Adapting Image Large Language Models (Image-LLMs) to long-form video is hindered by the large number of redundant visual tokens. Existing video adapters reduce this cost, but their unconstrained projections may generate representations that deviate from the input distribution expected by a frozen Image-LLM, degrading i...
Li-Shuai Gao, Yu-Jie Zhong, Yi-Fan Li et al.· Proceedings of the 34th ACM...· 0 citations
Flow-based image generators achieve strong semantic synthesis but still produce localized structural distortions, such as malformed hands and limbs. Existing post-training methods typically optimize global scalar rewards, which provide weak spatial credit assignment and may alter well-formed regions while correcting lo...
Li-Shuai Gao, Yi-Fan Li, Tong Zhang et al.· Proceedings of the 34th ACM...· 0 citations
This work presents InfoAgent, a training-free framework for evidence-bound visual-symbolic program synthesis, which records factual payloads, evidence provenance, execution routes, and verification obligations in a typed dependency graph and introduces InfoGraphicBench-Evidence, where complete-checklist pass rates on 2...
Yi-Fan Li, Tong Li, Qi Zeng 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.