activity
20242026
collaborators

15 papers

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.LG2026

ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models

Long Lian, Sida Wang, Felix Juefei-Xu +7

Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial lat…

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…