activity
20242026
collaborators

6 papers

cs.CV2026

Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs

Pengcheng Wang, Zhiquan Wang, Jayoung Lee +5

Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across vision-language tasks. However, their high inference cost, arising from both the large…

cs.AI2026

Efficient Table Retrieval and Understanding with Multimodal Large Language Models

Zhuoyan Xu, Haoyang Fang, Boran Han +4

Tabular data is frequently captured in image form across a wide range of real-world scenarios such as financial reports, handwritten records, and document scans. These visual repre…

cs.LG2025

Neural at ArchEHR-QA 2025: Agentic Prompt Optimization for Evidence-Grounded Clinical Question Answering

Sai Prasanna Teja Reddy Bogireddy, Abrar Majeedi, Viswanatha Reddy Gajjala +3

Automated question answering (QA) over electronic health records (EHRs) can bridge critical information gaps for clinicians and patients, yet it demands both precise evidence retri…

cs.LG2025

Can Language Models Compose Skills In-Context?

Zidong Liu, Zhuoyan Xu, Zhenmei Shi +1

Composing basic skills from simple tasks to accomplish composite tasks is crucial for modern intelligent systems. We investigate the in-context composition ability of language mode…

cs.AI2025

Learning to Inference Adaptively for Multimodal Large Language Models

Zhuoyan Xu, Khoi Duc Nguyen, Preeti Mukherjee +4

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in visual reasoning, yet come with substantial computational cost, limiting their deployment in resource…

cs.CL2024

Out-of-distribution generalization via composition: a lens through induction heads in Transformers

Jiajun Song, Zhuoyan Xu, Yiqiao Zhong

Large language models (LLMs) such as GPT-4 sometimes appear to be creative, solving novel tasks often with a few demonstrations in the prompt. These tasks require the models to gen…