Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs Paper • 2608.01755 • Published 3 days ago • 135
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published 8 days ago • 139
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published 15 days ago • 309
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Paper • 2607.16617 • Published 19 days ago • 141
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published 18 days ago • 166
Learning from the Self-future: On-policy Self-distillation for dLLMs Paper • 2606.18195 • Published Jun 16 • 77
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 126
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 253