Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published May 7 • 238
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards Paper • 2605.21467 • Published May 20 • 207
SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents Paper • 2605.21384 • Published May 20 • 4
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding Paper • 2605.20104 • Published May 19 • 7
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution Paper • 2605.18401 • Published May 18 • 130
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation Paper • 2604.28196 • Published Apr 30 • 74
nraptisss/Qwen3-8B-TMF921-Intent-QLoRA-qwen3-8b-qlora-20260501-083834 Text Generation • Updated May 7 • 4 • 2