Spotlight on Token Perception for Multimodal Reinforcement Learning Paper • 2510.09285 • Published 21 days ago • 35
Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Delibration Paper • 2509.14760 • Published Sep 18 • 52
WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents Paper • 2509.06501 • Published Sep 8 • 78
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models Paper • 2508.09834 • Published Aug 13 • 53
STITCH: Simultaneous Thinking and Talking with Chunked Reasoning for Spoken Language Models Paper • 2507.15375 • Published Jul 21 • 30
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs Paper • 2506.19290 • Published Jun 24 • 52
SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks Paper • 2506.10954 • Published Jun 12 • 52
VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models Paper • 2505.23656 • Published May 29 • 25
Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations Paper • 2506.04633 • Published Jun 5 • 19
Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning Paper • 2506.04207 • Published Jun 4 • 48
CSVQA: A Chinese Multimodal Benchmark for Evaluating STEM Reasoning Capabilities of VLMs Paper • 2505.24120 • Published May 30 • 49
SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond Paper • 2505.19641 • Published May 26 • 67
The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models Paper • 2505.22617 • Published May 28 • 130
FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow Paper • 2505.17399 • Published May 23 • 14
OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning Paper • 2505.08617 • Published May 13 • 41
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping Paper • 2505.15612 • Published May 21 • 34
Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Paper • 2505.14810 • Published May 20 • 62
Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark Paper • 2501.05444 • Published Jan 9 • 3