activity
20242026
most citedToward Beginner-Friendly LLMs for Language Learning: Controlling Difficulty in Conversation

1 citations · 1 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2025

HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing

Zixuan Bian, Ruohan Ren, Yue Yang +1

3D scene generation plays a crucial role in gaming, artistic creation, virtual reality, and many other domains. However, current 3D scene design still relies heavily on extensive m…

cs.CV2025

DenseAnnotate: Enabling Scalable Dense Caption Collection for Images and 3D Scenes via Spoken Descriptions

Xiaoyu Lin, Aniket Ghorpade, Hansheng Zhu +9

With the rapid adoption of multimodal large language models (MLLMs) across diverse applications, there is a pressing need for task-centered, high-quality training data. A key limit…

cs.CV2025

Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation

Yue Yang, Ajay Patel, Matt Deitke +8

Reasoning about images with rich text, such as charts and documents, is a critical application of vision-language models (VLMs). However, VLMs often struggle in these domains due t…

cs.CV2025

Concept Lancet: Image Editing with Compositional Representation Transplant

Jinqi Luo, Tianjiao Ding, Kwan Ho Ryan Chan +3

Diffusion models are widely used for image editing tasks. Existing editing methods often design a representation manipulation procedure by curating an edit direction in the text em…

cs.CV2024

ViUniT: Visual Unit Tests for More Robust Visual Programming

Artemis Panagopoulou, Honglu Zhou, Silvio Savarese +4

Programming based approaches to reasoning tasks have substantially expanded the types of questions models can answer about visual scenes. Yet on benchmark visual reasoning data, wh…

cs.CV2024

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Matt Deitke, Christopher Clark, Sangho Lee +47

Today's most advanced vision-language models (VLMs) remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good perfor…