choices. Collectively, our results establish In-Place TTT as a promising step towards a paradigm of continual learning in LLMs.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 1.08,
+      "quality_score": 2.0,
+      "final_score": 5.08,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.06169",
+      "pdf_link": "https://arxiv.org/pdf/2604.06169.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06169.png"
+      ],
+      "engagement": {
+        "likes": 18,
+        "comments": 1
+      },
+      "submitted_by": "taesiri",
+      "organization": ""
+    },
+    {
+      "id": "2603.25111",
+      "title": "SEVerA: Verified Synthesis of Self-Evolving Agents",
+      "authors": "Debangshu Banerjee, Changming Xu, Gagandeep Singh",
+      "abstract": "Recent advances have shown the effectiveness of self-evolving LLM agents on tasks such as program repair and scientific discovery. In this paradigm, a planner LLM synthesizes an agent program that invokes parametric models, including LLMs, which are then tuned per task to improve performance. However, existing self-evolving agent frameworks provide no formal guarantees of safety or correctness. Because such programs are often executed autonomously on unseen inputs, this lack of guarantees raises reliability and security concerns. We formulate agentic code generation as a constrained learning problem, combining hard formal specifications with soft objectives capturing task utility. We introduce Formally Guarded Generative Models (FGGM), which allow the planner LLM to specify a formal output contract for each generative model call using first-order logic. Each FGGM call wraps the underlying model in a rejection sampler with a verified fallback, ensuring every returned output satisfies the contract for any input and parameter setting. Building on FGGM, we present SEVerA (Self-Evolving Verified Agents), a three-stage framework: Search synthesizes candidate parametric programs containing FGGM calls; Verification proves correctness with respect to hard constraints for all parameter values, reducing the problem to unconstrained learning; and Learning applies scalable gradient-based optimization, including GRPO-style fine-tuning, to improve the soft objective while preserving correctness. We evaluate SEVerA on Dafny program verification, symbolic math synthesis, and policy-compliant agentic tool use (τ^2-bench). Across tasks, SEVerA achieves zero constraint violations while improving performance over unconstrained and SOTA baselines, showing that formal behavioral constraints not only guarantee correctness but also steer synthesis toward higher-quality agents.",
+      "published": "2026-03-26T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.9,
+      "quality_score": 2.3,
+      "final_score": 5.0,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2603.25111",
+      "pdf_link": "https://arxiv.org/pdf/2603.25111.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2603.25111.png"
+      ],
+      "engagement": {
+        "likes": 15,
+        "comments": 1
+      },
+      "submitted_by": "Debangshu Banerjee",
+      "organization": ""
+    },
+    {
+      "id": "2604.07023",
+      "title": "MARS: Enabling Autoregressive Models Multi-Token Generation",
+      "authors": "Ziqi Jin, Lei Wang, Ziwei Luo, Aixin Sun",
+      "abstract": "Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an instruction-tuned AR model to predict multiple tokens per forward pass. MARS adds no architectural modifications, no extra parameters, and produces a single model that can still be called exactly like the original AR model with no performance degradation. Unlike speculative decoding, which maintains a separate draft model alongside the target, or multi-head approaches such as Medusa, which attach additional prediction heads, MARS requires only continued training on existing instruction data. When generating one token per forward pass, MARS matches or exceeds the AR baseline on six standard benchmarks. When allowed to accept multiple tokens per step, it maintains baseline-level accuracy while achieving 1.5-1.7x throughput. We further develop a block-level KV caching strategy for batch inference, achieving up to 1.71x wall-clock speedup over AR with KV cache on Qwen2.5-7B. Finally, MARS supports real-time speed adjustment via confidence thresholding: under high request load, the serving system can increase throughput on the fly without swapping models or restarting, providing a practical latency-quality knob for deployment.",
+      "published": "2026-04-08T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 1.26,
+      "quality_score": 1.1,
+      "final_score": 4.96,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.07023",
+      "pdf_link": "https://arxiv.org/pdf/2604.07023.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07023.png"
+      ],
+      "engagement": {
+        "likes": 21,
+        "comments": 1
+      },
+      "submitted_by": "Phi",
+      "organization": "NanyangTechnologicalUniversity"
+    },
+    {
+      "id": "2604.07209",
+      "title": "INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling",
+      "authors": "InSpatio Team, Donghui Shen, Guofeng Zhang, Haomin Liu, Haoyu Ji, Hujun Bao, Hongjia Zhai, Jialin Liu, Jing Guo, Nan Wang, Siji Pan, Weihong Pan, Weijian Xie, Xianbin Liu, Xiaojun Xiang, Xiaoyu Zhang, Xinyu Chen, Yifu Wang, Yipeng Chen, Zhenzhou Fan, Zhewen Le, Zhichao Ye, Ziqiang Zhao",
+      "abstract": "Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual realism, making it difficult to support seamless navigation in complex environments. To address these challenges, we propose INSPATIO-WORLD, a novel real-time framework capable of recovering and generating high-fidelity, dynamic interactive scenes from a single reference video. At the core of our approach is a Spatiotemporal Autoregressive (STAR) architecture, which enables consistent and controllable scene evolution through two tightly coupled components: Implicit Spatiotemporal Cache aggregates reference and historical observations into a latent world representation, ensuring global consistency during long-horizon navigation; Explicit Spatial Constraint Module enforces geometric structure and translates user interactions into precise and physically plausible camera trajectories. Furthermore, we introduce Joint Distribution Matching Distillation (JDMD). By using real-world data distributions as a regularizing guide, JDMD effectively overcomes the fidelity degradation typically caused by over-reliance on synthetic data. Extensive experiments demonstrate that INSPATIO-WORLD significantly outperforms existing state-of-the-art (SOTA) models in spatial consistency and interaction precision, ranking first among real-time interactive methods on the WorldScore-Dynamic benchmark, and establishing a practical pipeline for navigating 4D environments reconstructed from monocular videos.",
+      "published": "2026-04-08T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.84,
+      "quality_score": 2.3,
+      "final_score": 4.94,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.07209",
+      "pdf_link": "https://arxiv.org/pdf/2604.07209.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07209.png"
+      ],
+      "engagement": {
+        "likes": 14,
+        "comments": 0
+      },
+      "submitted_by": "taesiri",
+      "organization": ""
+    },
+    {
+      "id": "2604.06170",
+      "title": "Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework",
+      "authors": "Komal Kumar, Aman Chadha, Salman Khan, Fahad Shahbaz Khan, Hisham Cholakkal",
+      "abstract": "The rapid growth of scientific literature has made it increasingly difficult for researchers to efficiently discover, evaluate, and synthesize relevant work. Recent advances in multi-agent large language models (LLMs) have demonstrated strong potential for understanding user intent and are being trained to utilize various tools. In this paper, we introduce Paper Circle, a multi-agent research discovery and analysis system designed to reduce the effort required to find, assess, organize, and understand academic literature. The system comprises two complementary pipelines: (1) a Discovery Pipeline that integrates offline and online retrieval from multiple sources, multi-criteria scoring, diversity-aware ranking, and structured outputs; and (2) an Analysis Pipeline that transforms individual papers into structured knowledge graphs with typed nodes such as concepts, methods, experiments, and figures, enabling graph-aware question answering and coverage verification. Both pipelines are implemented within a coder LLM-based multi-agent orchestration framework and produce fully reproducible, synchronized outputs including JSON, CSV, BibTeX, Markdown, and HTML at each agent step. This paper describes the system architecture, agent roles, retrieval and scoring methods, knowledge graph schema, and evaluation interfaces that together form the Paper Circle research workflow. We benchmark Paper Circle on both paper retrieval and paper review generation, reporting hit rate, MRR, and Recall at K. Results show consistent improvements with stronger agent models. We have publicly released the website at https://papercircle.vercel.app/ and the code at https://github.com/MAXNORM8650/papercircle.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 1.2,
+      "quality_score": 1.2,
+      "final_score": 4.93,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.06170",
+      "pdf_link": "https://arxiv.org/pdf/2604.06170.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06170.png"
+      ],
+      "engagement": {
+        "likes": 20,
+        "comments": 2
+      },
+      "submitted_by": "Komal Kumar",
+      "organization": "MBZUAI"
+    },
+    {
+      "id": "2604.05181",
+      "title": "General Multimodal Protein Design Enables DNA-Encoding of Chemistry",
+      "authors": "Jarrid Rector-Brooks, Théophile Lambert, Marta Skreta, Daniel Roth, Yueming Long, Zi-Qi Li, Xi Zhang, Miruna Cretu, Francesca-Zhoufan Li, Tanvi Ganapathy, Emily Jin, Avishek Joey Bose, Jason Yang, Kirill Neklyudov, Yoshua Bengio, Alexander Tong, Frances H. Arnold, Cheng-Hao Liu",
+      "abstract": "Evolution is an extraordinary engine for enzymatic diversity, yet the chemistry it has explored remains a narrow slice of what DNA can encode. Deep generative models can design new proteins that bind ligands, but none have created enzymes without pre-specifying catalytic residues. We introduce DISCO (DIffusion for Sequence-structure CO-design), a multimodal model that co-designs protein sequence and 3D structure around arbitrary biomolecules, as well as inference-time scaling methods that optimize objectives across both modalities. Conditioned solely on reactive intermediates, DISCO designs diverse heme enzymes with novel active-site geometries. These enzymes catalyze new-to-nature carbene-transfer reactions, including alkene cyclopropanation, spirocyclopropanation, B-H, and C(sp^3)-H insertions, with high activities exceeding those of engineered enzymes. Random mutagenesis of a selected design further confirmed that enzyme activity can be improved through directed evolution. By providing a scalable route to evolvable enzymes, DISCO broadens the potential scope of genetically encodable transformations. Code is available at https://github.com/DISCO-design/DISCO.",
+      "published": "2026-04-06T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 1.38,
+      "quality_score": 0.3,
+      "final_score": 4.81,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.05181",
+      "pdf_link": "https://arxiv.org/pdf/2604.05181.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05181.png"
+      ],
+      "engagement": {
+        "likes": 23,
+        "comments": 2
+      },
+      "submitted_by": "Jarrid Rector-Brooks",
+      "organization": "DISCO-Design"
+    },
+    {
+      "id": "2604.04215",
+      "title": "DARE: Diffusion Large Language Models Alignment and Reinforcement Executor",
+      "authors": "Jingyi Yang, Yuxian Jiang, Xuhao Hu, Shuang Cheng, Biqing Qi, Jing Shao",
+      "abstract": "Diffusion large language models (dLLMs) are emerging as a compelling alternative to dominant autoregressive models, replacing strictly sequential token generation with iterative denoising and parallel generation dynamics. However, their open-source ecosystem remains fragmented across model families and, in particular, across post-training pipelines, where reinforcement learning objectives, rollout implementations and evaluation scripts are often released as paper-specific codebases. This fragmentation slows research iteration, raises the engineering burden of reproduction, and makes fair comparison across algorithms difficult. We present DARE (dLLMs Alignment and Reinforcement Executor), an open framework for post-training and evaluating dLLMs. Built on top of verl~sheng2024hybridflow and OpenCompass~2023opencompass, DARE unifies supervised fine-tuning, parameter-efficient fine-tuning, preference optimization, and dLLM-specific reinforcement learning under a shared execution stack for both masked and block diffusion language models. Across representative model families including LLaDA, Dream, SDAR, and LLaDA2.x, DARE provides broad algorithmic coverage, reproducible benchmark evaluation, and practical acceleration. Extensive empirical results position that DARE serves as a reusable research substrate for developing, comparing, and deploying post-training methods for current and emerging dLLMs.",
+      "published": "2026-04-05T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 1.08,
+      "quality_score": 0.9,
+      "final_score": 4.71,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.04215",
+      "pdf_link": "https://arxiv.org/pdf/2604.04215.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04215.png"
+      ],
+      "engagement": {
+        "likes": 18,
+        "comments": 2
+      },
+      "submitted_by": "jingyi Yang",
+      "organization": "Fudan-University"
+    },
+    {
+      "id": "2604.05172",
+      "title": "ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces",
+      "authors": "Xiangyi Li, Kyoung Whan Choe, Yimin Liu, Xiaokun Chen, Chujun Tao, Bingran You, Wenbo Chen, Zonglin Di, Jiankai Sun, Shenghan Zheng, Jiajun Bao, Yuanli Wang, Weixiang Yan, Yiyuan Li, Han-chung Lee",
+      "abstract": "Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is risky due to potentially irreversible changes. Existing benchmarks rely on simplified environments and fail to capture realistic, stateful, multi-service workflows. We introduce ClawsBench, a benchmark for evaluating and improving LLM agents in realistic productivity settings. It includes five high-fidelity mock services (Gmail, Slack, Google Calendar, Google Docs, Google Drive) with full state management and deterministic snapshot/restore, along with 44 structured tasks covering single-service, cross-service, and safety-critical scenarios. We decompose agent scaffolding into two independent levers (domain skills that inject API knowledge via progressive disclosure, and a meta prompt that coordinates behavior across services) and vary both to measure their separate and combined effects. Experiments across 6 models, 4 agent harnesses, and 33 conditions show that with full scaffolding, agents achieve task success rates of 39-64% but exhibit unsafe action rates of 7-33%. On OpenClaw, the top five models fall within a 10 percentage-point band on task success (53-63%), with unsafe action rates from 7% to 23% and no consistent ordering between the two metrics. We identify eight recurring patterns of unsafe behavior, including multi-step sandbox escalation and silent contract modification.",
+      "published": "2026-04-06T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 1.02,
+      "quality_score": 0.7,
+      "final_score": 4.59,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.05172",
+      "pdf_link": "https://arxiv.org/pdf/2604.05172.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05172.png"
+      ],
+      "engagement": {
+        "likes": 17,
+        "comments": 2
+      },
+      "submitted_by": "Xiangyi Li",
+      "organization": "benchflow"
+    },
+    {
+      "id": "2604.07340",
+      "title": "TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders",
+      "authors": "Teng Li, Ziyuan Huang, Cong Chen, Yangfu Li, Yuanhuiyi Lyu, Dandan Zheng, Chunhua Shen, Jun Zhang",
+      "abstract": "We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this strategy often leads to latent representation collapse, which degrades generative performance. Instead of relying on increasingly complex architectures or multi-stage training schemes, TC-AE addresses this challenge from the perspective of the token space, the key bridge between pixels and image latents, through two complementary innovations: Firstly, we study token number scaling by adjusting the patch size in ViT under a fixed latent budget, and identify aggressive token-to-latent compression as the key factor that limits effective scaling. To address this issue, we decompose token-to-latent compression into two stages, reducing structural information loss and enabling effective token number scaling for generation. Secondly, to further mitigate latent representation collapse, we enhance the semantic structure of image tokens via joint self-supervised training, leading to more generative-friendly latents. With these designs, TC-AE achieves substantially improved reconstruction and generative performance under deep compression. We hope our research will advance ViT-based tokenizer for visual generation.",
+      "published": "2026-04-08T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.54,
+      "quality_score": 2.0,
+      "final_score": 4.54,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.07340",
+      "pdf_link": "https://arxiv.org/pdf/2604.07340.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07340.png"
+      ],
+      "engagement": {
+        "likes": 9,
+        "comments": 1
+      },
+      "submitted_by": "Teng LI",
+      "organization": ""
+    },
+    {
+      "id": "2604.06156",
+      "title": "MMEmb-R1: Reasoning-Enhanced Multimodal Embedding with Pair-Aware Selection and Adaptive Control",
+      "authors": "Yuchi Wang, Haiyang Yu, Weikang Bian, Jiefeng Long, Xiao Liang, Chao Feng, Hongsheng Li",
+      "abstract": "MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental challenges. First, structural misalignment between instance-level reasoning and pairwise contrastive supervision may lead to shortcut behavior, where the model merely learns the superficial format of reasoning. Second, reasoning is not universally beneficial for embedding tasks. Enforcing reasoning for all inputs may introduce unnecessary computation and latency, and can even obscure salient semantic signals for simple cases. To address these issues, we propose MMEmb-R1, an adaptive reasoning-based multimodal embedding framework. We formulate reasoning as a latent variable and introduce pair-aware reasoning selection that employs counterfactual intervention to identify reasoning paths beneficial for query-target alignment. Furthermore, we adopt reinforcement learning to selectively invoke reasoning only when necessary. Experiments on the MMEB-V2 benchmark demonstrate that our model achieves a score of 71.2 with only 4B parameters, establishing a new state-of-the-art while significantly reducing reasoning overhead and inference latency.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.42,
+      "quality_score": 2.3,
+      "final_score": 4.52,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.06156",
+      "pdf_link": "https://arxiv.org/pdf/2604.06156.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06156.png"
+      ],
+      "engagement": {
+        "likes": 7,
+        "comments": 2
+      },
+      "submitted_by": "wangyuchi",
+      "organization": "CUOHK"
+    },
+    {
+      "id": "2604.06916",
+      "title": "FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling",
+      "authors": "Yitong Li, Junsong Chen, Shuchen Xue, Pengcuo Zeren, Siyuan Fu, Dinghao Yang, Yangyang Tang, Junjie Bai, Ping Luo, Song Han, Enze Xie",
+      "abstract": "Reinforcement-Learning-based post-training has recently emerged as a promising paradigm for aligning text-to-image diffusion models with human preferences. In recent studies, increasing the rollout group size yields pronounced performance improvements, indicating substantial room for further alignment gains. However, scaling rollouts on large-scale foundational diffusion models (e.g., FLUX.1-12B) imposes a heavy computational burden. To alleviate this bottleneck, we explore the integration of FP4 quantization into Diffusion RL rollouts. Yet, we identify that naive quantized pipelines inherently introduce risks of performance degradation. To overcome this dilemma between efficiency and training integrity, we propose Sol-RL (Speed-of-light RL), a novel FP4-empowered Two-stage Reinforcement Learning framework. First, we utilize high-throughput NVFP4 rollouts to generate a massive candidate pool and extract a highly contrastive subset. Second, we regenerate these selected samples in BF16 precision and optimize the policy exclusively on them. By decoupling candidate exploration from policy optimization, Sol-RL integrates the algorithmic mechanisms of rollout scaling with the system-level throughput gains of NVFP4. This synergistic algorithm-hardware design effectively accelerates the rollout phase while reserving high-fidelity samples for optimization. We empirically demonstrate that our framework maintains the training integrity of BF16 precision pipeline while fully exploiting the throughput gains enabled by FP4 arithmetic. Extensive experiments across SANA, FLUX.1, and SD3.5-L substantiate that our approach delivers superior alignment performance across multiple metrics while accelerating training convergence by up to 4.64times, unlocking the power of massive rollout scaling at a fraction of the cost.",
+      "published": "2026-04-08T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.42,
+      "quality_score": 2.0,
+      "final_score": 4.42,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.06916",
+      "pdf_link": "https://arxiv.org/pdf/2604.06916.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06916.png"
+      ],
+      "engagement": {
+        "likes": 7,
+        "comments": 0
+      },
+      "submitted_by": "taesiri",
+      "organization": "nvidia"
+    },
+    {
+      "id": "2604.05081",
+      "title": "MedGemma 1.5 Technical Report",
+      "authors": "Andrew Sellergren, Chufan Gao, Fereshteh Mahvar, Timo Kohlberger, Fayaz Jamil, Madeleine Traverse, Alberto Tono, Bashir Sadjad, Lin Yang, Charles Lau, Liron Yatziv, Tiffany Chen, Bram Sterling, Kenneth Philbrick, Richa Tiwari, Yun Liu, Madhuram Jajoo, Chandrashekar Sankarapu, Swapnil Vispute, Harshad Purandare, Abhishek Bijay Mishra, Sam Schmidgall, Tao Tu, Anil Palepu, Chunjong Park, Tim Strother, Rahul Thapa, Yong Cheng, Preeti Singh, Kat Black, Yossi Matias, Katherine Chou, Avinatan Hassidim, Kavi Goel, Joelle Barral, Tris Warkentin, Shravya Shetty, Dale Webster, Sunny Virmani, David F. Steiner, Can Kirmizibayrak, Daniel Golden",
+      "abstract": "We introduce MedGemma 1.5 4B, the latest model in the MedGemma collection. MedGemma 1.5 expands on MedGemma 1 by integrating additional capabilities: high-dimensional medical imaging (CT/MRI volumes and histopathology whole slide images), anatomical localization via bounding boxes, multi-timepoint chest X-ray analysis, and improved medical document understanding (lab reports, electronic health records). We detail the innovations required to enable these modalities within a single architecture, including new training data, long-context 3D volume slicing, and whole-slide pathology sampling. Compared to MedGemma 1 4B, MedGemma 1.5 4B demonstrates significant gains in these new areas, improving 3D MRI condition classification accuracy by 11% and 3D CT condition classification by 3% (absolute improvements). In whole slide pathology imaging, MedGemma 1.5 4B achieves a 47% macro F1 gain. Additionally, it improves anatomical localization with a 35% increase in Intersection over Union on chest X-rays and achieves a 4% macro accuracy for longitudinal (multi-timepoint) chest x-ray analysis. Beyond its improved multimodal performance over MedGemma 1, MedGemma 1.5 improves on text-based clinical knowledge and reasoning, improving by 5% on MedQA accuracy and 22% on EHRQA accuracy. It also achieves an average of 18% macro F1 on 4 different lab report information extraction datasets (EHR Datasets 2, 3, 4, and Mendeley Clinical Laboratory Test Reports). Taken together, MedGemma 1.5 serves as a robust, open resource for the community, designed as an improved foundation on which developers can create the next generation of medical AI systems. Resources and tutorials for building upon MedGemma 1.5 can be found at https://goo.gle/MedGemma.",
+      "published": "2026-04-06T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.54,
+      "quality_score": 1.6,
+      "final_score": 4.41,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.05081",
+      "pdf_link": "https://arxiv.org/pdf/2604.05081.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05081.png"
+      ],
+      "engagement": {
+        "likes": 9,
+        "comments": 1
+      },
+      "submitted_by": "taesiri",
+      "organization": ""
+    },
+    {
+      "id": "2604.06757",
+      "title": "FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching",
+      "authors": "Junchao Yi, Rui Zhao, Jiahao Tang, Weixian Lei, Linjie Li, Qisheng Su, Zhengyuan Yang, Lijuan Wang, Xiaofeng Zhu, Alex Jinpeng Wang",
+      "abstract": "Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking whether all modalities, including textual descriptions, spatial layouts, and editing instructions, can be unified into a single visual representation. We present FlowInOne, a framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean image-in, image-out pipeline governed by a single flow matching model. This vision-centric formulation naturally eliminates cross-modal alignment bottlenecks, noise scheduling, and task-specific architectural branches, unifying text-to-image generation, layout-guided editing, and visual instruction following under one coherent paradigm. To support this, we introduce VisPrompt-5M, a large-scale dataset of 5 million visual prompt pairs spanning diverse tasks including physics-aware force dynamics and trajectory prediction, alongside VP-Bench, a rigorously curated benchmark assessing instruction faithfulness, spatial precision, visual realism, and content consistency. Extensive experiments demonstrate that FlowInOne achieves state-of-the-art performance across all unified generation tasks, surpassing both open-source models and competitive commercial systems, establishing a new foundation for fully vision-centric generative modeling where perception and creation coexist within a single continuous visual space.",
+      "published": "2026-04-08T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.3,
+      "quality_score": 2.3,
+      "final_score": 4.4,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.06757",
+      "pdf_link": "https://arxiv.org/pdf/2604.06757.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06757.png"
+      ],
+      "engagement": {
+        "likes": 5,
+        "comments": 2
+      },
+      "submitted_by": "Rui Zhao",
+      "organization": ""
+    },
+    {
+      "id": "2604.06079",
+      "title": "Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning",
+      "authors": "Juekai Lin, Yun Zhu, Honglin Lin, Sijing Li, Tianwei Lin, Zheng Liu, Xiaoyang Wang, Wenqiao Zhang, Lijun Wu",
+      "abstract": "Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While TikZ is the de facto standard for scientific schematics due to its programmatic flexibility, its requirement for rigorous spatial precision presents a significant challenge for Multimodal Large Language Models. Progress is currently stifled by two primary gaps: (1) Data Quality Gap: existing image-TikZ corpora often lack strict executability and reliable visual alignment; (2) Evaluation Gap: a lack of benchmarks for both structural and visual fidelity. To address these, we present a closed-loop framework featuring: SciTikZ-230K, a large-scale, high-quality dataset from our Execution-Centric Data Engine covering 11 diverse scientific disciplines; SciTikZ-Bench, a multifaceted benchmark spanning from basic geometric constructs to intricate hierarchical schematics to evaluate both visual fidelity and structural logic. To further broaden the scope of visual-code optimization methodology, we introduce a novel Dual Self-Consistency Reinforcement Learning optimization paradigm, which utilizes Round-Trip Verification to penalize degenerate code and boost overall self-consistency. Empowered by these, our trained model SciTikZer-8B achieves state-of-the-art performance, consistently outperforming proprietary giants like Gemini-2.5-Pro and massive models like Qwen3-VL-235B-A22B-Instruct.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.18,
+      "quality_score": 2.3,
+      "final_score": 4.28,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.06079",
+      "pdf_link": "https://arxiv.org/pdf/2604.06079.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06079.png"
+      ],
+      "engagement": {
+        "likes": 3,
+        "comments": 1
+      },
+      "submitted_by": "taesiri",
+      "organization": ""
+    },
+    {
+      "id": "2604.05643",
+      "title": "Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs",
+      "authors": "Hongyuan Yuan, Xinran He, Run Shao, Bolei He, Xianwei Xue, Mengke Chen, Qiutong Pan, Haiwei Wang, Haifeng Li",
+      "abstract": "Extending CoT through RL has been widely used to enhance the reasoning capabilities of LLMs. However, due to the sparsity of reward signals, it can also induce undesirable thinking patterns such as overthinking, i.e., generating redundant intermediate reasoning content. In this work, we argue that a major source of such redundancy is inefficient reflection, which often manifests in two problematic patterns: Indiscriminate Reflection, where the model performs broad, low-impact checks throughout reasoning, and Repetitive Reflection, where it repeatedly re-verifies an already established conclusion. To address this, we introduce a graph-based CoT optimization framework. Specifically, we convert each linear CoT into a directed acyclic graph (DAG) with explicit dependency edges, and design a dual pruning strategy: branch-level pruning removes weakly contributing reflection branches, while depth-level pruning eliminates late-stage re-verification. We distill this behavior via a three-stage pipeline: (1) SFT to initialize the policy on pruned concise traces, (2) DPO to prefer correct but less redundant trajectories, and (3) GRPO with length penalty to jointly optimize answer correctness and efficiency. Experiments show that our approach reduces the average reasoning tokens by 42\\% while maintaining or improving accuracy.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.36,
+      "quality_score": 1.6,
+      "final_score": 4.23,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.05643",
+      "pdf_link": "https://arxiv.org/pdf/2604.05643.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05643.png"
+      ],
+      "engagement": {
+        "likes": 6,
+        "comments": 1
+      },
+      "submitted_by": "HeBolei",
+      "organization": "baidu"
+    },
+    {
+      "id": "2604.05533",
+      "title": "Experience Transfer for Multimodal LLM Agents in Minecraft Game",
+      "authors": "Chenghao Li, Jun Liu, Songbo Zhang, Huadong Jian, Hao Ni, Lik-Hang Lee, Sung-Ho Bae, Guoqing Wang, Yang Yang, Chaoning Zhang",
+      "abstract": "Multimodal LLM agents operating in complex game environments must continually reuse past experience to solve new tasks efficiently. In this work, we propose Echo, a transfer-oriented memory framework that enables agents to derive actionable knowledge from prior interactions rather than treating memory as a passive repository of static records. To make transfer explicit, Echo decomposes reusable knowledge into five dimensions: structure, attribute, process, function, and interaction. This formulation allows the agent to identify recurring patterns shared across different tasks and infer what prior experience remains applicable in new situations. Building on this formulation, Echo leverages In-Context Analogy Learning (ICAL) to retrieve relevant experiences and adapt them to unseen tasks through contextual examples. Experiments in Minecraft show that, under a from-scratch learning setting, Echo achieves a 1.3x to 1.7x speed-up on object-unlocking tasks. Moreover, Echo exhibits a burst-like chain-unlocking phenomenon, rapidly unlocking multiple similar items within a short time interval after acquiring transferable experience. These results suggest that experience transfer is a promising direction for improving the efficiency and adaptability of multimodal LLM agents in complex interactive environments.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.36,
+      "quality_score": 1.6,
+      "final_score": 4.23,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.05533",
+      "pdf_link": "https://arxiv.org/pdf/2604.05533.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05533.png"
+      ],
+      "engagement": {
+        "likes": 6,
+        "comments": 1
+      },
+      "submitted_by": "taesiri",
+      "organization": ""
+    },
+    {
+      "id": "2604.05846",
+      "title": "AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning",
+      "authors": "Yuanfu Sun, Kang Li, Dongzhe Fan, Jiajin Liu, Qiaoyu Tan",
+      "abstract": "Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of static, parametric knowledge. Yet existing agentic frameworks treat external information as unstructured text and fail to leverage the topological dependencies inherent in real-world data. To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference. Specifically, we propose AgentGL, the first reinforcement learning (RL)-driven framework for AGL. AgentGL equips an LLM agent with graph-native tools for multi-scale exploration, regulates tool usage via search-constrained thinking to balance accuracy and efficiency, and employs a graph-conditioned curriculum RL strategy to stabilize long-horizon policy learning without step-wise supervision. Across diverse Text-Attributed Graph (TAG) benchmarks and multiple LLM backbones, AgentGL substantially outperforms strong GraphLLMs and GraphRAG baselines, achieving absolute improvements of up to 17.5% in node classification and 28.4% in link prediction. These results demonstrate that AGL is a promising frontier for enabling LLMs to autonomously navigate and reason over complex relational environments. The code is publicly available at https://github.com/sunyuanfu/AgentGL.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.12,
+      "quality_score": 2.3,
+      "final_score": 4.22,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.05846",
+      "pdf_link": "https://arxiv.org/pdf/2604.05846.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05846.png"
+      ],
+      "engagement": {
+        "likes": 2,
+        "comments": 1
+      },
+      "submitted_by": "Yuanfu Sun",
+      "organization": "newyorkuniversity"
+    },
+    {
+      "id": "2604.00698",
+      "title": "Learning to Hint for Reinforcement Learning",
+      "authors": "Yu Xia, Canwen Xu, Zhewei Yao, Julian McAuley, Yuxiong He",
+      "abstract": "Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative advantage and thus no learning signal. For example, if a question is too hard for the reasoner, all sampled rollouts can be incorrect and receive zero reward. Recent work addresses this issue by adding hints or auxiliary scaffolds to such hard questions so that the reasoner produces mixed outcomes and recovers a non-zero update. However, existing hints are usually fixed rather than adapted to the current reasoner, and a hint that creates learning signal under the hinted input does not necessarily improve the no-hint policy used at test time. To this end, we propose Hint Learning for Reinforcement Learning (HiLL), a framework that jointly trains a hinter policy and a reasoner policy during RL. For each hard question, the hinter generates hints online conditioned on the current reasoner's incorrect rollout, allowing hint generation to adapt to the reasoner's evolving errors. We further introduce hint reliance, which measures how strongly correct hinted trajectories depend on the hint. We derive a transferability result showing that lower hint reliance implies stronger transfer from hinted success to no-hint success, and we use this result to define a transfer-weighted reward for training the hinter. Therefore, HiLL favors hints that not only recover informative GRPO groups, but also produce signals that are more likely to improve the original no-hint policy. Experiments across multiple benchmarks show that HiLL consistently outperforms GRPO and prior hint-based baselines, demonstrating the value of adaptive and transfer-aware hint learning for RL. The code is available at https://github.com/Andree-9/HiLL.",
+      "published": "2026-04-01T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.18,
+      "quality_score": 2.0,
+      "final_score": 4.18,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.00698",
+      "pdf_link": "https://arxiv.org/pdf/2604.00698.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.00698.png"
+      ],
+      "engagement": {
+        "likes": 3,
+        "comments": 1
+      },
+      "submitted_by": "Yu Xia",
+      "organization": "Snowflake"
+    },
+    {
+      "id": "2604.07343",
+      "title": "Personalized RewardBench: Evaluating Reward Models with Human Aligned Personalization",
+      "authors": "Qiyao Ma, Dechen Gao, Rui Cai, Boqi Zhao, Hanchu Zhou, Junshan Zhang, Zhe Zhao",
+      "abstract": "Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response quality are prevalent, evaluating how well reward models account for individual user preferences remains an open challenge. To bridge this gap, we introduce Personalized RewardBench, a novel benchmark designed to rigorously assess reward models' capacity to model personalized preferences. We construct chosen and rejected response pairs based on strict adherence to (or violation of) user-specific rubrics, ensuring that preference distinctions are uniquely tailored to the individual. In particular, human evaluations confirm that the primary discriminative factor between pairs is strictly personal preference, with both responses maintaining high general quality (e.g., correctness, relevance and helpfulness). Extensive testing reveals that existing state-of-the-art reward models struggle significantly with personalization, peaking at an accuracy of just 75.94%. Crucially, because an effective reward model benchmark should predict a reward model's performance on downstream tasks, we conduct experiments demonstrating that our benchmark exhibits a significantly higher correlation with downstream performance in both Best-of-N (BoN) sampling and Proximal Policy Optimization (PPO) compared to existing baselines. These findings establish Personalized RewardBench as a robust and accurate proxy for evaluating reward models' performance in downstream applications.",
+      "published": "2026-04-08T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.18,
+      "quality_score": 2.0,
+      "final_score": 4.18,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.07343",
+      "pdf_link": "https://arxiv.org/pdf/2604.07343.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.07343.png"
+      ],
+      "engagement": {
+        "likes": 3,
+        "comments": 1
+      },
+      "submitted_by": "Rui(Yanson) Cai",
+      "organization": "ucdavis"
+    },
+    {
+      "id": "2604.04356",
+      "title": "REAM: Merging Improves Pruning of Experts in LLMs",
+      "authors": "Saurav Jha, Maryam Hashemzadeh, Ali Saheb Pasand, Ali Parviz, Min-Joong Lee, Boris Knyazev",
+      "abstract": "Mixture-of-Experts (MoE) large language models (LLMs) are among the top-performing architectures. The largest models, often with hundreds of billions of parameters, pose significant memory challenges for deployment. Traditional approaches to reduce memory requirements include weight pruning and quantization. Motivated by the Router-weighted Expert Activation Pruning (REAP) that prunes experts, we propose a novel method, Router-weighted Expert Activation Merging (REAM). Instead of removing experts, REAM groups them and merges their weights, better preserving original performance. We evaluate REAM against REAP and other baselines across multiple MoE LLMs on diverse multiple-choice (MC) question answering and generative (GEN) benchmarks. Our results reveal a trade-off between MC and GEN performance that depends on the mix of calibration data. By controlling the mix of general, math and coding data, we examine the Pareto frontier of this trade-off and show that REAM often outperforms the baselines and in many cases is comparable to the original uncompressed models.",
+      "published": "2026-04-06T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.18,
+      "quality_score": 2.0,
+      "final_score": 4.18,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.04356",
+      "pdf_link": "https://arxiv.org/pdf/2604.04356.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.04356.png"
+      ],
+      "engagement": {
+        "likes": 3,
+        "comments": 3
+      },
+      "submitted_by": "Boris Knyazev",
+      "organization": "SamsungSAILMontreal"
+    },
+    {
+      "id": "2604.05939",
+      "title": "Context-Value-Action Architecture for Value-Driven Large Language Model Agents",
+      "authors": "TianZe Zhang, Sirui Sun, Yuhang Xie, Xin Zhang, Zhiqiang Wu, Guojie Song",
+      "abstract": "Large Language Models (LLMs) have shown promise in simulating human behavior, yet existing agents often exhibit behavioral rigidity, a flaw frequently masked by the self-referential bias of current \"LLM-as-a-judge\" evaluations. By evaluating against empirical ground truth, we reveal a counter-intuitive phenomenon: increasing the intensity of prompt-driven reasoning does not enhance fidelity but rather exacerbates value polarization, collapsing population diversity. To address this, we propose the Context-Value-Action (CVA) architecture, grounded in the Stimulus-Organism-Response (S-O-R) model and Schwartz's Theory of Basic Human Values. Unlike methods relying on self-verification, CVA decouples action generation from cognitive reasoning via a novel Value Verifier trained on authentic human data to explicitly model dynamic value activation. Experiments on CVABench, which comprises over 1.1 million real-world interaction traces, demonstrate that CVA significantly outperforms baselines. Our approach effectively mitigates polarization while offering superior behavioral fidelity and interpretability.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.18,
+      "quality_score": 2.0,
+      "final_score": 4.18,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.05939",
+      "pdf_link": "https://arxiv.org/pdf/2604.05939.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.05939.png"
+      ],
+      "engagement": {
+        "likes": 3,
+        "comments": 2
+      },
+      "submitted_by": "Rajkumar rawal",
+      "organization": "PekingUniversity"
+    },
+    {
+      "id": "2604.06168",
+      "title": "Action Images: End-to-End Policy Learning via Multiview Video Generation",
+      "authors": "Haoyu Zhen, Zixian Gao, Qiao Sun, Yilin Zhao, Yuncong Yang, Yilun Du, Tsun-Hsuan Wang, Yi-Ling Qiao, Chuang Gan",
+      "abstract": "World action models (WAMs) have emerged as a promising direction for robot policy learning, as they can leverage powerful video backbones to model the future states. However, existing approaches often rely on separate action modules, or use action representations that are not pixel-grounded, making it difficult to fully exploit the pretrained knowledge of video models and limiting transfer across viewpoints and environments. In this work, we present Action Images, a unified world action model that formulates policy learning as multiview video generation. Instead of encoding control as low-dimensional tokens, we translate 7-DoF robot actions into interpretable action images: multi-view action videos that are grounded in 2D pixels and explicitly track robot-arm motion. This pixel-grounded action representation allows the video backbone itself to act as a zero-shot policy, without a separate policy head or action module. Beyond control, the same unified model supports video-action joint generation, action-conditioned video generation, and action labeling under a shared representation. On RLBench and real-world evaluations, our model achieves the strongest zero-shot success rates and improves video-action joint generation quality over prior video-space world models, suggesting that interpretable action images are a promising route to policy learning.",
+      "published": "2026-04-07T00:00:00.000Z",
+      "categories": [],
+      "relevance_score": 1.0,
+      "recency_score": 3.0,
+      "popularity_score": 0.54,
+      "quality_score": 0.8,
+      "final_score": 4.14,
+      "matched_domain": "daily_papers",
+      "matched_keywords": [],
+      "link": "https://huggingface.co/papers/2604.06168",
+      "pdf_link": "https://arxiv.org/pdf/2604.06168.pdf",
+      "source": "huggingface",
+      "media_urls": [
+        "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2604.06168.png"
+      ],
+      "engagement": {
+        "likes": 9,
+        "comments": 1
+      },
+      "submitted_by": "taesiri",
+      "organization": ""
+    }
+  ],
+  "total_found": 50,
+  "total_filtered": 0,
+  "search_date": "2026-04-09"
+}