OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization Paper • 2605.17757 • Published 5 days ago • 56
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published 11 days ago • 186
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution Paper • 2605.18401 • Published 5 days ago • 122
Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models Paper • 2605.15961 • Published 8 days ago • 7
llmfan46/MiniMax-M2.7-BF16-ultra-uncensored-heretic Text Generation • 229B • Updated 1 day ago • 291 • 4
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO Paper • 2605.04077 • Published Apr 14 • 7
World2Minecraft: Occupancy-Driven Simulated Scenes Construction Paper • 2604.27578 • Published 23 days ago • 5
From Context to Skills: Can Language Models Learn from Context Skillfully? Paper • 2604.27660 • Published 20 days ago • 162
Operating-Layer Controls for Onchain Language-Model Agents Under Real Capital Paper • 2604.26091 • Published 25 days ago • 6
MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation Paper • 2604.17435 • Published Apr 19 • 3
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published Apr 3 • 629
CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning Paper • 2604.03231 • Published Apr 3 • 7