view article Article DeepSeek-V4: a million-token context that agents can actually use 6 days ago • 39
moonshotai/Kimi-K2.6 Image-Text-to-Text • 1.1T • Updated about 5 hours ago • 591k • • 1.16k
Seedance 2.0: Advancing Video Generation for World Complexity Paper • 2604.14148 • Published 15 days ago • 153
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance Paper • 2604.12627 • Published 16 days ago • 99
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 22 days ago • 323
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published 21 days ago • 287
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning Paper • 2604.04746 • Published 22 days ago • 71
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents Paper • 2604.06132 • Published 23 days ago • 118
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale Paper • 2604.04771 • Published 24 days ago • 122