Aug 10, 2026 · Artificial Intelligence

DriveTeach-VLA Bridges Autonomous Driving Scenes and Foundation Model Pre‑training via Image Trajectories

The ECCV‑2026 paper introduces DriveTeach‑VLA, a vision‑language‑action model that improves autonomous driving by distilling traffic‑aware visual cues and projecting BEV trajectories onto image pixels, achieving state‑of‑the‑art PDMS scores of 90.4 on NAVSIM and up to 92.7 with a trajectory selector, while detailing the training pipeline, visual distillation, 2D‑TGP prompting, and extensive ablations.

Vision-Language-Actionautonomous drivingfoundation models

0 likes · 11 min read

DriveTeach-VLA Bridges Autonomous Driving Scenes and Foundation Model Pre‑training via Image Trajectories

Data Party THU

Jul 5, 2026 · Artificial Intelligence

Is One‑Prompt Image Generation Obsolete? Meet GenEvolve’s Tool‑Orchestrated Agents

GenEvolve introduces a self‑evolving image‑generation agent that orchestrates search, reference retrieval, and knowledge‑query tools into a prompt‑reference program, training via teacher‑student SFT and visual‑experience self‑distillation to achieve higher KScore on open‑source and strong generators.

Tool Orchestrationagentic AIbenchmark

0 likes · 9 min read

Is One‑Prompt Image Generation Obsolete? Meet GenEvolve’s Tool‑Orchestrated Agents