English
Related papers

Related papers: Structure Over Scale: Learning Visual Reasoning fr…

200 papers

Large Vision-Language Models (LVLMs) achieve strong performance on visual question answering benchmarks, yet often rely on spurious correlations rather than genuine causal reasoning. Existing evaluations primarily assess the correctness of…

Artificial Intelligence · Computer Science 2026-02-25 Dhita Putri Pratama , Soyeon Caren Han , Yihao Ding

Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at…

Databases · Computer Science 2026-03-31 Wenhan Yu , Zhaoxi Zhang , Wang Chen , Guanqiang Qi , Weikang Li , Lei Sha , Deguo Xia , Jizhou Huang

Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coherent behavior. Unlike humans, who readily infer intentions,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Wenshuo Peng , Gongxuan Wang , Tianmeng Yang , Chuanhao Li , Xiaojie Xu , Hui He , Kaipeng Zhang

Video Large Language Models (Video-LLMs) excel in video understanding but suffer from high inference latency during autoregressive generation. Speculative Decoding (SD) mitigates this by applying a draft-and-verify paradigm, yet existing…

Computation and Language · Computer Science 2026-04-10 Yicheng Ji , Jun Zhang , Jinpeng Chen , Cong Wang , Lidan Shou , Gang Chen , Huan Li

Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Yi Chen , Yuying Ge , Rui Wang , Yixiao Ge , Lu Qiu , Ying Shan , Xihui Liu

We present LoCoVQA, a dynamic benchmark generator for evaluating long-context extractive reasoning in vision language models (VLMs). LoCoVQA augments test examples for mathematical reasoning, VQA, and character recognition tasks with…

Computation and Language · Computer Science 2024-10-07 Aditya Sharma , Michael Saxon , William Yang Wang

While chain-of-thought (CoT) prompting improves reasoning in large language models, its effectiveness in vision-language models (VLMs) remains limited due to over-reliance on textual cues and memorized knowledge. To investigate the visual…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Charles Corbière , Simon Roburin , Syrielle Montariol , Antoine Bosselut , Alexandre Alahi

Visual question answering (VQA) is a challenging multi-modal task that requires not only the semantic understanding of both images and questions, but also the sound perception of a step-by-step reasoning process that would lead to the…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Siwen Luo , Soyeon Caren Han , Kaiyuan Sun , Josiah Poon

Recent pre-trained language models (PLMs) equipped with foundation reasoning skills have shown remarkable performance on downstream complex tasks. However, the significant structure reasoning skill has been rarely studied, which involves…

Computation and Language · Computer Science 2023-07-18 Siyuan Wang , Zhongyu Wei , Jiarong Xu , Taishan Li , Zhihao Fan

Vision-Language Models have made significant progress on many perception-focused tasks. However, their progress on reasoning-focused tasks remains limited due to the lack of high-quality and diverse training data. In this work, we aim to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Yiming Jia , Jiachen Li , Xiang Yue , Bo Li , Ping Nie , Kai Zou , Wenhu Chen

We introduce MAIA (Multimodal AI Assessment), a native-Italian benchmark designed for fine-grained investigation of the reasoning abilities of visual language models on videos. MAIA differs from other available video benchmarks for its…

Logical connectives and their implications on the meaning of a natural language sentence are a fundamental aspect of understanding. In this paper, we investigate whether visual question answering (VQA) systems trained to answer a question…

Computer Vision and Pattern Recognition · Computer Science 2020-07-17 Tejas Gokhale , Pratyay Banerjee , Chitta Baral , Yezhou Yang

Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynamics. World-model VLAs address this by predicting future…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Fuxiang Yang , Donglin Di , Lulu Tang , Xuancheng Zhang , Lei Fan , Hao Li , Chen Wei , Tonghua Su , Baorui Ma

The rapid evolution of video generative models has shifted their focus from producing visually plausible outputs to tackling tasks requiring physical plausibility and logical consistency. However, despite recent breakthroughs such as Veo…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Harold Haodong Chen , Disen Lan , Wen-Jie Shu , Qingyang Liu , Zihan Wang , Sirui Chen , Wenkai Cheng , Kanghao Chen , Hongfei Zhang , Zixin Zhang , Rongjin Guo , Yu Cheng , Ying-Cong Chen

Despite recent advances demonstrating vision-language models' (VLMs) abilities to describe complex relationships in images using natural language, their capability to quantitatively reason about object sizes and distances remains…

Computer Vision and Pattern Recognition · Computer Science 2024-09-17 Yuan-Hong Liao , Rafid Mahmood , Sanja Fidler , David Acuna

While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Le Zhuo , Songhao Han , Yuandong Pu , Boxiang Qiu , Sayak Paul , Yue Liao , Yihao Liu , Jie Shao , Xi Chen , Si Liu , Hongsheng Li

What does it take to build a visual reasoner that works across charts, science, spatial understanding, and open-ended tasks? The strongest vision-language models (VLMs) show such broad visual reasoning is within reach, but the recipe behind…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Gabriel Sarch , Linrong Cai , Qunzhong Wang , Haoyang Wu , Danqi Chen , Zhuang Liu

Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent research suggests current vision-language models (VLMs) trained on curated…

Visual Question Answering (VQA) is a challenge task that combines natural language processing and computer vision techniques and gradually becomes a benchmark test task in multimodal large language models (MLLMs). The goal of our survey is…

Computation and Language · Computer Science 2024-11-27 Jiayi Kuang , Jingyou Xie , Haohao Luo , Ronghao Li , Zhe Xu , Xianfeng Cheng , Yinghui Li , Xika Lin , Ying Shen

Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions, an approach inspired by Chain-of-Thought (CoT) reasoning in language models. Yet even…

Robotics · Computer Science 2026-01-15 Yilin Wu , Anqi Li , Tucker Hermans , Fabio Ramos , Andrea Bajcsy , Claudia Pérez-D'Arpino