相关论文: Video-Browser: Towards Agentic Open-web Video Brow…
Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented…
Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video…
Deep reasoning is fundamental for solving complex tasks, especially in vision-centric scenarios that demand sequential, multimodal understanding. However, existing benchmarks typically evaluate agents with fully synthetic, single-turn…
The surging demand for adapting long-form cinematic content into short videos has motivated the need for versatile automatic video compilation systems. However, existing compilation methods are limited to predefined tasks, and the community…
Learning high-quality video representation has shown significant applications in computer vision and remains challenging. Previous work based on mask autoencoders such as ImageMAE and VideoMAE has proven the effectiveness of learning…
Recent advancements in visual generative models have enabled high-quality image and video generation, opening diverse applications. However, evaluating these models often demands sampling hundreds or thousands of images or videos, making…
Despite significant advances in autonomous web navigation, current methods remain far from human-level performance in complex web environments. We argue that this limitation stems from Topological Blindness, where agents are forced to…
While there is overall agreement that future technology for organizing, browsing and searching videos hinges on the development of methods for high-level semantic understanding of video, so far no consensus has been reached on the best way…
For many applications with limited computation, communication, storage and energy resources, there is an imperative need of computer vision methods that could select an informative subset of the input video for efficient processing at or…
This paper addresses the critical and underexplored challenge of long video understanding with low computational budgets. We propose LongVideo-R1, an active, reasoning-equipped multimodal large language model (MLLM) agent designed for…
Recent streaming video understanding methods increasingly rely on complex memory mechanisms to handle long video streams. We challenge this trend with a simple finding: a sliding-window baseline that feeds only the most recent N frames to…
We present PresentAgent, a multimodal agent that transforms long-form documents into narrated presentation videos. While existing approaches are limited to generating static slides or text summaries, our method advances beyond these…
Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require iterative search planning and reasoning over search results.…
Visual agents operating in the wild must respond to queries precisely when sufficient evidence first appears in a video stream, a critical capability that is overlooked by conventional video LLMs evaluated in offline settings. The shift to…
Despite advancements in Video Large Language Models (Vid-LLMs) improving multimodal understanding, challenges persist in streaming video reasoning due to its reliance on contextual information. Existing paradigms feed all available…
One of the fundamental problems in digital agents is their lack of understanding of their environment. For instance, a web browsing agent may get lost in unfamiliar websites, uncertain what pages must be visited to achieve its goals. To…
We introduce PhysicalAgent, an agentic framework for robotic manipulation that integrates iterative reasoning, diffusion-based video generation, and closed-loop execution. Given a textual instruction, our method generates short video…
Long video understanding poses unique challenges due to their temporal complexity and low information density. Recent works address this task by sampling numerous frames or incorporating auxiliary tools using LLMs, both of which result in…
In this work, we propose MetaAgent, an agentic paradigm inspired by the principle of learning-by-doing, where expertise is developed through hands-on practice and continual self-improvement. MetaAgent starts with a minimal workflow,…
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding responses with retrieved information. As an emerging paradigm, Agentic RAG further enhances this process by introducing autonomous LLM agents into the…