Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/3ICML 2026Poster· General Machine Learning / Data

SciNet: Evaluating AI Agents in Relation-Aware Scientific Literature Retrieval

Chenyang Shao · Fengli Xu · Yong Li

智能体与工具评测与基准检索与知识OpenReview

作者位次 #4/4ICML 2026Poster· Deep Learning / Foundation Models

ChaosNexus: A Foundation Model for ODE-based Chaotic System Forecasting with Hierarchical Multi-scale Awareness

Chang Liu · Bohao Zhao · Jingtao Ding · Yong Li

OpenReview

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

LiveFigure: Generating Editable Scientific Illustration with VLM Agents

Chenyang Shao · Jiahe Liu · Fengli Xu · Yong Li

多模态智能体与工具OpenReview

作者位次 #6/6ICML 2026Poster· Applications / Chemistry, Physics, and Earth Sciences

Generative Adaptation of Dynamics to Environmental Shifts via Weight-space Diffusion

Ruikun Li · Huandong Wang · Jingtao Ding · Yuan Yuan · Qingmin Liao · Yong Li

OpenReview

作者位次 #11/11ICML 2026Poster

iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework

Jianjie Fang · Yingshan Lei · Qin Wan · Ziyou Wang · Yuchao Huang · Yongyan Xu · Baining Zhao · Weichen Zhang · Chen Gao · Xinlei Chen · Yong Li

评测与基准OpenReview

作者位次 #4/4ICML 2026Poster· Applications / Time Series

Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting

Wanjin Feng · Yuan Yuan · Jingtao Ding · Yong Li

对齐与偏好评测与基准OpenReview

作者位次 #5/5ICML 2026Poster

UrbanMLLM: Joint Learning of Cross-view Imagery for Urban Understanding

Xin Zhang · Tianjian Ouyang · Yu Shang · Qingmin Liao · Yong Li

多模态OpenReview

作者位次 #5/5ICML 2026Poster· General Machine Learning / Supervised Learning

Beyond Accuracy and Complexity: The Effective Information Criterion for Structurally Stable Symbolic Regression

Zihan Yu · Guanren Wang · Jingtao Ding · Huandong Wang · Yong Li

OpenReview

作者位次 #4/6ICML 2026Poster· Reinforcement Learning / Batch/Offline

Reward-Preserving Counterfactual State Editing for Offline Reinforcement Learning

Siyu Wang · Xiaocong Chen · Mingming Gong · Yong Li · Quan Sheng · Lina Yao

强化学习与后训练检索与知识OpenReview

作者位次 #10/10ICML 2026Poster· Applications / Everything Else

LitReview Arena: Evaluating Literature Review Agents with Battle-style Peer Review Platform

Ruotong Zhao · Zhiyu Chen · Xurui Liu · Haidong Xue · Dong Liang · Jigao Fu · Wu YanBiao · Yuanyi Zhen · Fengli Xu · Yong Li

智能体与工具评测与基准OpenReview

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

AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agent

Yu Li · Lehui Li · Lin Chen · Qingmin Liao · Fengli Xu · Yong Li

智能体与工具检索与知识OpenReview

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

Towards Professional-Grade Financial Agents: Benchmarking, Tooling, and Structured Reasoning

Cheng Huang · Jinghua Piao · Wang Ranran · Yong Li

推理智能体与工具评测与基准OpenReview

作者位次 #8/9ICML 2026Poster· Deep Learning / Foundation Models

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling

Tengyao Tu · Yulin Li · Huiling Zhen · Libo Qin · Zhoujun Wei · Jinghua Piao · Zhuotao Tian · Yong Li · Min Zhang

推理OpenReview

作者位次 #7/7ICML 2026Poster· Applications / Social Sciences

MarketSim: Simulating Stock Markets with Large-Scale Generative Agents

Jinghua Piao · zhentao liu · Cheng Huang · Huang Jiarui · Songwei Li · Wang Ranran · Yong Li

社会与人本智能体与工具OpenReview

Yong Li

获取完整研究档案

联系方式

2026 顶会论文

SciNet: Evaluating AI Agents in Relation-Aware Scientific Literature Retrieval

ChaosNexus: A Foundation Model for ODE-based Chaotic System Forecasting with Hierarchical Multi-scale Awareness

LiveFigure: Generating Editable Scientific Illustration with VLM Agents

Generative Adaptation of Dynamics to Environmental Shifts via Weight-space Diffusion

iWorld-Bench: A Benchmark for Interactive World Models with a Unified Action Generation Framework

Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting

UrbanMLLM: Joint Learning of Cross-view Imagery for Urban Understanding

Beyond Accuracy and Complexity: The Effective Information Criterion for Structurally Stable Symbolic Regression

Reward-Preserving Counterfactual State Editing for Offline Reinforcement Learning

LitReview Arena: Evaluating Literature Review Agents with Battle-style Peer Review Platform

AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agent

Towards Professional-Grade Financial Agents: Benchmarking, Tooling, and Structured Reasoning

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling

MarketSim: Simulating Stock Markets with Large-Scale Generative Agents

常见合作者