arXiv Computer Vision September 10, 2026 By Zhe Gao, Shiyu Shen, Taifeng Chai, Weinong Wang, Haotian Xu, Xing Wu, Wenbin Li, Qi Fan, Yang Gao, Dacheng Tao

VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning

Read the original on arXiv Computer Vision →

VideoTIR introduces a reinforcement‑learning approach to improve long‑video understanding by encouraging multimodal large language models to use comprehensive multi‑level toolkits efficiently. It combines Zero‑RL and SFT cold‑starting strategies to help models retrieve and focus on meaningful video segments, images, and regions, thereby reducing hallucinations. The method includes Toolkit Action Grouped Policy Optimization (TAGPO) to streamline tool‑calling and a sandbox‑based trajectory synthesis framework for high‑quality data, achieving strong results on three long‑video QA benchmarks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI

Aug 28

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models

CounterVid introduces a scalable counterfactual video generation framework that creates videos differing only in actions or temporal structure while keeping scene context intact. The approach uses multimodal LLMs for action proposals and diffusion models for editing, producing a synthetic dataset of ~26k preference pairs for action recognition and sequence ordering. With the MixDPO optimization method, the authors demonstrate significant improvements in action recognition and temporal ordering on Qwen2.5‑VL and InternVL3 backbones, while maintaining overall video understanding.

By Tobia Poppi, Burak Uzkent, Amanmeet Garg, Lucas Porto, Garin Kessler, Yezhou Yang, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara, Florian Schiffers

llms diffusion multimodal benchmarks safety

arXiv AI

Aug 25

Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents

arXiv:2608.23329v1 Announce Type: cross Abstract: Open-world video understanding often requires a model to locate sparse visual evidence and acquire external knowledge that is absent from the video a...

By Wenqi Liu, Shijie Ma, Yunxiao Wang, Meng Liu, Qile Su, Han Liu, Bohan Hou, Xuanyu Zheng, Changyi Liu, Tianke Zhang, Haonan Fan, Kaiyu Jiang, Yingxin Li, Jiankang Chen, Xu Wang, Bin Wen, Tingting Gao, Han Li, Jianhua Yin, Yinwei Wei, Xuemeng Song

agents reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jul 20

Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding

arXiv:2607. 15778v1 Announce Type: cross Abstract: Video Large Language Models (Video LLMs) have made significant advancements in various video understanding tasks.

By Wei Feng, Xin Wang, Yu-Wei Zhan, Yuwei Zhou, Wenwu Zhu

llms reinforcement-learning benchmarks

arXiv AI

Jun 30

Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task

arXiv:2512. 10359v1 Announce Type: cross Abstract: Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios.

By Sunqi Fan, Jiashuo Cui, Meng-Hao Guo, Shuojin Yang

llms agents nlp multimodal

arXiv Computer Vision

Aug 21

Video Evidence to Reasoning Efficient Video Understanding via Explicit Evidence Grounding

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

llms reinforcement-learning multimodal benchmarks safety

arXiv Machine Learning

Sep 1

SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding

arXiv:2604.12335v2 Announce Type: replace-cross Abstract: Training multimodal large language models (MLLMs) for video understanding requires large-scale annotated data spanning diverse tasks such as...

By Tanzila Rahman, Renjie Liao, Leonid Sigal

llms computer-vision nlp fine-tuning multimodal

One email a morning, machine-written

Related stories

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models

Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents

Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding

Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task

Video Evidence to Reasoning Efficient Video Understanding via Explicit Evidence Grounding

SynMulti: Synthetic-to-Real Learning for Multimodal Video Understanding