相关论文: Act2See: Emergent Active Visual Perception for Vid…

Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…

Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning. Despite these successes, current benchmarks still follow a…

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

Visual perception in modern Vision-Language Models (VLMs) is constrained by a perceptual bandwidth bottleneck: a broad field of view preserves global context but sacrifices the fine-grained details required for complex reasoning. We argue…

The increasing demand for intelligent systems capable of interpreting and reasoning about visual content requires the development of large Vision-and-Language Models (VLMs) that are not only accurate but also have explicit reasoning…

Vision Language Models (VLMs) perform well on standard video tasks but struggle with physics-related reasoning involving motion dynamics and spatial interactions. We present a novel approach to address this gap by translating physical-world…

Multimodal large language models (MLLMs) are flourishing, but mainly focus on images with less attention than videos, especially in sub-fields such as prompt engineering, video chain-of-thought (CoT), and instruction tuning on videos.…

Integrating vision-language models (VLMs) into end-to-end (E2E) autonomous driving (AD) systems has shown promise in improving scene understanding. However, existing integration strategies suffer from several limitations: they either…

Despite significant advances in Vision Language Models (VLMs), they remain constrained by the complexity and redundancy of visual input. When images contain large amounts of irrelevant information, VLMs are susceptible to interference, thus…

The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in actual visual evidence. However, existing datasets face limitations in scalability due to…

Natural language goes beyond dryly describing visual content. It contains rich abstract concepts to express feeling, creativity and properties that cannot be directly perceived. Yet, current research in Vision Language Models (VLMs) has not…

Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant potential in complex visual tasks through the integration of Chain-of-Thought (CoT) reasoning. However, in Video Question Answering, extended thinking…

Vision Language Models (VLMs) are becoming increasingly integral to multimedia understanding; however, they often struggle with domain-specific video classification tasks, particularly in cases with limited data. This stems from a critical…

Vision-Language Models (VLMs) exhibit remarkable common-sense and semantic reasoning capabilities. However, they lack a grounded understanding of physical dynamics. This limitation arises from training VLMs on static internet-scale…

Human action recognition in long-term videos, characterized by complex backgrounds and subtle action differences, poses significant challenges for traditional deep learning models due to computational overhead, difficulty in capturing…

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…

Vision-language models (VLMs) have recently emerged as a promising paradigm for video anomaly detection (VAD) due to their strong visual reasoning ability and natural language-based explainability. In this paper, we aim to address a key…

Recent video generation models have revealed the emergence of Chain-of-Frame (CoF) reasoning, enabling frame-by-frame visual inference. With this capability, video models have been successfully applied to various visual tasks (e.g., maze…

Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many visually grounded questions can be answered using only…

Reasoning in vision-language models (VLMs) has recently attracted significant attention due to its broad applicability across diverse downstream tasks. However, it remains unclear whether the superior performance of VLMs stems from genuine…