paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
HL

Houde Liu

IROS 2026×6ICRA 2026×3ACL 2026ICML 2026多模态对齐与偏好社会与人本理论与学习动力学推理
OROpenReview
新星分资深
32
一作贡献0
核心/参与17
方向广度19
合作网络6
0 一作 · 11 篇 · IROS 2026 / ICRA 2026 / ACL 2026 / ICML 2026

获取完整研究档案

首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。

联系方式

实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。

2026 顶会论文

11
作者位次 #9/10ACL 2026Poster· Natural Language Processing

R eflect RM : Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework

Kai Qin · Liangxin Liu · Yu Liang · Longzheng Wang · Wangyan · Zhang Yueyang · Long Xia · Zhiyuan Sun · Houde Liu · Daiting Shi

摘要

Reward Models (RMs) are critical components in the Reinforcement Learning from Human Feedback (RLHF) pipeline, directly determining the alignment quality of Large Language Models (LLMs). Recently, Generative Reward Models (GRMs) have emerged as a superior paradigm, offering higher interpretabilit...

对齐与偏好评测与基准社会与人本OpenReview 项目页
作者位次 #5/5IROS 2026Poster· Grounding VLA Manipulation in the Real World

Phase-VLA: Efficient Long-Horizon Manipulation Via Proprioception-Guided Visual Attention

Yancong Wei · Zhihao Xu · Sicheng Liu · Kangkang Dong · Houde Liu

多模态效率与系统Perception for Grasping and ManipulationForce and Tactile SensingImitation LearningOpenReview
作者位次 #7/7IROS 2026Poster· Guiding Long-Horizon Reinforcement Learning

Stage-Transition Dense Reward Modeling for Reinforcement Learning

Yang Yang · Bingjie Chen · Zihan Wang · Yizhe Li · Guoping Pan · Yi Cheng · Houde Liu

对齐与偏好强化学习与后训练Learning from DemonstrationReinforcement LearningLearning from ExperienceOpenReview
作者位次 #5/5IROS 2026Poster· Pushing SLAM into Adverse Sensing Conditions

DV-SLAM: Uncalibrated Monocular 4D VGGT SLAM in Dynamic Environments without External Models

Yi Liu · Haoxuan Xu · Keyu Fan · Zhewen Chen · Houde Liu

多模态MappingComputer Vision for AutomationSLAMOpenReview
作者位次 #7/7IROS 2026Poster· Generalizing Manipulation Skills from Demonstrations

Trajectory-Based Diffusion from One‑shot Human Video for Generalizable Manipulation

Guoping Pan · Xinmiao Yu · Wannan Cao · Baolin Jiang · Yizhe Li · Yi Cheng · Houde Liu

多模态社会与人本理论与学习动力学Imitation LearningLearning from DemonstrationDeep Learning in Grasping and ManipulationOpenReview

常见合作者

YCYi Cheng×5KDKangkang Dong×4GPGuoping Pan×4YLYizhe Li×3YWYancong Wei×2SLSicheng Liu×2YLYi Liu×2HXHaoxuan Xu×2KFKeyu Fan×2YYYang Yang×2ZWZihan Wang×2MWmingxin wang×2