papers

Publications (14)

cs.LG2026

Diffusion Approximations for Thompson Sampling in the Small Gap Regime

Lin Fan, Peter W. Glynn

We study the process-level dynamics of Thompson sampling and related sampling-based bandit algorithms in the ``small gap'' regime, where the gaps between the arm means are of order…

cs.LG2024

The Fragility of Optimized Bandit Algorithms

Lin Fan, Peter W. Glynn

Much of the literature on optimal design of bandit algorithms is based on minimization of expected regret. It is well known that designs that are optimal over certain exponential f…

cs.CL2025

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

5 Team, Aohan Zeng, Xin Lv +167

We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that s…

cs.LG2024

MDA: An Interpretable and Scalable Multi-Modal Fusion under Missing Modalities and Intrinsic Noise Conditions

Lin Fan, Yafei Ou, Cenyang Zheng +5

Multi-modal learning has shown exceptional performance in various tasks, especially in medical applications, where it integrates diverse medical information for comprehensive diagn…

cs.CL2026

RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis

Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo +9

Large Language Models have evolved from single-round generators into long-horizon agents, capable of complex text synthesis scenarios. However, current evaluation frameworks lack t…

cs.CV2026

RAM-H1200: A Unified Evaluation and Dataset on Hand Radiographs for Rheumatoid Arthritis

Songxiao Yang, Haolin Wang, Yao Fu +9

Rheumatoid arthritis (RA) assessment from hand radiographs requires multi-level analysis and modeling of anatomical structures and fine-grained local pathological changes. However,…

cs.LG2026

GLM-5: from Vibe Coding to Agentic Engineering

GLM-5-Team, :, Aohan Zeng +184

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (AR…

cs.AI2026

Evolving Medical Imaging Agents via Experience-driven Self-skill Discovery

Lin Fan, Pengyu Dai, Zhipeng Deng +4

Clinical image interpretation is inherently multi-step and tool-centric: clinicians iteratively combine visual evidence with patient context, quantify findings, and refine their de…

econ.EM2025

Change-Point Testing for Risk Measures in Time Series

Lin Fan, Junting Duan, Peter W. Glynn +1

We propose novel methods for change-point testing for nonparametric estimators of expected shortfall and related risk measures in weakly dependent time series. We can detect genera…

physics.chem-ph2023

Mass-selected Ion-molecule Cluster Beam Apparatus for Ultrafast Photofragmentation Studies

Xiaojun Wang, Mahmudul Hasan, Lin Fan +4

We describe an apparatus to study the fragmentation of ion-molecule clusters triggered by laser excitation and transfer of an electron from the iodide to the neutral molecule. The…

cs.CV2026

Step-CoT: Stepwise Visual Chain-of-Thought for Medical Visual Question Answering

Lin Fan, Yafei Ou, Zhipeng Deng +8

Chain-of-thought (CoT) reasoning has advanced medical visual question answering (VQA), yet most existing CoT rationales are free-form and fail to capture the structured reasoning p…

cs.CL2026

HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writing

Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo +7

Evaluating the writing capabilities of large language models (LLMs) remains a significant challenge due to the multidimensional nature of writing skills and the limitations of exis…

cs.LG2024

Tri-VQA: Triangular Reasoning Medical Visual Question Answering for Multi-Attribute Analysis

Lin Fan, Xun Gong, Cenyang Zheng +1

The intersection of medical Visual Question Answering (Med-VQA) is a challenging research topic with advantages including patient engagement and clinical expert involvement for sec…

cs.LG2022

The Typical Behavior of Bandit Algorithms

Lin Fan, Peter W. Glynn

We establish strong laws of large numbers and central limit theorems for the regret of two of the most popular bandit algorithms: Thompson sampling and UCB. Here, our characterizat…