English
Related papers

Related papers: STEP: Enhancing Video-LLMs' Compositional Reasonin…

200 papers

Despite their powerful text generation capabilities, large language models (LLMs) still struggle to effectively utilize external tools to solve complex tasks, a challenge known as tool learning. Existing methods primarily rely on supervised…

Computation and Language · Computer Science 2025-08-19 Yuanqing Yu , Zhefan Wang , Weizhi Ma , Shuai Wang , Chuhan Wu , Zhiqiang Guo , Min Zhang

The improved competence of generative models can help building multi-modal virtual assistants that leverage modalities beyond language. By observing humans performing multi-step tasks, one can build assistants that have situational…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Pha Nguyen , Sailik Sengupta , Girik Malik , Arshit Gupta , Bonan Min

Large Language Models (LLMs) and agent-based systems often struggle with compositional generalization due to a data bottleneck in which complex skill combinations follow a long-tailed, power-law distribution, limiting both…

Computation and Language · Computer Science 2026-01-08 Yifan Wei , Li Du , Xiaoyan Yu , Yang Feng , Angsheng Li

Breaking down a problem into intermediate steps has demonstrated impressive performance in Large Language Model (LLM) reasoning. However, the growth of the reasoning chain introduces uncertainty and error accumulation, making it challenging…

Computation and Language · Computer Science 2023-10-27 Yuxi Xie , Kenji Kawaguchi , Yiran Zhao , Xu Zhao , Min-Yen Kan , Junxian He , Qizhe Xie

Multimodal large language models (LLMs) have made rapid progress in visual understanding, yet their extension from images to videos often reduces to a naive concatenation of frame tokens. In this work, we investigate what video finetuning…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Ruiqi Yang , Tian Yun , Zihan Wang , Ellie Pavlick

The "Thinking with Text" and "Thinking with Images" paradigms significantly improve the reasoning abilities of large language models (LLMs) and Vision-Language Models (VLMs). However, these paradigms have inherent limitations. (1) Images…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Jingqi Tong , Yurong Mou , Hangcheng Li , Mingzhe Li , Yongzhuo Yang , Ming Zhang , Qiguang Chen , Tianyi Liang , Xiaomeng Hu , Yining Zheng , Xinchi Chen , Jun Zhao , Xuanjing Huang , Xipeng Qiu

First-person action recognition is a challenging task in video understanding. Because of strong ego-motion and a limited field of view, many backgrounds or noisy frames in a first-person video can distract an action recognition model during…

Computer Vision and Pattern Recognition · Computer Science 2021-12-03 Lijin Yang , Yifei Huang , Yusuke Sugano , Yoichi Sato

Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Xuchen Li , Xuzhao Li , Shiyu Hu , Kaiqi Huang , Wentao Zhang

In this paper, we present a spatio-temporal tendency reasoning (STR) network for recovering human body pose and shape from videos. Previous approaches have focused on how to extend 3D human datasets and temporal-based learning to promote…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Boyang Zhang , SuPing Wu , Hu Cao , Kehua Ma , Pan Li , Lei Lin

Video reasoning requires a fine-grained understanding of the temporal dependencies and event-level relations between objects and events in videos. Current Multimodal Large Language Models (MLLMs) are prone to severe temporal hallucinations…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Zixu Cheng , Da Li , Jian Hu , Yuhang Zang , Ziquan Liu , Shaogang Gong , Wei Li

Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hallucinations. In particular, these methods tend to perform reasoning solely relying on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Qizhong Tan , Zhuotao Tian , Guangming Lu , Jun Yu , Wenjie Pei

Although most current large multimodal models (LMMs) can already understand photos of natural scenes and portraits, their understanding of abstract images, e.g., charts, maps, or layouts, and visual reasoning capabilities remains quite…

Computer Vision and Pattern Recognition · Computer Science 2024-10-04 Wenqi Zhang , Zhenglin Cheng , Yuanyu He , Mengna Wang , Yongliang Shen , Zeqi Tan , Guiyang Hou , Mingqian He , Yanna Ma , Weiming Lu , Yueting Zhuang

Real-world reasoning often requires combining information across modalities, connecting textual context with visual cues in a multi-hop process. Yet, most multimodal benchmarks fail to capture this ability: they typically rely on single…

Machine Learning · Computer Science 2026-04-03 Junyoung Sung , Seungwoo Lyu , Minjun Kim , Sumin An , Arsha Nagrani , Paul Hongsuck Seo

The video reasoning ability of multimodal large language models (MLLMs) is crucial for downstream tasks like video question answering and temporal grounding. While recent approaches have explored text-based chain-of-thought (CoT) reasoning…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Haoji Zhang , Xin Gu , Jiawen Li , Chixiang Ma , Sule Bai , Chubin Zhang , Bowen Zhang , Zhichao Zhou , Dongliang He , Yansong Tang

Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Hongyu Li , Jinyu Chen , Ziyu Wei , Shaofei Huang , Tianrui Hui , Jialin Gao , Xiaoming Wei , Si Liu

The application of visual instruction tuning and other post-training techniques has significantly enhanced the capabilities of Large Language Models (LLMs) in visual understanding, enriching Vision-Language Models (VLMs) with more…

Computer Vision and Pattern Recognition · Computer Science 2025-06-11 Mingjie Xu , Andrew Estornell , Hongzheng Yang , Yuzhi Zhao , Zhaowei Zhu , Qi Xuan , Jiaheng Wei

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to…

Computer Vision and Pattern Recognition · Computer Science 2026-02-04 Ming Nie , Dan Ding , Chunwei Wang , Yuanfan Guo , Jianhua Han , Hang Xu , Li Zhang

We introduce VideoComp, a benchmark and learning framework for advancing video-text compositionality understanding, aimed at improving vision-language models (VLMs) in fine-grained temporal alignment. Unlike existing benchmarks focused on…

Computer Vision and Pattern Recognition · Computer Science 2025-04-11 Dahun Kim , AJ Piergiovanni , Ganesh Mallya , Anelia Angelova

Spatio-temporal video grounding (STVG) requires localizing a target object in untrimmed videos both temporally and spatially from natural language descriptions. Despite their strong language understanding, multimodal large language models…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Xin Gu , Haoji Zhang , Qihang Fan , Jingxuan Niu , Zhipeng Zhang , Libo Zhang , Guang Chen , Fan Chen , Longyin Wen , Sijie Zhu

We study video-grounded dialogue generation, where a response is generated based on the dialogue context and the associated video. The primary challenges of this task lie in (1) the difficulty of integrating video data into pre-trained…

Computation and Language · Computer Science 2022-10-25 Xueliang Zhao , Yuxuan Wang , Chongyang Tao , Chenshuo Wang , Dongyan Zhao