3 papers
cs.AI2026
Scaling Discovery Requires Forgetting
Shangyin Tan, Ben Zhou, Lakshya A Agrawal +8
Automated research with LLM agents has shown promising results in various domains. Through iterative refinement and scored verifiers, LLM agents are capable of discovering new idea…
cs.CV2026
SparseWAM: Driving World-Action Models are Worth 16 Register Tokens
Yixiang Yang, Lizhong Zhang, Xingyu Zhang +6
World Action Models (WAMs) transfer scene-dynamics priors to planning by jointly forecasting future scenes and ego trajectories. However, WAMs built on video generators must genera…
cs.CV2026
SurroundNEXO: Ego-Centric Metric Bridging for Spatially Consistent Geometry in Autonomous Driving
Shuai Yuan, Runxi Tang, Yuzhou Ji +8
Modern autonomous driving depends on accurate metric 3D understanding for perception, reconstruction, and planning, which in turn requires reliable multi-camera depth prediction. H…