TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation Paper • 2605.22355 • Published 2 days ago • 167
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization Paper • 2605.17757 • Published 5 days ago • 60
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution Paper • 2605.18401 • Published 5 days ago • 122
Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation Paper • 2605.11739 • Published 10 days ago • 55
MilaWang/lirpg-fullparam-olmo-3-7b-instruct-sciknoweval-material-a01-nostd-fix-exadv-meta Updated 15 days ago • 1
Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning Paper • 2604.16029 • Published Apr 17 • 23
ViVa: A Video-Generative Value Model for Robot Reinforcement Learning Paper • 2604.08168 • Published Apr 9 • 18
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Paper • 2604.07430 • Published Apr 8 • 187
When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published Apr 9 • 115
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published Mar 27 • 364