Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/5ICML 2026Poster· Deep Learning / Generative Models and Autoencoders

FedPDG: Prediction Discrepancy–Guided Data Generation for Heterogeneous Federated Learning

Yuqi Wang · Jianwei Niu · Xinghao Wu · Xuefeng Liu · Xin Hao

OpenReview

作者位次 #2/7CVPR 2026Spotlight· Computer Vision & Pattern Recognition

Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning

Xinghao Wu · Jianwei Niu · Xuefeng Liu · Guogang Zhu · Jiayuan Zhang · Shaojie Tang · Wei Chen

多模态可解释性OpenReview 项目页

作者位次 #2/4ACL 2026Poster· Natural Language Processing

E dge F ormer: Latency-Aware Collaborative Multi-Head Attention of Transformer Inference in Edge Networks

Yiming Yao · Jianwei Niu · Bin Dai · Tao Ren

摘要

Recent breakthroughs in Transformer-based large models, have driven widespread tasks, yet their reliance on centralized cloud deployment raises significant privacy risks due to sensitive data exposure. While edge-based collaborative inference offers a privacy-preserving alternative, existing meth...

效率与系统安全可解释性OpenReview 项目页

作者位次 #6/6ICRA 2026Oral· Robotics & Automation

CMAR-search: Commonsense and Memory Augmented Reasoning for Object Search in Dynamic Interactive Environments

Kaiyao Liao · Qingfeng Li · Xinlei Zhang · Chen Chen · Qing Sun · Jianwei Niu

检索与知识推理OpenReview

作者位次 #7/7IROS 2026Poster· Certifying Safety in Learned Robot Control

Real-Time High-Precision Collision Detection Via Physics-Motivated Fusion

hailong han · Qingfeng Li · Qing Sun · Yuanbo Dou · Chen Chen · Xuefeng Liu · Jianwei Niu

安全Failure Detection and RecoveryRobot SafetyMachine Learning for Robot ControlOpenReview

作者位次 #2/7IROS 2026Poster· Making Reinforcement Learning Practical for Manipulation

Escaping the Greedy Trap: Robust Manipulation Via Spatial Beam Search in Coarse-To-Fine Reinforcement Learning

Yuanhao Xiang · Jianwei Niu · Ningbo Gu · Enda Xiang · Jingzhi Cui · Xinli Zhong · Mu Li

强化学习与后训练检索与知识Reinforcement LearningLearning from ExperiencePerception-Action CouplingOpenReview

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

The Aggregated Model is a Confounder: Enabling Deconfounded Federated Learning for OOD Generalization

Jiayuan Zhang · Xuefeng Liu · Jianwei Niu · Haotian Yang · Wanyu LIN · Xinghao Wu

理论与学习动力学OpenReview

作者位次 #4/4INFOCOM 2026Oral· Computer Communications & Networking

SemCache: Semantic-Aware Cache Sharing for Efficient Multi-User LoRA-Adapted LLM Inference at the Edge

Tao Ren · Yiming Yao · Zheyuan Hu · Jianwei Niu

效率与系统OpenReview

作者位次 #2/4AAAI 2026Poster· Artificial Intelligence

From Scene to Object: Enhancing Open-Vocabulary Object Detection via Foreground-Background Context Reasoning

Yanqi Li · Jianwei Niu · Ningbo Gu · Tao Ren

推理OpenReview

作者位次 #2/3AAAI 2026Poster· Artificial Intelligence

DoKnowAD: Calibrating Normal Representations with Refined Domain Knowledge to Enhance Time Series Anomaly Detection

Shiwang Xing · Jianwei Niu · Tao Ren

可解释性检索与知识OpenReview

作者位次 #2/5AAAI 2026Poster· Artificial Intelligence

Learning to Optimize Job Shop Scheduling Under Structural Uncertainty

Rui Zhang · Jianwei Niu · Xuefeng Liu · Shaojie Tang · Jing Yuan