paper-with-me

홈 › Papers

UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist

2025-11-11 · Zhengyang Liang, Daoan Zhang, Huichi Zhou, Rui Huang, Bobo Li, Yuechen Zhang, Shengqiong Wu, Xiaohan Wang, Jiebo Luo, Lizi Liao, Hao Fei arxiv

While specialized AI models excel at isolated video tasks like generation or understanding, real-world applications demand complex, iterative workflows that combine these capabilities. To bridge this gap, we introduce UniVA, an open-source, omni-capable multi-agent framework for next-generation video generalists that unifies video understanding, segmentation, editing, and generation into cohesive workflows. UniVA employs a Plan-and-Act dual-agent architecture that drives a highly automated and proactive workflow: a planner agent interprets user intentions and decomposes them into structured video-processing steps, while executor agents execute these through modular, MCP-based tool servers (for analysis, generation, editing, tracking, etc.). Through a hierarchical multi-level memory (global knowledge, task context, and user-specific preferences), UniVA sustains long-horizon reasoning, contextual continuity, and inter-agent communication, enabling interactive and self-reflective video creation with full traceability. This design enables iterative and any-conditioned video workflows (e.g., text/image/video-conditioned generation $\rightarrow$ multi-round editing $\rightarrow$ object segmentation $\rightarrow$ compositional synthesis) that were previously cumbersome to achieve with single-purpose models or monolithic video-language models. We also introduce UniVA-Bench, a benchmark suite of multi-step video tasks spanning understanding, editing, segmentation, and generation, to rigorously evaluate such agentic video systems. Both UniVA and UniVA-Bench are fully open-sourced, aiming to catalyze research on interactive, agentic, and general-purpose video intelligence for the next generation of multimodal AI systems. (https://univa.online/)

📄 PDF Abstract BibTeX arXiv:2511.08521

Code (0)

등록된 구현이 없습니다.

Tasks

Object Segmentation

Similar Papers 제목 키워드 기반

Learning sources of variability from high-dimensional observational studies

2023-07-26 · Eric W. Bridgeford, Jaewon Chung, Brian Gilbert, Sambit Panda 외

Causal inference studies whether the presence of a variable influences an observed outcome. As measured by quantities such as the "average treatment effect," this paradigm is employed across numerous biological fields, f…

Causal Inference

UnIVAL: Unified Model for Image, Video, Audio and Language Tasks

2023-07-30 · Mustafa Shukor, Corentin Dancette, Alexandre Rame, Matthieu Cord

Large Language Models (LLMs) have made the ambitious quest for generalist agents significantly far from being a fantasy. A key hurdle for building such general models is the diversity and heterogeneity of tasks and modal…

Out-of-Distribution Generalization

Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots

2025-03-07 · Linqi Ye, Rankun Li, Xiaowen Hu, Jiayi Li 외

This paper introduces Unity RL Playground, an open-source reinforcement learning framework built on top of Unity ML-Agents. Unity RL Playground automates the process of training mobile robots to perform various locomotio…

Unity

Conversational AI Multi-Agent Interoperability, Universal Open APIs for Agentic Natural Language Multimodal Communications

2024-07-28 · Diego Gosmar, Deborah A. Dahl, Emmett Coin

This paper analyses Conversational AI multi-agent interoperability frameworks and describes the novel architecture proposed by the Open Voice Interoperability initiative (Linux Foundation AI and DATA), also known briefly…

Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

2026-01-11 · Chengwen Liu, Xiaomin Yu, Zhuoyue Chang, Zhe Huang 외 arxiv

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 e…

Video Question Answering