相关论文: VidBridge-R1: Bridging QA and Captioning for RL-ba…

In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative…

Recent progress in large-scale robotic datasets and vision-language models (VLMs) has advanced research on vision-language-action (VLA) models. However, existing VLA models still face two fundamental challenges: (i) producing precise…

This work concerns video-language pre-training and representation learning. In this now ubiquitous training scheme, a model first performs pre-training on paired videos and text (e.g., video clips and accompanied subtitles) from a large…

Reinforcement learning (RL) has shown strong potential for enhancing reasoning in multimodal large language models, yet existing video reasoning methods often rely on coarse sequence-level rewards or single-factor token selection,…

Generating informative and knowledge-rich image captions remains a challenge for many existing captioning models, which often produce generic descriptions that lack specificity and contextual depth. To address this limitation, we propose…

The performance of Video Question Answering (VideoQA) models is fundamentally constrained by the nature of their supervision, which typically consists of isolated, factual question-answer pairs. This "bag-of-facts" approach fails to capture…

Video temporal grounding (VTG) aims to locate precise segments in videos based on language queries, which is a fundamental challenge in video understanding. While recent Multimodal Large Language Models (MLLMs) have shown promise in…

Knowledge-based Visual Question Answering (VQA) expects models to rely on external knowledge for robust answer prediction. Though significant it is, this paper discovers several leading factors impeding the advancement of current…

Current video understanding models rely on fixed frame sampling strategies, processing predetermined visual inputs regardless of the specific reasoning requirements of each question. This static approach limits their ability to adaptively…

Recent video-text foundation models have demonstrated strong performance on a wide variety of downstream video understanding tasks. Can these video-text models genuinely understand the contents of natural videos? Standard video-text…

Recent breakthroughs in reasoning models have markedly advanced the reasoning capabilities of large language models, particularly via training on tasks with verifiable rewards. Yet, a significant gap persists in their adaptation to real…

Recent works on large language models (LLMs) have successfully demonstrated the emergence of reasoning capabilities via reinforcement learning (RL). Although recent efforts leverage group relative policy optimization (GRPO) for MLLMs…

Reasoning-centric video object segmentation is an inherently complex task: the query often refers to dynamics, causality, and temporal interactions, rather than static appearances. Yet existing solutions generally collapse these factors…

What makes good representations for video understanding, such as anticipating future activities, or answering video-conditioned questions? While earlier approaches focus on end-to-end learning directly from video pixels, we propose to…

Large pre-trained multimodal models have demonstrated significant success in a range of downstream tasks, including image captioning, image-text retrieval, visual question answering (VQA), etc. However, many of these methods rely on…

Visual Question Answering (VQA) has attracted attention from both computer vision and natural language processing communities. Most existing approaches adopt the pipeline of representing an image via pre-trained CNNs, and then using the…

Image captioning is one of the most fundamental tasks in computer vision. Owing to its open-ended nature, it has received significant attention in the era of multimodal large language models (MLLMs). In pursuit of ever more detailed and…

While generative video models have achieved remarkable visual fidelity, their capacity to internalize and reason over implicit world rules remains a critical yet under-explored frontier. To bridge this gap, we present RISE-Video, a…

This paper proposes the first video-grounded entailment tree reasoning method for commonsense video question answering (VQA). Despite the remarkable progress of large visual-language models (VLMs), there are growing concerns that they learn…

As AI-generated video becomes increasingly pervasive across media platforms, the ability to reliably distinguish synthetic content from authentic footage has become both urgent and essential. Existing approaches have primarily treated this…