Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/4ICLR 2026Poster· Optimization / Learning for Optimization

ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across Types

Ziao Guo · Yang Li · Shiyue Wang · Junchi Yan

可解释性OpenReview

作者位次 #7/7ICLR 2026Poster· Deep Learning / Algorithms

Achieving low-bit Muon through subspace preservation and grid quantization

Huaijin Wu · Bingrui Li · Yebin Yang · Yi Tu · Zhanpeng Zhou · Jianfei Chen · Junchi Yan

效率与系统OpenReview

作者位次 #5/5ICLR 2026Poster· Applications / Time Series

MMPD: Diverse Time Series Forecasting via Multi-Mode Patch Diffusion Loss

Yunhao Zhang · Wenyao Hu · Jiale Zheng · Lujia Pan · Junchi Yan

OpenReview

作者位次 #10/11ICLR 2026Poster· Applications / Robotics

Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions

Cunxin Fan · Xiaosong Jia · Yihang Sun · Yixiao Wang · Jianglan Wei · Ziyang Gong · Xiangyu Zhao · Masayoshi Tomizuka · Xue Yang · Junchi Yan · Mingyu Ding

多模态OpenReview

作者位次 #4/5ICLR 2026Poster· Optimization / Learning for Optimization

Native Adaptive Solution Expansion for Diffusion-based Combinatorial Optimization

Yu Wang · Yang Li · Jiale Ma · Junchi Yan · Yi Chang

OpenReview

作者位次 #8/8ICLR 2026Poster· Deep Learning / Attention Mechanisms

ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning

Xiaohan Qin · Victor Wang · Ning Liao · Cancheng Zhang · Xiangdong Zhang · Mingquan Feng · Jingzhi Wang · Junchi Yan

可解释性强化学习与后训练OpenReview

作者位次 #3/3ICLR 2026Poster

MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial Optimization

Lvda Chen · Yang Li · Junchi Yan

可解释性OpenReview

作者位次 #7/7ICLR 2026Poster

TrajTok: What makes for a good trajectory tokenizer in behavior generation?

Zhiyuan Zhang · Xiaosong Jia · Guanyu Chen · Qifeng Li · Zuxuan Wu · Yu-Gang Jiang · Junchi Yan

数据与预训练OpenReview

作者位次 #10/10ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation

Yuan Feng · Yue Yang · Xiaohan He · Jiatong Zhao · Jianlong Chen · DAOCHENG FU · Qi Liu · Renqiu Xia · Bo Zhang · Junchi Yan

多模态评测与基准OpenReview

作者位次 #4/6ICLR 2026Poster· Social Aspects / Fairness, Equity, Justice and Safety

When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms

Qibing Ren · Zhijie Zheng · Jiaxuan Guo · Junchi Yan · Lizhuang Ma · Jing Shao

社会与人本智能体与工具安全OpenReview

作者位次 #6/8ICLR 2026Poster

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention

Xiaosong Jia · Yihang Sun · Junqi You · songbur wong · Zichen Zou · Junchi Yan · Zuxuan Wu · Yu-Gang Jiang

效率与系统OpenReview

作者位次 #7/7ICLR 2026Poster

Let's Explore Step by Step: Generating Provable Formal Statements with Deductive Exploration

Qi Liu · Kangjie Bao · Yue Yang · Xinhao Zheng · Renqiu Xia · Qinxiang Cao · Junchi Yan

理论与学习动力学OpenReview

作者位次 #6/6ICLR 2026Poster· Applications / Robotics

DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving

Haisheng Su · Wei Wu · Feixiang Song · Junjie Zhang · Zhenjie Yang · Junchi Yan

效率与系统长上下文与架构OpenReview

作者位次 #10/11ICLR 2026Poster

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

Ziyang Gong · Wenhao Li · Xianzheng Ma · Songyuan Li · Zhaokai Wang · Songze Li · Jiayi Ji · Xue Yang · Gen Luo · Junchi Yan · Rongrong Ji

多模态评测与基准长上下文与架构OpenReview

作者位次 #10/11ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization

Teng Zhang · Ziqian Fan · Mingxin Liu · Xin Zhang · Xudong Lu · Wentong Li · Yue Zhou · Yi Yu · Xiang Li · Junchi Yan · Xue Yang

多模态OpenReview

作者位次 #6/10ICLR 2026Poster· Applications / Language, Speech and Dialog

Group Verification-based Policy Optimization for Interactive Coding Agents

Silong Dai · Changzhi Sun · Haolun Wu · Huanran Zheng · Tao Ji · Junchi Yan · Yuanbin Wu · Dell Zhang · Xiaoling Wang · Xuelong Li

智能体与工具多模态强化学习与后训练OpenReview

作者位次 #10/14ICLR 2026Poster

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

Xiangyu Zhao · Lin · Tianhao Liang · Yifan Zhou · Wenhao Chai · Yuzhe Gu · Weiyun Wang · Kai Chen · Gen Luo · Junchi Yan · Wenwei Zhang · Hua Yang · Haodong Duan · Xue Yang

推理多模态强化学习与后训练OpenReview

作者位次 #7/7CVPR 2026Spotlight· Computer Vision & Pattern Recognition

ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving

Han Lu · Xiaosong Jia · Yichen Xie · Siyu Sun · Wenlong Liao · Xiaokang Yang · Junchi Yan

推理多模态OpenReview 项目页

作者位次 #8/8CVPR 2026Poster· Computer Vision & Pattern Recognition

DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving

Zhenjie Yang · Yilin Chai · Xiaosong Jia · Qifeng Li · Yuqian Shao · Xuekai Zhu · Haisheng Su · Junchi Yan

多模态效率与系统OpenReview 项目页

作者位次 #10/11CVPR 2026Poster· Computer Vision & Pattern Recognition

Spatial Retrieval Augmented Autonomous Driving

Xiaosong Jia · Chenhe Zhang · Yule Jiang · songbur wong · Zhiyuan Zhang · Chen Chen · Shaofeng Zhang · Xuanhe Zhou · Xue Yang · Junchi Yan · Yu-Gang Jiang

多模态检索与知识OpenReview 项目页

作者位次 #9/10CVPR 2026Poster· Computer Vision & Pattern Recognition

Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs

Rujiao Long · Yang Li · Xingyao Zhang · Weixun Wang · Tianqianjin Lin · Xi Zhao · Yuchi Xu · Wenbo Su · Junchi Yan · Zerui Huang (Taobao &amp

推理多模态OpenReview 项目页

作者位次 #5/5KDD 2026Oral· Knowledge Discovery & Data Mining

Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial Confinement Fusion

Jiatong Zhao · Tengyue Zhang · Yuhan Wang · Fuyuan Wu · Junchi Yan

强化学习与后训练检索与知识OpenReview

作者位次 #7/8AAAI 2026Poster· Artificial Intelligence

ST-TPP: Learning Semi-Transductive Temporal Point Processes with Gromov-Wasserstein Barycentric Regularization

Qingmei Wang · Tianyu Huang · Yujie Long · Yuxin Wu · Fanmeng Wang · Xi Sun · Junchi Yan · Hongteng Xu

OpenReview

作者位次 #3/3AAAI 2026Poster· Artificial Intelligence

Towards Real-Time Neutral Atom Array Assembly via Unsupervised Hologram Generation and Path Optimization

Ge Yan · Yuchen Wang · Junchi Yan

OpenReview

作者位次 #7/7AAAI 2026Poster· Artificial Intelligence

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD

Tongcheng Zhang · Zhanpeng Zhou · Mingze Wang · Andi Han · Wei Huang · Taiji Suzuki · Junchi Yan

理论与学习动力学OpenReview

Junchi Yan

获取完整研究档案

联系方式

2026 顶会论文

ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across Types

Achieving low-bit Muon through subspace preservation and grid quantization

MMPD: Diverse Time Series Forecasting via Multi-Mode Patch Diffusion Loss

Interleave-VLA: Enhancing Robot Manipulation with Image-Text Interleaved Instructions

Native Adaptive Solution Expansion for Diffusion-based Combinatorial Optimization

ssToken: Self-modulated and Semantic-aware Token Selection for LLM Fine-tuning

MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial Optimization

TrajTok: What makes for a good trajectory tokenizer in behavior generation?

GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation

When AI Agents Collude Online: Financial Fraud Risks by Collaborative LLM Agents on Social Platforms

Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention

Let's Explore Step by Step: Generating Provable Formal Statements with Deductive Exploration

DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization

Group Verification-based Policy Optimization for Interactive Coding Agents

MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization

ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving

DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving

Spatial Retrieval Augmented Autonomous Driving

Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs

Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial Confinement Fusion

ST-TPP: Learning Semi-Transductive Temporal Point Processes with Gromov-Wasserstein Barycentric Regularization

Towards Real-Time Neutral Atom Array Assembly via Unsupervised Hologram Generation and Path Optimization

On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD

常见合作者