3 papers
cs.CV2026
Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding
Houlun Chen, Xin Wang, Guangyao Li +4
Long video understanding is challenging due to rich and complicated multimodal clues in long temporal range.Current methods adopt reasoning to improve the model's ability to analyz…
cs.CV2026
VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation
Shikun Sun, Liao Qu, Huichao Zhang +8
Visual generation is dominated by three paradigms: AutoRegressive (AR), diffusion, and Visual AutoRegressive (VAR) models. Unlike AR and diffusion, VARs operate on heterogeneous in…
cs.CV2024
VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
Houlun Chen, Xin Wang, Hong Chen +5
Existing Video Corpus Moment Retrieval (VCMR) is limited to coarse-grained understanding, which hinders precise video moment localization when given fine-grained queries. In this p…