Researcher — paper.dinq.me

2026 顶会论文

作者位次 #8/13ISCA 2026Oral· Computer Architecture

STEP: Adaptive Spatio-Temporal Expert Prefetching for Low-Latency and Memory-Efficient MoE Inference

Fangxin Liu · Ning Yang · Zongwu Wang · Chenyang Guan · Haomin Li · Yu Feng · Liqiang Lu · Xiang Li · Siran Yang · Jiamang Wang · Lin Qu · Li Jiang · Haibing Guan

效率与系统检索与知识长上下文与架构OpenReview

作者位次 #9/12ICLR 2026Poster· Applications / Language, Speech and Dialog

Reconstructing KV Caches with Cross-Layer Fusion for Enhanced Transformers

Hongzhan Lin · Zhiqi Bai · Xinmiao Zhang · Siran Yang · Jiamang Wang · Yunlong Xu · JIAHENG LIU · Yongchi Zhao · Xiang Li · Yuchi Xu · Wenbo Su · Zerui Huang (Taobao &amp

多模态效率与系统OpenReview

一作CVPR 2026Poster· Computer Vision & Pattern Recognition

TRM-VLA: Temporal-Aware Chain-of-Thought Reasoning and Memorization for Vision-Language-Action Models

Xiang Li · Ya-Li Li · Yuan Wang · Shengjin Wang

推理多模态OpenReview 项目页

一作CVPR 2026Poster· Computer Vision & Pattern Recognition

SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion

Xiang Li · Heqian Qiu · Lanxiao Wang · Benliu Qiu · Fanman Meng · Linfeng Xu · Hongliang Li

对齐与偏好多模态OpenReview 项目页

作者位次 #2/5CVPR 2026Poster· Computer Vision & Pattern Recognition

HSI-GPT2: A Dual-Granularity Large Motion Reasoning Model with Diffusion Refinement for Human-Scene Interaction

Yuan Wang · Xiang Li · Yali Li · Xuege Hou · Shengjin Wang

推理多模态社会与人本OpenReview 项目页

作者位次 #6/20KDD 2026Oral· Knowledge Discovery & Data Mining

SAGE: Scalable AI Governance & Evaluation

Benjamin Hoan Le · Xueying Lu · Nicholas Stern · Wenqiong Liu · Igor Lapchuk · Xiang Li · Baofen Zheng · Kevin Rosenberg · Jiewen Huang · Zhe Zhang · Abraham Cabangbang · Satej Milind Wagle · Jianqiang Shen · Raghavan Muthuregunathan · Abhinav Gupta · Mathew Teoh · Andrew J. N. Kirk · Thomas Kwan · Jingwei Wu · Wenjing Zhang

评测与基准检索与知识OpenReview

一作ICRA 2026Oral· Robotics & Automation

GS-UVCE: Gaussian Splatting-Driven Unsupervised Visual Consistency Enhancement for Underwater 3D Scene Reconstruction

Xiang Li · Chi Li · Yiming Xu · Yan Zhuang

多模态OpenReview

作者位次 #5/5ICRA 2026Oral· Robotics & Automation

CoorGrasp: Coordinated Contact Control for Adaptive Dexterous Grasping Under Uncertainty

Mingrui Yu · Yongpeng Jiang · Yongyi Jia · Yi Ren · Xiang Li

OpenReview

一作ICRA 2026Oral· Robotics & Automation

Flexible Trajectory Planning for Autonomous Vehicles via Environmental Assessment in Extreme Scenarios

Xiang Li · Ke Lin · Xiaoqing Yang · Kejian Yan · Yanjie Li · Yunjiang Lou

推理OpenReview

作者位次 #8/8ICRA 2026Oral· Robotics & Automation

From Swept Contact to Pose: Probe-Aware Registration via Complementary-Shape Docking

Chen Chen · Yunwen Li · Yifan Xu · Xiangjie Yan · Chang Shu · Jianxia Hou · Shiji Song · Xiang Li

可解释性OpenReview

作者位次 #7/9ICRA 2026Oral· Robotics & Automation

GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation

Ying Chai · Litao Deng · Ruizhi Shao · Jiajun Zhang · Kangchen Lv · Liangjun Xing · Xiang Li · Hongwen Zhang · Yebin Liu

可解释性OpenReview

作者位次 #7/8IROS 2026Poster· Efficiency and Safety in Vision-Language-Action Models

VLSA: Vision-Language-Action Models with Plug-And-Play Safety Constraint Layer

Songqiao Hu · Zeyi Liu · Shuang Liu · Jun CEN · Zihan Meng · Shihefeng Wang · Xiang Li · Xiao He

评测与基准安全多模态AI-Enabled RoboticsRobot SafetyPerformance Evaluation and BenchmarkingOpenReview

作者位次 #5/5IROS 2026Poster· Language-Guided Foundation Models for Dexterous Grasping

Arm-Aware Guided Dexterous Grasp Generation with Arm-Agnostic Grasp Models

Yongyi Jia · Yongpeng Jiang · Kangchen Lv · Yi Ren · Xiang Li

GraspingDeep Learning in Grasping and ManipulationDexterous ManipulationOpenReview

作者位次 #7/7IROS 2026Poster· Interfaces and Autonomy in Medical Robotics

Coverage Planning for Robotic Tooth Preparation in Densely Constrained Environments

Yunwen Li · Chen Chen · Xiangjie Yan · Chang Shu · Jianxia Hou · Shiji Song · Xiang Li

推理社会与人本Medical Robots and SystemsSurgical Robotics: PlanningOpenReview

作者位次 #5/5IROS 2026Poster· Generalizing Manipulation Skills from Demonstrations

Kinematics-Aware Diffusion Policy with Consistent 3D Observation and Action Space for Whole-Arm Robotic Manipulation

Kangchen Lv · Mingrui Yu · Yongyi Jia · Chenyu Zhang · Xiang Li

理论与学习动力学Imitation LearningDeep Learning in Grasping and ManipulationLearning from DemonstrationOpenReview

作者位次 #3/6INFOCOM 2026Oral· Computer Communications & Networking

DIMO: Constrained Computing Power Information Dissemination with Multi-hop Task Offloading

Wenbin Xu · Shan Zhang · Xiang Li · Tianchun Gan · Zhiyuan Wang · Hongbin Luo

OpenReview

一作AAAI 2026Poster· Artificial Intelligence

TCoT: Trajectory Chain-of-Thoughts for Robotic Manipulation with Failure Recovery in Vision-Language-Action Model

Xiang Li · Ya-Li Li · Yuan Wang · Huaqiang Wang · Shengjin Wang

推理多模态OpenReview

作者位次 #5/7AAAI 2026Poster· Artificial Intelligence

Ego-PMOVE: Prompt-aware Mixture of View Experts Network for Egocentric Gaze Prediction

Heqian Qiu · Lanxiao Wang · Taijin Zhao · Zhaofeng Shi · Xiang Li · Linfeng Xu · Hongliang Li

OpenReview

作者位次 #2/7AAAI 2026Poster· Artificial Intelligence

GeoBayes: Probabilistic Image Geo-Localization Inference via Sequential Bayesian Updating

Weimin Shi · Xiang Li · Kaige Li · Junhao Fang · Qiang Zhou · Qichuan Geng · Zhong Zhou

多模态效率与系统OpenReview

一作AAAI 2026Poster· Artificial Intelligence

GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object Detection

Xiang Li · Wenxi Li · Yuetong Wang · Chenyang Lyu · Haozhe Lin · guiguang ding · Yuchen Guo

效率与系统OpenReview

作者位次 #4/5AAAI 2026Poster· Artificial Intelligence

LPPG-RL: Lexicographically Projected Policy Gradient Reinforcement Learning with Subproblem Exploration

Ruiyu Qiu · Rui Wang · Guanghui Yang · Xiang Li · Zhijiang Shao

强化学习与后训练OpenReview

作者位次 #6/7AAAI 2026Poster· Artificial Intelligence

Efficient Transcoder Adaptation for Fine-Tuned Models: Revealing Medical Reasoning Mechanisms in Large Language Models

Zhouxing Tan · Hanlin Xue · Yulong Wan · Ruochong Xiong · Xu Chu · Xiang Li · Junfei Liu

推理可解释性强化学习与后训练OpenReview

Xiang Li

获取完整研究档案

联系方式

2026 顶会论文

STEP: Adaptive Spatio-Temporal Expert Prefetching for Low-Latency and Memory-Efficient MoE Inference

Reconstructing KV Caches with Cross-Layer Fusion for Enhanced Transformers

TRM-VLA: Temporal-Aware Chain-of-Thought Reasoning and Memorization for Vision-Language-Action Models

SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion

HSI-GPT2: A Dual-Granularity Large Motion Reasoning Model with Diffusion Refinement for Human-Scene Interaction

SAGE: Scalable AI Governance & Evaluation

GS-UVCE: Gaussian Splatting-Driven Unsupervised Visual Consistency Enhancement for Underwater 3D Scene Reconstruction

CoorGrasp: Coordinated Contact Control for Adaptive Dexterous Grasping Under Uncertainty

Flexible Trajectory Planning for Autonomous Vehicles via Environmental Assessment in Extreme Scenarios

From Swept Contact to Pose: Probe-Aware Registration via Complementary-Shape Docking

GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation

VLSA: Vision-Language-Action Models with Plug-And-Play Safety Constraint Layer

Arm-Aware Guided Dexterous Grasp Generation with Arm-Agnostic Grasp Models

Coverage Planning for Robotic Tooth Preparation in Densely Constrained Environments

Kinematics-Aware Diffusion Policy with Consistent 3D Observation and Action Space for Whole-Arm Robotic Manipulation

DIMO: Constrained Computing Power Information Dissemination with Multi-hop Task Offloading

TCoT: Trajectory Chain-of-Thoughts for Robotic Manipulation with Failure Recovery in Vision-Language-Action Model

Ego-PMOVE: Prompt-aware Mixture of View Experts Network for Egocentric Gaze Prediction

GeoBayes: Probabilistic Image Geo-Localization Inference via Sequential Bayesian Updating

GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object Detection

LPPG-RL: Lexicographically Projected Policy Gradient Reinforcement Learning with Subproblem Exploration

Efficient Transcoder Adaptation for Fine-Tuned Models: Revealing Medical Reasoning Mechanisms in Large Language Models

常见合作者