2 citations · 9 across the 18 of their papers we have counts for
20 papers
In-Cell Learning: Language Models That Update Their Own Weights in Sequence Without Changing the File They Ship
Zifeng Liu, Yaxin Lu, Xuanhan Wu +6
A 4-bit quantized weight specifies a rounding cell rather than a single full-precision value. We introduce in-cell learning, a paradigm for writing new knowledge only within these…
GlaKG: A Biomarker-Centric Fundus Knowledge Graph for Explainable Glaucoma Diagnosis and Risk Assessment
Cheng Huang, Jia Zhang, Yi Jiang +7
Glaucoma is a leading cause of irreversible blindness worldwide, yet most automated diagnosis systems rely on opaque deep-learning models that offer little clinical interpretabilit…
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +378
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
RL-Index: Reinforcement Learning for Retrieval Index Reasoning
Yongjia Lei, Nedim Lipka, Zhisheng Qi +7
Retrieving external knowledge is crucial for real-world tasks but remains difficult when queries and relevant knowledge are linked by implicit reasoning (e.g., shared theorems or c…
ClinEnv: An Interactive Multi-Stage Long Horizon EHR Environment for Agents
Yuxing Lu, Yushuhong Lin, Wenqi Shi +4
Clinical practice is not the selection of an answer from enumerated options: a physician gathers heterogeneous information incrementally and commits to sequential, irreversible dec…
Deep reflective reasoning in interdependence constrained structured data extraction from clinical notes for digital health
Jingwei Huang, Kuroush Nezafati, Zhikai Chi +9
Extracting structured information from clinical notes requires navigating a dense web of interdependent variables where the value of one attribute logically constrains others. Exis…
MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning
Meng Lu, Yuxing Lu, Yuchen Zhuang +6
Vision language models (VLMs) achieve strong performance on general image understanding but struggle to think with medical images, especially when performing multi-step reasoning t…
Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
Meng Lu, Ran Xu, Yi Fang +14
While recent vision-language models (VLMs) demonstrate strong image understanding, their ability to "think with images", i.e., to reason through multi-step visual interactions, rem…
AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
Ran Xu, Yuchen Zhuang, Zihan Dong +7
Search-augmented LLMs often struggle with complex reasoning tasks due to ineffective multi-hop retrieval and limited reasoning ability. We propose AceSearcher, a cooperative self-p…
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
Fang Wu, Aaron Tu, Weihao Xuan +21
Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue tha…
MENDR: Manifold Explainable Neural Data Representations
Matthew Chen, Micky Nnamdi, Justin Shao +7
Foundation models for electroencephalography (EEG) signals have recently demonstrated success in learning generalized representations of EEGs, outperforming specialized models in v…
RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation
Ran Xu, Yuchen Zhuang, Yue Yu +3
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved at inference time. While RAG demonstrates strong performance…
WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning
Yuchen Zhuang, Di Jin, Jiaao Chen +3
Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on sup…
MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science
Ran Xu, Yuchen Zhuang, Yishan Zhong +13
We introduce MedAgentGym, a scalable and interactive training environment designed to enhance coding-based biomedical reasoning capabilities in large language model (LLM) agents. M…
Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration
Ran Xu, Wenqi Shi, Yuchen Zhuang +4
Retrieval-Augmented Generation (RAG) systems often struggle to handle multi-hop question-answering tasks accurately due to irrelevant context retrieval and limited complex reasonin…
MedAdapter: Efficient Test-Time Adaptation of Large Language Models towards Medical Reasoning
Wenqi Shi, Ran Xu, Yuchen Zhuang +5
Despite their improved capabilities in generation and reasoning, adapting large language models (LLMs) to the biomedical domain remains challenging due to their immense size and co…
BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers
Ran Xu, Wenqi Shi, Yue Yu +6
Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient public…
RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records
Ran Xu, Wenqi Shi, Yue Yu +5
We present RAM-EHR, a Retrieval AugMentation pipeline to improve clinical predictions on Electronic Health Records (EHRs). RAM-EHR first collects multiple knowledge sources, conver…
EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Records
Wenqi Shi, Ran Xu, Yuchen Zhuang +7
Large language models (LLMs) have demonstrated exceptional capabilities in planning and tool utilization as autonomous agents, but few have been developed for medical problem-solvi…
Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models
Ran Xu, Hejie Cui, Yue Yu +6
Clinical natural language processing requires methods that can address domain-specific challenges, such as complex medical terminology and clinical contexts. Recently, large langua…