Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/3ICML 2026Poster· Deep Learning / Large Language Models

Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning

Yan Jiang · Ruihong Qiu · Zi Huang

推理强化学习与后训练OpenReview

作者位次 #2/3ICML 2026Poster· Deep Learning / Graph Neural Networks

GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuning

Yan Jiang · Ruihong Qiu · Zi Huang

OpenReview

作者位次 #2/3ICML 2026Poster· Deep Learning / Graph Neural Networks

What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition

Danny Wang · Ruihong Qiu · Zi Huang

OpenReview

作者位次 #2/3ACL 2026Poster· Natural Language Processing

TRN - R 1-Zero: Text-rich Network Reasoning via LLM s with Reinforcement Learning Only

Yilun Liu · Ruihong Qiu · Zi Huang

摘要

Zero-shot reasoning on text-rich networks (TRNs) remains a challenging frontier, as models must integrate textual semantics with relational structure without task-specific supervision. While graph neural networks rely on fixed label spaces and supervised objectives, recent large language model (L...

强化学习与后训练推理多模态OpenReview 项目页

Ruihong Qiu

获取完整研究档案

联系方式

2026 顶会论文

Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning

GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuning

What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decomposition

TRN - R 1-Zero: Text-rich Network Reasoning via LLM s with Reinforcement Learning Only

常见合作者