3 papers
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…
cs.CL2026
Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs
Wenrui Zhou, Mohamed Hendy, Shu Yang +5
As video large language models (Video-LLMs) become increasingly integrated into real-world applications that demand grounded multimodal reasoning, ensuring their factual consistenc…
cs.SD2025
Teaching Physical Awareness to LLMs through Sounds
Weiguo Wang, Andy Nie, Wenrui Zhou +2
Large Language Models (LLMs) have shown remarkable capabilities in text and multimodal processing, yet they fundamentally lack physical awareness--understanding of real-world physi…