The paper introduces SAVER, a dense-to-sparse post‑training framework that leverages dense video views as training‑time references to improve sparse‑frame inference. By optimizing paired dense and sparse views with grounding and reliability‑gated reference rewards, SAVER learns to preserve task‑relevant temporal evidence while using far fewer frames. Evaluated on three temporal grounding and six video question‑answering benchmarks, SAVER consistently outperforms dense‑frame baselines, matching or surpassing them with substantially reduced frame budgets.
By Wenfang Sun, Yingjun Du, Cees G. M. Snoek
arXiv:2602. 13602v2 Announce Type: replace-cross Abstract: We present \revise (\underline{Re}asoning with \underline{Vi}deo \underline{S}parsity), a multi-round agent for video question answering (VQA).
By Chenwei Xu, Zhen Ye, Shang Wu, Weijian Li, Zihan Wang, Zhuofan Xia, Lie Lu, Pranav Maneriker, Fan Du, Manling Li, Han Liu
arXiv:2601. 07761v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) face a fundamental dilemma in video reasoning: they are caught between the prohibitive computational costs of verbose reasoning and the hallucination risks of efficient, ungrounded approaches.
By Yanxiang Huang, Guohua Gao, Zhaoyang Wei
The paper introduces Clue-OPSD, a clue‑privileged on‑policy self‑distillation framework that improves long‑video understanding by focusing on short, question‑relevant clue intervals rather than the entire video. Experiments on multiple benchmarks and Qwen3.5 model scales show that this approach consistently outperforms standard backbone models and competes strongly with supervised post‑training baselines, all while requiring fewer input frames and no additional inference modules.
By Kaishen Wang, Dongdi Zhao, Yijun Liang, Dingqiang Ye, Ruibo Chen, Heng Huang, Di Fu
The paper introduces structured video prompting, a training‑free inference‑time technique that augments input videos with lightweight spatial and temporal structure to provide explicit anchors for evidence organization. By applying this method to two video benchmarks and two open video‑language models, the authors demonstrate performance improvements across several tasks, with gains varying by model and task. The study suggests that failures in video‑language models stem not only from reasoning capacity but also from how video evidence is presented during inference.
By Sadegh Mohammadian
arXiv:2609.39021v1 Announce Type: new
Abstract: Reinforcement learning (RL) has substantially improved the reasoning ability of multimodal language models through verifiable rewards and increasingly...
By Haiying He, Xin Zheng, Shaoli Hu, Shijun Xiao, Xuanhe Liu, Bing Li, Harry Yang
arXiv:2506. 01274v2 Announce Type: replace-cross Abstract: Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame selection strategies, albeit with the rapid development of video-specialized LMMs.
By Hosu Lee, Junho Kim, Hyunjun Kim, Yong Man Ro
arXiv:2607. 24582v1 Announce Type: cross Abstract: Long-video understanding increasingly relies on large vision-language models and tool-augmented reasoning, but most systems apply the same inference procedure to every example regardless of difficulty.
By Jinlong Yang, Wenhao Zhang, Kuanwei Lin, Sijie Cheng
Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video and its parametric memory. While Thinking-with-Video...
arXiv:2610.00757v1 Announce Type: new
Abstract: Long-video question answering is limited by the high cost of visual tokens and by the fixed context width of current VLMs. A long-video question may re...
By Haowen Guan, Shengzhi Li, Shichao Pei
arXiv:2608.20814v1 Announce Type: new
Abstract: Though Multimodal Large Language Models (MLLMs) have shown impressive potential in video understanding, long video understanding (LVU) remains challeng...
By Beibei Zhang, Chao Xu, Jun Lan, Zongyi Li, Lai Wei, Huijia Zhu, Tongwei Ren
The paper introduces STITCH, a training‑free method that partitions videos into semantically meaningful temporal chunks using a frozen video‑text backbone. By detecting changes in the embedding sequence of short video windows, STITCH produces reusable temporal abstractions that can be applied to multiple tasks such as event boundary detection, language‑based moment retrieval, and frame selection for vision‑language models. Experiments show that STITCH performs competitively with specialized methods while requiring no task‑specific training, especially when processing is limited to a few frames or tokens.
By Etienne Casanova, Sevan Brodjian, Pietro Perona