Researcher — paper.dinq.me

2026 顶会论文

作者位次 #12/12ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes

Keliang Li · Hongze Shen · Hao Shi · RuiBing Hou · Hong Chang · Jie Huang · Chenghao Jia · Wen Wang · Yiling Wu · Dongmei Jiang · Shiguang Shan · Xilin CHEN

多模态可解释性社会与人本OpenReview

作者位次 #4/4ICLR 2026Poster· Applications / Robotics

Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling

Xiaolong Tang · Meina Kan · Shiguang Shan · Xilin CHEN

推理OpenReview

作者位次 #5/5CVPR 2026Poster· Computer Vision & Pattern Recognition

V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs

Sen Nie · Jie Zhang · Jianxin Yan · Shiguang Shan · Xilin CHEN

安全多模态OpenReview 项目页

作者位次 #5/5CVPR 2026Poster· Computer Vision & Pattern Recognition

UniPercept: A Unified Diffusion Model for Generalizable Visual Perception

Zuyan Zhao · Zhenliang He · Meina Kan · Shiguang Shan · Xilin CHEN

多模态理论与学习动力学OpenReview 项目页

作者位次 #5/5ACL 2026Poster· Natural Language Processing

INFACT : A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video- LLM s

Yangjunqi · Yuecong Min · Jie Zhang · Shiguang Shan · Xilin CHEN

摘要

Despite rapid progress, Video Large Language Models (Video-LLMs) remain unreliable due to hallucinations, which are outputs that contradict either video evidence (faithfulness) or verifiable world knowledge (factuality).Existing benchmarks provide limited coverage of factuality hallucinations and...

多模态评测与基准检索与知识OpenReview 项目页

作者位次 #3/3ICRA 2026Oral· Robotics & Automation

Learning View-Invariant Sign Language Representations via Dual-Stream Contrastive Learning

Yuting Peng · Yuecong Min · Xilin CHEN

可解释性OpenReview

作者位次 #4/4IROS 2026Oral· Humans in the Robot Learning Loop

Augmenting Robot Imitation Learning with Human Videos without Additional Robot Data

YiFan Zhang · Chuyan Xiong · Ruiping Wang · Xilin CHEN

多模态社会与人本Imitation LearningLearning from DemonstrationHuman-Robot CollaborationOpenReview

Xilin CHEN

获取完整研究档案

联系方式