相关论文: CVP: Central-Peripheral Vision-Inspired Multimodal…

Current solutions for efficiently constructing large vision-language (VL) models follow a two-step paradigm: projecting the output of pre-trained vision encoders to the input space of pre-trained language models as visual prompts; and then…

The "style trap" poses a significant challenge for Large Vision-Language Models (LVLMs), hindering robust semantic understanding across diverse visual styles, especially in in-context learning (ICL). Existing methods often fail to…

Multi-view clustering (MVC) aims to explore the common clustering structure across multiple views. Many existing MVC methods heavily rely on the assumption of view consistency, where alignments for corresponding samples across different…

Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism. By revisiting the self-attention responses in Transformers, we empirically observe two…

As a prominent parameter-efficient fine-tuning technique in NLP, prompt tuning is being explored its potential in computer vision. Typical methods for visual prompt tuning follow the sequential modeling paradigm stemming from NLP, which…

We propose the Multiple View Performer (MVP) - a new architecture for 3D shape completion from a series of temporally sequential views. MVP accomplishes this task by using linear-attention Transformers called Performers. Our model allows…

Urban design is a highly visual discipline that requires visualization for informed decision making. However, traditional urban design tools are mostly limited to representations on 2D displays that lack intuitive awareness. The popularity…

Open-world 3D scene understanding is a critical challenge that involves recognizing and distinguishing diverse objects and categories from 3D data, such as point clouds, without relying on manual annotations. Traditional methods struggle…

Recently, polar coordinate-based representations have shown promise for 3D perceptual tasks. Compared to Cartesian methods, polar grids provide a viable alternative, offering better detail preservation in nearby spaces while covering larger…

Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference.…

Real-time rendering and animation of humans is a core function in games, movies, and telepresence applications. Existing methods have a number of drawbacks we aim to address with our work. Triangle meshes have difficulty modeling thin…

We tackle the task of scalable unsupervised object-centric representation learning on 3D scenes. Existing approaches to object-centric representation learning show limitations in generalizing to larger scenes as their learning processes…

Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus…

The event-based Vision-Language Model (VLM) recently has made good progress for practical vision tasks. However, most of these works just utilize CLIP for focusing on traditional perception tasks, which obstruct model understanding…

We present a Collaborative Agent-Based Framework for Multi-Image Reasoning. Our approach tackles the challenge of interleaved multimodal reasoning across diverse datasets and task formats by employing a dual-agent system: a language-based…

Precise spatial understanding from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs), as their visual representations are predominantly semantic and lack explicit geometric grounding. While…

3D Visual Grounding (3DVG) aims to localize the referent of natural language referring expressions through two core tasks: Referring Expression Comprehension (3DREC) and Segmentation (3DRES). While existing methods achieve high accuracy in…

Vision-based Interfaces (VIs) are pivotal in advancing Human-Computer Interaction (HCI), particularly in enhancing context awareness. However, there are significant opportunities for these interfaces due to rapid advancements in multimodal…

Spatial intelligence, which refers to the ability to reason about geometric and physical structure from visual observations, remains a core challenge for multimodal large language models. Despite promising performance, recent multimodal…

Many real-world tasks require an agent to reason jointly over text and visual objects, (e.g., navigating in public spaces), which we refer to as context-sensitive text-rich visual reasoning. Specifically, these tasks require an…