15 papers
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…
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…
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…
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…
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…
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…