Knowledge distillation improves a student model's reasoning ability through supervision from a teacher. On-policy self-distillation (OPSD) uses the same model as both teacher and student under different contexts: the student generates reasoning trajectories from the question alone, while the teacher additionally receiv...
TrafficImag is introduced, the first benchmark for counterfactual roadside traffic video generation, which combines a large-scale roadside dataset with an executable protocol that supports behavior reasoning, intervention-aware image editing, and conditional video generation.
Xiang-Yu Li, Tian-Yi Wang, Zhi-Hao Dou et al.· 0 citations
Improvements show that an explicit graph world model harness can substantially improve the reliability and efficiency of long-horizon embodied planning across compact and frontier hosted LLM capabilities.
Rui-Yang Wang, Hao-Lun Hsu, S. Mehta et al.· arXiv.org· 0 citations
This work proposes AMRM-Pure, a purification framework that denoises adversarial inputs by preserving patch-level semantics, and formulate this process as a tractable optimization problem with respect to the input.
Zhihao Dou, Zhiqiang Gao, Dongfei Cui et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.