Researcher — paper.dinq.me

2026 顶会论文

作者位次 #19/20ICML 2026Poster· Deep Learning / Large Language Models

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

jialiang zhu · Gongrui Zhang · Xiaolong Ma · Lin Xu · Miaosen Zhang · Ruiqi Yang · Song Wang · Kai Qiu · Zhirong Wu · Qi Dai · Ruichun Ma · Bei Liu · Yifan Yang · Chong Luo · Zhengyuan Yang · Linjie Li · Lijuan Wang · Weizhu Chen · Xin Geng · Baining Guo

智能体与工具效率与系统检索与知识OpenReview

作者位次 #6/6ICML 2026Poster

Knowledge Diversion for Efficient Morphology Control and Policy Transfer

Fu Feng · Ruixiao Shi · Yucheng Xie · Jianlu Shen · Tmall Group of Alibaba) · Xin Geng

效率与系统检索与知识OpenReview

作者位次 #5/5ICML 2026Poster

Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform

Jianlu Shen · Fu Feng · Yucheng Xie · JIAQI LYU · Xin Geng

检索与知识OpenReview

作者位次 #6/6ICML 2026Poster· Deep Learning / Large Language Models

When Labelers Stay Silent: The Power of Ties in Cost-Effective Preference Learning

JIAQI LYU · Zihan Zhang · CJ Y · Shiyu Xia · Ning Xu · Xin Geng

对齐与偏好OpenReview

作者位次 #4/4ICML 2026Poster· Applications / Language, Speech and Dialog

XPERT: Expert Knowledge Transfer for Effective Training of Language Models

Chang Liu · boyu shi · Xu Yang · Xin Geng

多模态检索与知识OpenReview

作者位次 #5/5ICML 2026Poster· Deep Learning / Large Language Models

Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions

boyu shi · Chang Liu · Chuanbao Gao · Xu Yang · Xin Geng

可解释性效率与系统OpenReview

作者位次 #9/11ICML 2026Poster· Reinforcement Learning / Everything Else

Positive–Unlabeled Reinforcement Learning Distillation for On-Premise Small Models

Zhiqiang Kou · Junyang Chen · Xin-Qiang Cai · Xiaobo Xia · Ming-Kun Xie · Dong-Dong Wu · Biao Liu · Yuheng Jia · Xin Geng · Masashi Sugiyama · Tat-Seng Chua

强化学习与后训练OpenReview

作者位次 #11/11ICML 2026Poster· Deep Learning / Large Language Models

Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training

Miaosen Zhang · Yishan Liu · Shuxia Lin · Qi Dai · Chong Luo · Baining Guo · Weihao Jiang · Peng Hou · Anxiang Zeng · Xu Yang · Xin Geng

理论与学习动力学OpenReview

作者位次 #6/6ICML 2026Poster· General Machine Learning / Transfer, Multitask and Meta-learning

Self-Supervised Weight Templates for Scalable Vision Model Initialization

Yucheng Xie · Fu Feng · Ruixiao Shi · Tmall Group of Alibaba) · Yong Rui · Xin Geng

多模态OpenReview

作者位次 #10/10ICML 2026Poster· General Machine Learning / Supervised Learning

Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity

Junxiang Wu · Zhiqiang Kou · Hongwei Zeng · Wenke Huang · Biao Liu · Hanlin Gu · Yuheng Jia · Di Jiang · Yang Liu · Xin Geng

OpenReview

作者位次 #5/5ICML 2026Poster· Deep Learning / Algorithms

FedPAT: Federated Test-Time Adaptation via Prototype Affinity Topology

Shunxin Guo · JIAQI LYU · Zhiqiang Kou · Shuxia Lin · Xin Geng

OpenReview

作者位次 #3/4ICML 2026Poster· General Machine Learning / Everything Else

Class-Prior Perturbation-Robust Regularization for Imbalanced Unreliable Partial Label Learning

Congyu Qiao · Haohao Dong · Xin Geng · Ning Xu

OpenReview

作者位次 #4/4ICML 2026Poster· Deep Learning / Everything Else

Energy-Structured Low-Rank Adaptation for Continual Learning

Longhua Li · Lei Qi · Qi Tian · Xin Geng

效率与系统OpenReview

作者位次 #6/6CVPR 2026Poster· Computer Vision & Pattern Recognition

A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling

Jianlu Shen · Fu Feng · Jiaze Xu · Yucheng Xie · Jiaqi Lv · Xin Geng

多模态检索与知识OpenReview 项目页

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

FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning

Zhiqiang Kou · Junxiang Wu · Wenke Huang · Wenwen He · Ming-Kun Xie · changwei wang · Yuheng Jia · Di Jiang · Yang Liu · Xin Geng · Qiang Yang

安全多模态OpenReview 项目页

作者位次 #4/4CVPR 2026Poster· Computer Vision & Pattern Recognition

Model Merging in the Essential Subspace

Longhua Li · Lei Qi · Qi Tian · Xin Geng

多模态OpenReview 项目页

作者位次 #4/4CVPR 2026Poster· Computer Vision & Pattern Recognition

Unlocking Pre-trained Weights: Parameter Inheritance for Zero-Shot Initialization

Jiaze Xu · Shiyu Xia · Jiaqi Lv · Xin Geng

多模态数据与预训练OpenReview 项目页

Xin Geng

获取完整研究档案

联系方式

2026 顶会论文

RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents

Knowledge Diversion for Efficient Morphology Control and Policy Transfer

Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform

When Labelers Stay Silent: The Power of Ties in Cost-Effective Preference Learning

XPERT: Expert Knowledge Transfer for Effective Training of Language Models

Understanding Performance Collapse in Layer-Pruned Large Language Models via Decision Representation Transitions

Positive–Unlabeled Reinforcement Learning Distillation for On-Premise Small Models

Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training

Self-Supervised Weight Templates for Scalable Vision Model Initialization

Trustworthy Federated Label Distribution Learning under Annotation Quality Disparity

FedPAT: Federated Test-Time Adaptation via Prototype Affinity Topology

Class-Prior Perturbation-Robust Regularization for Imbalanced Unreliable Partial Label Learning

Energy-Structured Low-Rank Adaptation for Continual Learning

A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling

FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning

Model Merging in the Essential Subspace

Unlocking Pre-trained Weights: Parameter Inheritance for Zero-Shot Initialization

常见合作者