WARP: Weight-Space Analysis for Recovering Training Data Portfolios Paper • 2607.01686 • Published 19 days ago • 9
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning Paper • 2606.32017 • Published 21 days ago • 12
EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation Paper • 2605.23271 • Published May 22 • 81
DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards Paper • 2605.21467 • Published May 20 • 207
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration Paper • 2605.20025 • Published May 19 • 191
BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE Paper • 2605.14438 • Published May 14 • 5