LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 5 days ago • 182
Video Generation Models are General-Purpose Vision Learners Paper • 2607.09024 • Published 11 days ago • 81
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models Paper • 2606.11324 • Published Jun 9 • 171
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off Paper • 2604.13902 • Published Apr 15 • 62
Crowded in B-Space: Calibrating Shared Directions for LoRA Merging Paper • 2604.16826 • Published Apr 18 • 18
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published Apr 8 • 329
Adam's Law: Textual Frequency Law on Large Language Models Paper • 2604.02176 • Published Apr 2 • 510
Working Notes on Late Interaction Dynamics: Analyzing Targeted Behaviors of Late Interaction Models Paper • 2603.26259 • Published Mar 27 • 8
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence Paper • 2603.28032 • Published Mar 30 • 344