activity
20242026
collaborators
Showing cs.CVShow all

15 papers · 1 filter

cs.CV2026

Open-Ended CT Volume Segmentation with Weak Supervision from Language

Sanjay Subramanian, Junwei Yu, Zirui Wang +5

We introduce a method for training a text-conditioned segmentation model for CT scans, which combines voxel-level supervision with coarse but scalable slice-level supervision from…

cs.CV2026

Reconstruction Alignment Improves Unified Multimodal Models

Ji Xie, Trevor Darrell, Luke Zettlemoyer +1

Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image-text pairs (or sequences) wh…

cs.CV2026

Stateful Visual Encoders for Vision-Language Models

Zirui Wang, Junwei Yu, Adam Yala +3

Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, vis…

cs.CV2026

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing

Baifeng Shi, Stephanie Fu, Long Lian +10

Multi-modal large language models (MLLMs) have advanced general-purpose video understanding but struggle with long, high-resolution videos -- they process every pixel equally in th…

cs.CV2026

Visually Prompted Benchmarks Are Surprisingly Fragile

Haiwen Feng, Long Lian, Lisa Dunlap +6

A key challenge in evaluating VLMs is testing models' ability to analyze visual content independently from their textual priors. Recent benchmarks such as BLINK probe visual percep…

cs.CV2025

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

Yiming Qin, Bomin Wei, Jiaxin Ge +4

Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and g…