Get started
Author

Hongxin Ding

Observed name: Ding, Hongxin
Institution: Peking University
Observed institution: Peking University
OpenAlex ID: A5137994304
The Tell-Tale Norm: $\ell_2$ Magnitude as a Signal for Reasoning Dynamics in Large Language Models
2026 · Zhang, Jinyang, Ding, Hongxin, et al. · arXiv (Cornell University)
PDF
DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search
2026 · Association for Computational Linguistics 2026, Chu, Xu, et al. · Underline Science Inc.
ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs
2026 · Association for Computational Linguistics 2026, Ding, Hongxin, et al. · Underline Science Inc.
57 - Toward Better EHR Reasoning in LLMs: Reinforcement Learning with Expert Attention Guidance
2026 · Association for Artificial Intelligence 2026, Ding, Hongxin, et al. · Underline Science Inc.
Toward Better EHR Reasoning in LLMs: Reinforcement Learning with Expert Attention Guidance
2026 · Association for Artificial Intelligence 2026, Ding, Hongxin, et al. · Underline Science Inc.
The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment
2026 · Tianyu Jia, Yue Fang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis
2026 · Jinyang Zhang, Weibin Liao, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Works count: 7
Citation count:
H-index:
I10-index:
Year
Topic
Type