Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs Paper • 2608.01755 • Published 16 days ago • 141
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Paper • 2607.16617 • Published Jul 18 • 143
VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance Paper • 2607.14660 • Published Jul 16 • 9
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published Jun 28 • 170
StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration Paper • 2605.25659 • Published May 25 • 17