11 papers
The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs
Qiji Zhou, Junyi Hu, Peiyu Wang +1
Visual interventions provide a training-free way to reduce hallucinations in multimodal large language models. However, an intervention may have little leverage at some layers and…
Westlake Scholar: AI-Enhanced Scholarly Discovery over an Institutional Repository
Junshu Pan, Luodan Zhang, Yifeng Lu +5
Institutional repositories (IRs) provide mature infrastructure for preserving and disseminating research outputs, but conventional record- and document-centric interfaces provide l…
Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks
Guangsheng Bao, Lihua Rong, Yanbin Zhao +3
Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using add…
Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision Support
Chen Zhan, Xihe Qiu, Xiaoyu Tan +8
Large language models perform well on static medical examinations, yet clinical diagnosis often requires iterative evidence gathering under uncertainty. Building on prior interacti…
AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists
Junshu Pan, Panzhong Lu, Yixuan Weng +5
Recent advances in artificial intelligence (AI) have accelerated the growth of both human-authored and AI-generated research outputs, placing increasing strain on traditional acade…
On the Cost and Benefit of Chain of Thought: A Learning-Theoretic Perspective
Yue Zhang, Zhiyi Dong, Tommaso Cesari +1
We develop a learning-theoretic framework for understanding Chain of Thought (CoT). We model CoT as the interaction between an answer map and a chain rule that generates intermedia…
Airalogy: AI-empowered universal data digitization for research automation
Zijie Yang, Qiji Zhou, Fang Guo +19
Research data are the foundation of Artificial Intelligence (AI)-driven science, yet current AI applications remain limited to a few fields with readily available, well-structured,…
Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model
Junshu Pan, Wei Shen, Shulin Huang +2
Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without…
Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation
Qiji Zhou, Yifan Gong, Guangsheng Bao +5
Counterfactual reasoning is crucial for robust video understanding but remains underexplored in existing multimodal benchmarks. In this paper, we introduce \textbf{COVER} (\textbf{…
Decoupling Content and Expression: Two-Dimensional Detection of AI-Generated Text
Guangsheng Bao, Lihua Rong, Yanbin Zhao +2
The wide usage of LLMs raises critical requirements on detecting AI participation in texts. Existing studies investigate these detections in scattered contexts, leaving a systemati…
Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models
Qiji Zhou, Ruochen Zhou, Zike Hu +3
Recent advancements in Chain-of-Thought (CoT) and related rationale-based works have significantly improved the performance of Large Language Models (LLMs) in complex reasoning tas…