1 citations · 3 across the 11 of their papers we have counts for
13 papers
Does Gradient Conflict Predict the Understanding--Generation Trade-off? A Controlled Audit of Conflict-Metric Validity in Unified Multimodal Models
Shuyang Jiang, Fucheng Deng, Yuchuan Luo +1
Unified multimodal models (UMMs) are increasingly designed around gradient conflict between understanding and generation objectives. The premise that reducing these metrics improve…
Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach
Haolin Li, Shuyang Jiang, Ruipeng Zhang +3
While large language models hold promise for complex medical applications, their development is hindered by the scarcity of high-quality reasoning data. To address this issue, exis…
Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models
Shuyang Jiang, Yuhao Wang, Ya Zhang +2
Current critic-free RL methods for large reasoning models suffer from severe inefficiency when training on positive homogeneous prompts (where all rollouts are correct), resulting…
EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis
Yusheng Liao, Chaoyi Wu, Junwei Liu +12
Electronic Health Records (EHRs) contain rich yet complex information, and their automated analysis is critical for clinical decision-making. Despite recent advances of large langu…
Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling
Shuyang Jiang, Yusheng Liao, Ya Zhang +2
While large reasoning models trained with critic-free reinforcement learning and verifiable rewards (RLVR) represent the state-of-the-art, their practical utility is hampered by ``…
HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks
Zhe Chen, Yusheng Liao, Zhiyuan Zhu +4
Medical large vision-language Models (Med-LVLMs) have shown promise in clinical applications but suffer from factual inaccuracies and unreliable outputs, posing risks in real-world…
MedS: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision
Shuyang Jiang, Yusheng Liao, Zhe Chen +3
Medical language models face critical barriers to real-world clinical reasoning applications. However, mainstream efforts, which fall short in task coverage, lack fine-grained supe…
Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical Applications
Zhe Chen, Yusheng Liao, Shuyang Jiang +4
Large language models hold promise for addressing medical challenges, such as medical diagnosis reasoning, research knowledge acquisition, clinical decision-making, and consumer he…
ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents
Yusheng Liao, Shuyang Jiang, Yanfeng Wang +1
Large Language Models (LLMs) have shown promising potential in the medical domain, assisting with tasks like clinical note generation and patient communication. However, current LL…
MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation
Yusheng Liao, Shuyang Jiang, Zhe Chen +2
Large language models (LLMs) have shown substantial progress in natural language understanding and generation, proving valuable especially in the medical field. Despite advancement…
TAIA: Large Language Models are Out-of-Distribution Data Learners
Shuyang Jiang, Yusheng Liao, Ya Zhang +2
Fine-tuning on task-specific question-answer pairs is a predominant method for enhancing the performance of instruction-tuned large language models (LLMs) on downstream tasks. Howe…
MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts
Yusheng Liao, Shuyang Jiang, Yu Wang +1
Large language models like ChatGPT have shown substantial progress in natural language understanding and generation, proving valuable across various disciplines, including the medi…
RAGFormer: Learning Semantic Attributes and Topological Structure for Fraud Detection
Haolin Li, Shuyang Jiang, Lifeng Zhang +3
Fraud detection remains a challenging task due to the complex and deceptive nature of fraudulent activities. Current approaches primarily concentrate on learning only one perspecti…