3 papers
cs.CV2026
ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving
Xuchang Zhong, He Zheng, Chenxu Zhao +9
World-model-based autonomous driving endows the model with the ability to understand scene evolution. Yet this promise is undermined by the prevailing imagine-then-act paradigm, wh…
cs.CV2026
PerceptDrive: Perception Prior World-Action Modeling with Adaptive Expert Routing for End-to-End Autonomous Driving
Yushan Liu, Tianxiong Lv, Bohua Wang +11
Frozen perception foundation models encode rich geometric, semantic, and dynamic knowledge. Yet narrow conditioning interfaces may attenuate task-relevant cues, while static fusion…
cs.LG2026
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
Yuying Li, Leqi Zheng, Yongzi Yu +6
On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms. Recent OPD methods increasingly focus on…