Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/4NeurIPS 2026Poster

From Expert Knowledge to Optimization Modeling: Prototype-Based Data Synthesis and Logical Reinforcement Learning

Bo Hu · Qingcan Kang · Qian Liu · Mingxuan Yuan

推理强化学习与后训练检索与知识OpenReview

作者位次 #4/6NeurIPS 2026Poster

LADDERS: Length-Aware Data Distribution and Existing-Response Speculation for Fast RL Rollout Generation

Shengpeng Yin · Hui-Ling Zhen · Xing Li · Mingxuan Yuan · Zishuo Wang · Yuxin Peng

强化学习与后训练OpenReview

作者位次 #5/5NeurIPS 2026Poster

GEM: Interpretable Language Models via Geometric Embedding Alignment

Dimitrios Tsaras · Yankun Hong · Lei Chen · Zhiyao Xie · Mingxuan Yuan

对齐与偏好可解释性OpenReview

作者位次 #6/6NeurIPS 2026Poster

EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling

Qingcan Kang · Mingyang LIU · Xiaojin Fu · Shixiong Kai · Tao Zhong · Mingxuan Yuan

OpenReview

作者位次 #6/7NeurIPS 2026Poster

MemDLM: Memory-Enhanced DLM Training

Zehua Pei · Hui-Ling Zhen · Weizhe Lin · Sinno Pan · Yunhe Wang · Mingxuan Yuan · Bei Yu

检索与知识OpenReview

作者位次 #8/9NeurIPS 2026Poster· General Machine Learning / Representation Learning

FuncFormer: Circuit Representation Learning via the Flow of Functional Propagation

Yunjie Ji · Jie Wang · Zhihai Wang · Min Li · Junhua Huang · Zhihao Shi · Feng Wu · Mingxuan Yuan · Jianye Hao

可解释性OpenReview

作者位次 #9/10NeurIPS 2026Poster

PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding

Shengyin Sun · Yiming Li · Renxi Liu · Xinqi Li · Hui-Ling Zhen · Weizhe Lin · Chen Chen · Xianzhi Yu · Mingxuan Yuan · Chen Ma

效率与系统代码OpenReview

作者位次 #13/16NeurIPS 2026Poster

PCBInnoBench: Benchmarking LLM Agents on Real-World PCB Design

Fuyuan Xia · Jiaxin Hu · Kewei Yu · Zihan Zhang · Zheng wei · Hehan Liang · Xianyue Chen · Tongze Zhang · Xingbo Feng · Shixiong Kai · Zhentao Tang · Yuqi Cui · Mingxuan Yuan · Linfeng Zhang · Qibing Ren · Junchi Yan

智能体与工具评测与基准OpenReview

作者位次 #4/7NeurIPS 2026Poster

Insight-Driven Search: A Framework for Multi-objective Automated Heuristic Design with Large Language Models

Shunyu Yao · Fei Liu · Ji Cheng · Mingxuan Yuan · Xialiang Tong · Zhenkun Wang · Qingfu Zhang

检索与知识OpenReview

作者位次 #6/7NeurIPS 2026Poster· Reinforcement Learning / Deep RL

Efficient Gradient-Aware Asynchronous Reinforcement Learning for LLM Post-Training

Songhan Yang · Jie Wang · Yinqi Bai · Xialiang Tong · Jianye Hao · Mingxuan Yuan · Feng Wu

强化学习与后训练效率与系统OpenReview

作者位次 #7/7NeurIPS 2026Poster

Opt-Arena: Evaluating, Selecting, and Generating Optimization Modeling Data via Tripartite Graphs

Yian Xu · Xiongwei Han · Jie Wang · Haoyang Liu · Yuyang Cai · Boxuan Niu · Mingxuan Yuan

评测与基准OpenReview

Mingxuan Yuan

获取完整研究档案

联系方式