Publications

Multi-Object Hallucination in Vision-Language Models

NeurIPS 2024
PDF Cite Website GitHub 🤗 Dataset
Multi-Object Hallucination in Vision-Language Models

Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use

EMNLP 2024
PDF Cite GitHub
Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use

3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination

Preprint
PDF Cite Website GitHub 3D-GRAND Data 3D-POPE Leaderboard 🤗 Demo
3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination

LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent

ICRA 2024
PDF Cite Website GitHub Video Live Demo
LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent

SEAGULL: An Embodied Agent for Instruction Following through Situated Dialog

Alexa Prize SimBot Challenge Proceedings 2023 (🏆 First Place)
PDF Cite Press: Amazon Science Press: U-M News Press: 机器之心
SEAGULL: An Embodied Agent for Instruction Following through Situated Dialog

DANLI: Deliberative Agent for Following Natural Language Instructions

EMNLP 2022
PDF Cite GitHub Video
DANLI: Deliberative Agent for Following Natural Language Instructions

MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences

NAACL 2021
PDF Cite Slides GitHub Video
MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language Sequences

What Gives the Answer Away? Question Answering Bias Analysis on Video QA Datasets

ACL 2020 Human Multimodal Language Workshop
PDF Cite Video
What Gives the Answer Away? Question Answering Bias Analysis on Video QA Datasets

SUOD: Toward Scalable Unsupervised Outlier Detection

AAAI 2020 Artificial Intelligence for Cyber Security (AICS) Workshop
PDF Cite Slides GitHub
SUOD: Toward Scalable Unsupervised Outlier Detection