Related papers: ReTool-Video: Recursive Tool-Using Video Agents wi…

Video reasoning has emerged as a critical capability for multimodal large language models (MLLMs), requiring models to move beyond static perception toward coherent understanding of temporal dynamics in complex scenes. Yet existing MLLMs…

Video understanding has been considered as one critical step towards world modeling, which is an important long-term problem in AI research. Recently, multimodal foundation models have shown such potential via large-scale pretraining. These…

Precise video retrieval requires multi-modal correlations to handle unseen vocabulary and scenes, becoming more complex for lengthy videos where models must perform effectively without prior training on a specific dataset. We introduce a…

Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to…

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models. However, existing methods rely solely on outcome rewards, without explicitly optimizing verification or leveraging…

This paper presents an integrated multi-agents architecture for indexing and retrieving video information.The focus of our work is to elaborate an extensible approach that gathers a priori almost of the mandatory tools which palliate to the…

The scaling of large language models to encode all the world's knowledge in model parameters is unsustainable and has exacerbated resource barriers. Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to…

Temporal Video Grounding (TVG), which requires pinpointing relevant temporal segments from video based on language query, has always been a highly challenging task in the field of video understanding. Videos often have a larger volume of…

Vision-Language Models (VLMs) have enabled substantial progress in video understanding by leveraging cross-modal reasoning capabilities. However, their effectiveness is limited by the restricted context window and the high computational…

Tool learning aims to enhance and expand large language models' (LLMs) capabilities with external tools, which has gained significant attention recently. Current methods have shown that LLMs can effectively handle a certain amount of tools…

We introduce VisTA, a new reinforcement learning framework that empowers visual agents to dynamically explore, select, and combine tools from a diverse library based on empirical performance. Existing methods for tool-augmented reasoning…

Agentic multimodal models should not only comprehend text and images, but also actively invoke external tools, such as code execution environments and web search, and integrate these operations into reasoning. In this work, we introduce…

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…

Recent advances in large language models have significantly improved textual reasoning through the effective use of Chain-of-Thought (CoT) and reinforcement learning. However, extending these successes to vision-language tasks remains…

While recent multimodal models have shown progress in vision-language tasks, small-scale variants still struggle with the fine-grained temporal reasoning required for video understanding. We introduce ReasonAct, a method that enhances video…

Referring-based Video Object Segmentation is a multimodal problem that requires producing fine-grained segmentation results guided by external cues. Traditional approaches to this task typically involve training specialized models, which…

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.…

Reranking is a critical component of modern retrieval systems, which typically pair an efficient first-stage retriever with a more expressive model to refine results. While large reasoning models have driven rapid progress in text-centric…

Reinforcement learning for agentic multimodal models often suffers from interaction collapse, where models learn to reduce tool usage and multi-turn reasoning, limiting the benefits of agentic behavior. We introduce PyVision-RL, a…

We propose VideoPerceiver, a novel video multimodal large language model (VMLLM) that enhances fine-grained perception in video understanding, addressing VMLLMs' limited ability to reason about brief actions in short clips or rare transient…