Researcher — paper.dinq.me

2026 顶会论文

作者位次 #7/9ICLR 2026Poster· Deep Learning / Attention Mechanisms

Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis

Qingyue Yang · Jie Wang · Xing Li · Yinqi Bai · Tong Xialiang · Huiling Zhen · Jianye Hao · Mingxuan Yuan · Bin Li

可解释性OpenReview

作者位次 #8/8ICLR 2026Poster· Reinforcement Learning / Deep RL

Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language Model

Jing Liang · Jinyi Liu · Yi Ma · Hongyao Tang · YAN ZHENG · Shuyue Hu · LEI BAI · Jianye Hao

强化学习与后训练效率与系统OpenReview

作者位次 #5/6ICLR 2026Poster· Applications / Robotics

One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration

Jinbang Huang · Yixin Xiao · Zhanguang Zhang · Mark Coates · Jianye Hao · Yingxue Zhang

推理OpenReview

作者位次 #13/15ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding

Yueming Xu · Jiahui Zhang · Ze Huang · Yurui Chen · Yanpeng Zhou · Dave Chen · Yu-Jie Yuan · Pengxiang Xia · Guowei Huang · Xinyue Cai · Zhongang Qi · Xingyue Quan · Jianye Hao · Hang Xu · Li Zhang

多模态代码OpenReview

作者位次 #7/7ICLR 2026Poster· General Machine Learning / Transfer, Multitask and Meta-learning

Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM Guidance

Xiaoqi Ni · Jie Wang · Lin Yang · Yiyang Lu · Hanzhu Chen · Rui Liu · Jianye Hao

推理OpenReview

作者位次 #9/9ICLR 2026Poster· Deep Learning / Everything Else

Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization

Xize Liang · Lin Yang · Jie Wang · Rui Liu · Yang Lu · Jinliang Zeng · Hanzhu Chen · Dong Li · Jianye Hao

推理强化学习与后训练OpenReview

作者位次 #4/9ICLR 2026Poster· Reinforcement Learning / Batch/Offline

Scalable In-Context Q-Learning

Jinmei Liu · Fuhong Liu · Zhenhong Sun · Jianye Hao · Huaxiong Li · Bo Wang · Daoyi Dong · Chunlin Chen · Zhi Wang

强化学习与后训练OpenReview

作者位次 #5/15ICLR 2026Poster· Applications / Genetics, Cell Biology, Health, etc

CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis

Yihang Xiao · Jinyi Liu · YAN ZHENG · Shaoqing Jiao · Jianye Hao · Xiaohan Xie · Limingzhi · Ruitao Wang · Fei Ni · Yuxiao Li · Zhen Wang · Xuequn Shang · Zhijie Bao · Changxiao Yang · Jiajie Peng

智能体与工具社会与人本OpenReview

作者位次 #6/6ICLR 2026Poster· Reinforcement Learning / Deep RL

The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning

Zihao Wu · Hongyao Tang · Yi Ma · Jiashun Liu · YAN ZHENG · Jianye Hao

强化学习与后训练OpenReview

作者位次 #10/10ICLR 2026Poster

Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

Yifu Yuan · Haiqin Cui · Yaoting Huang · Yibin Chen · Fei Ni · Zibin Dong · Pengyi Li · YAN ZHENG · Hongyao Tang · Jianye Hao

推理OpenReview

作者位次 #10/10ICLR 2026Poster

From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation

Yifu Yuan · Haiqin Cui · Yibin Chen · Zibin Dong · Fei Ni · Longxin Kou · Jinyi Liu · Pengyi Li · YAN ZHENG · Jianye Hao

推理OpenReview

作者位次 #9/10ICLR 2026Poster· Applications / Everything Else

K²-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control

Zhe Wu · Donglin Mo · Hongjin Lu · Junliang Xing · Jianheng Liu · Yuheng Jing · Kai Li · Kun Shao · Jianye Hao · Yuanchun Shi

智能体与工具OpenReview

作者位次 #7/9ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

ViMo: A Generative Visual GUI World Model for App Agents

Dezhao Luo · Bohan Tang · Kang Li · Georgios Papoudakis · Jifei Song · Shaogang Gong · Jianye Hao · Jun Wang · Kun Shao

多模态智能体与工具OpenReview

作者位次 #6/7ICLR 2026Poster· Reinforcement Learning / Deep RL

$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving

Pinzheng Wang · Shuli Xu · Juntao Li · Yu Luo · Dong Li · Jianye Hao · Min Zhang

强化学习与后训练推理OpenReview

作者位次 #7/9ICLR 2026Poster· Applications / Everything Else

Evolving Graph Structured Programs for Circuit Generation with Large Language Models

Yinqi Bai · Jie Wang · Lei Chen · Zhihai Wang · Yumeng Li · Mingxuan Yuan · Jianye Hao · Defu Lian · Enhong Chen

可解释性代码OpenReview

作者位次 #7/7ICLR 2026Poster· Applications / Neuroscience, Cognitive Science

A Hierarchical Circuit Symbolic Discovery Framework for Efficient Logic Optimization

Yinqi Bai · Jie Wang · Tong Xialiang · Longdi Pan · Jilai Pan · Mingxuan Yuan · Jianye Hao

推理可解释性效率与系统OpenReview

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

Latent-Guided Reasoning: Empowering Small LLMs with Large-Model Thinking

Hanzhu Chen · Lin Yang · Jie Wang · Junhao Yan · Zhe Wang · Xize Liang · Jianye Hao

推理OpenReview

作者位次 #7/7ICLR 2026Poster

EVLP: Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning

xinyan cai · Qiang Guan · Shiguang Wu · DaFeng Chi · Yuzheng Zhuang · Xingyue Quan · Jianye Hao

多模态强化学习与后训练OpenReview

作者位次 #12/13ICLR 2026Poster· Applications / Robotics

OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

Yuecheng Liu · DaFeng Chi · Shiguang Wu · Zhanguang Zhang · Yuzheng Zhuang · Bowen Yang · He Zhu · Lingfeng Zhang · Pengwei Xie · David Gamaliel Arcos Bravo · Yingxue Zhang · Jianye Hao · Xingyue Quan

推理OpenReview

作者位次 #7/9CVPR 2026Poster· Computer Vision & Pattern Recognition

SemanticVLA: Towards Semantic Reasoning over Action Memorization via Synergistic Explicit Trace and Latent Action Planning

Fei Ni · Zhuo Chen · Yifu Yuan · Zibin Dong · Xianze Yao · Shan Luo · Jianye Hao · Jiankang Deng · Stefanos Zafeiriou

推理多模态OpenReview 项目页

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

Human-like Abstract Visual Reasoning via Understanding and Solving Reasoning Loop

Xinwang Chen · Xiuxing Li · Qing Li · Ziyue Zhuang · Yutong Wu · Ziyu Li · Zhuo Wang · Kai Li · Jianye Hao · Xia Wu

多模态推理社会与人本OpenReview 项目页

作者位次 #7/8CVPR 2026Poster· Computer Vision & Pattern Recognition

Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation

Zaijing Li · Bing Hu · Rui Shao · Gongwei Chen · Dongmei Jiang · Pengwei Xie · Jianye Hao · an Jiaotong University)

多模态效率与系统检索与知识OpenReview 项目页

作者位次 #9/9KDD 2026Oral· Knowledge Discovery & Data Mining

PACE: Unleashing the Power of Code Embeddings to Boost AutoML Agents

Gangyi Zhao · Hebin Liang · Hongyao Tang · Yi Ma · Jinyi Liu · Zhaocheng Du · YAN ZHENG · Chenjun Xiao · Jianye Hao

智能体与工具检索与知识代码OpenReview

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

AgentSwift: Efficient LLM Agent Design via Value-Guided Hierarchical Search

Yu Li · Lehui Li · Zhihao Wu · Qingmin Liao · Jianye Hao · Kun Shao · Fengli Xu

智能体与工具效率与系统检索与知识OpenReview

Jianye Hao

获取完整研究档案

联系方式

2026 顶会论文

Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis

Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language Model

One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration

UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding

Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM Guidance

Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy Optimization

Scalable In-Context Q-Learning

CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis

The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning

Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation

K²-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control

ViMo: A Generative Visual GUI World Model for App Agents

$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving

Evolving Graph Structured Programs for Circuit Generation with Large Language Models

A Hierarchical Circuit Symbolic Discovery Framework for Efficient Logic Optimization

Latent-Guided Reasoning: Empowering Small LLMs with Large-Model Thinking

EVLP: Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning

OmniEVA: Embodied Versatile Planner via Task-Adaptive 3D-Grounded and Embodiment-aware Reasoning

SemanticVLA: Towards Semantic Reasoning over Action Memorization via Synergistic Explicit Trace and Latent Action Planning

Human-like Abstract Visual Reasoning via Understanding and Solving Reasoning Loop

Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation

PACE: Unleashing the Power of Code Embeddings to Boost AutoML Agents

AgentSwift: Efficient LLM Agent Design via Value-Guided Hierarchical Search

常见合作者