Researcher — paper.dinq.me

2026 顶会论文

作者位次 #2/8ICLR 2026Poster· Applications / Robotics

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denosing Diffusion Process

JIAYI CHEN · Wenxuan Song · Pengxiang Ding · Ziyang Zhou · Han Zhao · Barrett Tang · Donglin Wang · Haoang Li

多模态OpenReview

作者位次 #2/8ICLR 2026Poster· Applications / Robotics

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Fuhao Li · Wenxuan Song · Han Zhao · Jingbo Wang · Pengxiang Ding · Donglin Wang · Long ZENG · Haoang Li

对齐与偏好可解释性多模态OpenReview

作者位次 #9/11CVPR 2026Poster· Computer Vision & Pattern Recognition

Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation

Haodong Yan · Hang Yu · Zhide Zhong · Weilin Yuan · Xin Gong · Zehang Luo · Chengxi Heyu · Junfeng Li · Wenxuan Song · Shunbo Zhou · Haoang Li

多模态可解释性OpenReview 项目页

作者位次 #7/10CVPR 2026Poster· Computer Vision & Pattern Recognition

HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models

Minghui Lin · Pengxiang Ding · Shu Wang · Zifeng Zhuang · Yang Liu · Xinyang Tong · Wenxuan Song · Shangke Lyu · Siteng Huang · Donglin Wang

可解释性多模态OpenReview 项目页

一作ICRA 2026Oral· Robotics & Automation

Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline

Wenxuan Song · JIAYI CHEN · Xiaoquan Sun · Huashuo Lei · Yikai Qin · Wei Zhao · Pengxiang Ding · Han Zhao · Tongxin Wang · Pengxu Hou · Zhide Zhong · Haodong Yan · Donglin Wang · Jun Ma · Haoang Li

多模态评测与基准OpenReview

作者位次 #3/5CHI 2026Oral· Human-Computer Interaction

"In my defense, only three hours on Instagram": Designing Toward Digital Self-Awareness and Wellbeing

Karthik S. Bhat · Jiayue Melissa Shi · Wenxuan Song · Dong Whi Yoo · Koustuv Saha

社会与人本OpenReview

作者位次 #4/7CHI 2026Oral· Human-Computer Interaction

Does Sequencing Matter? Evaluating AI and Human Simulations for High-Stakes Communication Training in Law Enforcement

Duo Wang · Kyrian Liang · Qingxiao Zheng · Wenxuan Song · Jen Whiting · Mike Yao · Caroline G. L. Cao

社会与人本评测与基准OpenReview

作者位次 #2/8CHI 2026Oral· Human-Computer Interaction

Should the AI Speak First? Evaluating Proactive vs. Reactive Facilitation in Mixed-Reality Medical Training

Duo Wang · Wenxuan Song · Jianwei Ni · Qingxiao Zheng · Yuhan Zhou · Kyrian Liang · Mike Yao · Caroline G. L. Cao

社会与人本评测与基准OpenReview

一作AAAI 2026OralOutstanding Paper· Artificial Intelligence

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

Wenxuan Song · Ziyang Zhou · Han Zhao · JIAYI CHEN · Pengxiang Ding · Haodong Yan · Yuxin Huang · Feilong Tang · Donglin Wang · Haoang Li

多模态OpenReview

作者位次 #7/16AAAI 2026Poster· Artificial Intelligence

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

Yihao Wang · Pengxiang Ding · Lingxiao Li · Can Cui · Zirui Ge · Xinyang Tong · Wenxuan Song · Han Zhao · Wei Zhao · Pengxu Hou · Siteng Huang · Yifan Tang · Wenhui Wang · Ru Zhang · Jianyi Liu · Donglin Wang

多模态OpenReview

Wenxuan Song

获取完整研究档案

联系方式

2026 顶会论文

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denosing Diffusion Process

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model

Open-world Hand-Object Interaction Video Generation Based on Structure and Contact-aware Representation

HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models

Rethinking the Practicality of Vision-language-action Model: A Comprehensive Benchmark and An Improved Baseline

"In my defense, only three hours on Instagram": Designing Toward Digital Self-Awareness and Wellbeing

Does Sequencing Matter? Evaluating AI and Human Simulations for High-Stakes Communication Training in Law Enforcement

Should the AI Speak First? Evaluating Proactive vs. Reactive Facilitation in Mixed-Reality Medical Training

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

常见合作者