7 citations · 17 across the 9 of their papers we have counts for
10 papers
Right Direction, Wrong Step: Geometric Analysis of Finite-Step Failure in Looped Transformers
Zhihao Guo, Zonghan Wu, Haizhou Du +4
Looped Transformers offer a parameter-efficient route to test-time scaling by reusing shared layers for iterative latent reasoning. However, additional iterations can reduce suppor…
Mint-Agent: Introducing Finance-Native Agentic Foundation Models
Agent Team, Kun Wang, Gavin Zhang +7
Financial agents must do more than recall domain knowledge: they must be both reliable, executing precise operations over grounded evidence, and executive, sustaining long-horizon…
HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit
Zhihao Guo, Zonghan Wu, Huan Huo +6
Internal-state probes enable truthfulness prediction before a large language model generates an answer. When detectors change both the layers they read and the rules used to combin…
TimeSage-MT: A Multi-Turn Benchmark for Evaluating Agentic Time Series Reasoning
Yaxuan Kong, Qingren Yao, Yuqi Nie +7
Time series data inform critical decisions across many real-world domains. While large language model (LLM) agents can analyze data through natural language and tools, it remains u…
SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
Wentao Hu, Zhendong Chu, Yiming Zhang +6
Retrieval-augmented LLM agents increasingly rely on curated skill banks: collections of reusable textual principles that guide decision making on complex tasks. Existing approaches…
MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
Yin Zhang, Jiaxuan Zhao, Zonghan Wu +5
Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning tasks. Reinforcement Learning…
Towards Competent AI for Fundamental Analysis in Finance: A Benchmark Dataset and Evaluation
Zonghan Wu, Congyuan Zou, Junlin Wang +3
Generative AI, particularly large language models (LLMs), is beginning to transform the financial industry by automating tasks and helping to make sense of complex financial inform…
Ophtha-LLaMA2: A Large Language Model for Ophthalmology
Huan Zhao, Qian Ling, Yi Pan +14
In recent years, pre-trained large language models (LLMs) have achieved tremendous success in the field of Natural Language Processing (NLP). Prior studies have primarily focused o…
Evaluating Large Language Models in Ophthalmology
Jason Holmes, Shuyuan Ye, Yiwei Li +11
Purpose: The performance of three different large language models (LLMS) (GPT-3.5, GPT-4, and PaLM2) in answering ophthalmology professional questions was evaluated and compared wi…
Evaluating multiple large language models in pediatric ophthalmology
Jason Holmes, Rui Peng, Yiwei Li +10
IMPORTANCE The response effectiveness of different large language models (LLMs) and various individuals, including medical students, graduate students, and practicing physicians, i…