相关论文: Reframe Anything: LLM Agent for Open World Video R…

Long video understanding has emerged as an increasingly important yet challenging task in computer vision. Agent-based approaches are gaining popularity for processing long videos, as they can handle extended sequences and integrate various…

Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to…

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly…

The generalization of vision-language-action (VLA) models heavily relies on diverse training data. However, acquiring large-scale data for robot manipulation across varied object appearances is costly and labor-intensive. To address this…

Given the vast amounts of video available online, and recent breakthroughs in object detection with static images, object detection in video offers a promising new frontier. However, motion blur and compression artifacts cause substantial…

Despite the remarkable success of the LLaVA architecture for vision-language tasks, its design inherently struggles to effectively integrate visual features due to the inherent mismatch between text and vision modalities. We tackle this…

Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration agents, powered by vision-language models and large…

Vision-Language-Action (VLA) models have recently demonstrated strong performance across embodied tasks. Modern VLAs commonly employ diffusion action experts to efficiently generate high-precision continuous action chunks, while…

Large Language Models (LLMs) have been widely used in various tasks, motivating us to develop an LLM-based assistant for videos. Instead of training from scratch, we propose a module to transform arbitrary well-trained image-based LLMs into…

In high-stakes domains, small task-specific vision models are crucial due to their low computational requirements and the availability of numerous methods to explain their results. However, these explanations often reveal that the models do…

We present Lunima-OmniLV (abbreviated as OmniLV), a universal multimodal multi-task framework for low-level vision that addresses over 100 sub-tasks across four major categories: image restoration, image enhancement, weak-semantic dense…

The Large Vision-Language Model (LVLM) has enhanced the performance of various downstream tasks in visual-language understanding. Most existing approaches encode images and videos into separate feature spaces, which are then fed as inputs…

Pre-trained video large language models (Video LLMs) exhibit remarkable reasoning capabilities, yet adapting these models to new tasks involving additional modalities or data types (e.g., audio or 3D information) remains challenging. In…

Vision-Language-Action (VLA) models have gained popularity for learning robotic manipulation tasks that follow language instructions. State-of-the-art VLAs, such as OpenVLA and $\pi_{0}$, were trained on large-scale, manually labeled action…

Image ad understanding is a crucial task with wide real-world applications. Although highly challenging with the involvement of diverse atypical scenes, real-world entities, and reasoning over scene-texts, how to interpret image ads is…

Despite the rapid development of video Large Language Models (LLMs), a comprehensive evaluation is still absent. In this paper, we introduce a unified evaluation that encompasses multiple video tasks, including captioning, question and…

Building models that comprehends videos and responds specific user instructions is a practical and challenging topic, as it requires mastery of both vision understanding and knowledge reasoning. Compared to language and image modalities,…

Recent advances in multimodal LLMs and systems that use tools for long-video QA point to the promise of reasoning over hour-long episodes. However, many methods still compress content into lossy summaries or rely on limited toolsets,…

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention…

Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…