Chenliang Xu

Computer Science · Physical Sciences

36h-index6.5kcitations244works2.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Multimodal Machine Learning Applications(50), Human Pose and Action Recognition(39), Speech and Audio Processing(39), Music and Audio Processing(33), Video Analysis and Summarization(32)

Publications244 total

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
ArXiv.org·2026Open Access
SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
arXiv (Cornell University)·2026Open Access
Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
arXiv (Cornell University)·2026Open Access
Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling
arXiv (Cornell University)·2026Open Access
Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination
arXiv (Cornell University)·2025Open Access
Predicting the risk of asthma development in youth using machine learning models
PLoS ONE·2025· 1 citedOpen Access
Diagnosing Visual Reasoning: Challenges, Insights, and a Path Forward
arXiv (Cornell University)·2025Open Access
Generative AI for Cel-Animation: A Survey
2025
Leveraging Large Language Models to Identify Engagement-Driving Features in Vaping-Related TikTok Videos: Cross-Sectional Study
Journal of Medical Internet Research·2025Open Access
Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models
arXiv (Cornell University)·2025Open Access
AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning
arXiv (Cornell University)·2025Open Access
StreamME: Simplify 3D Gaussian Avatar within Live Stream
2025Open Access
StreamME: Simplify 3D Gaussian Avatar within Live Stream
arXiv (Cornell University)·2025Open Access
OPENXRD: A Comprehensive Benchmark and Enhancement Framework for LLM/MLLM XRD Question Answering
arXiv (Cornell University)·2025Open Access
What to Do Next? Memorizing skills from Egocentric Instructional Video
ArXiv.org·2025Open Access
ACTLLM: Action Consistency Tuned Large Language Model
arXiv (Cornell University)·2025Open Access
Can Sound Replace Vision in LLaVA With Token Substitution?
arXiv (Cornell University)·2025Open Access
Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach
2025· 1 cited
Learning to Highlight Audio by Watching Movies
2025· 1 cited
VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
2025· 1 citedOpen Access
page 1 of 13Next →

Frequent Co-authors

Yapeng Tian(12), Jason J. Corso(12), Zhiyao Duan(9), Lele Chen(8), Ross K. Maddox(6), Zhiheng Li(5), Yulun Zhang(4), Yun Fu(4), Luowei Zhou(4), Jiebo Luo(4), Jing Shi(4), Li Ding(3), Şefik Emre Eskimez(3), Bochen Li(2), Caiming Xiong(2), Guofeng Cui(2), Ziyi Kou(2), Di Hu(2), Parker Koch(2), Ali Vosoughi(2)