Zhenheng Yang

Computer Science · Physical Sciences

21h-index3.6kcitations50works0.42yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

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

Research Topics

Human Pose and Action Recognition(16), Advanced Vision and Imaging(12), Video Surveillance and Tracking Methods(11), Multimodal Machine Learning Applications(11), Robotics and Sensor-Based Localization(7)

Publications50 total

AgentComp: From Agentic Reasoning to Compositional Mastery in Text-to-Image Models
arXiv (Cornell University)·2025Open Access
Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-Boosted Similarity Matching
ArXiv.org·2025Open Access
The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
arXiv (Cornell University)·2025Open Access
FOCUS: Efficient Keyframe Selection for Long Video Understanding
arXiv (Cornell University)·2025Open Access
Improving Text-to-Image Generation with Input-Side Inference-Time Scaling
arXiv (Cornell University)·2025Open Access
Mixture of Contexts for Long Video Generation
arXiv (Cornell University)·2025· 1 citedOpen Access
<i>COEF-VQ:</i> Cost-Efficient Video Quality Understanding through a Cascaded Multimodal LLM Framework
2025Open Access
UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation
arXiv (Cornell University)·2025Open Access
MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs
arXiv (Cornell University)·2025Open Access
UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
arXiv (Cornell University)·2025Open Access
DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling
arXiv (Cornell University)·2025Open Access
UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths
arXiv (Cornell University)·2025Open Access
STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution
arXiv (Cornell University)·2025Open Access
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
2025Open Access
InstanceCap: Improving Text-to-Video Generation via Instance-aware Structured Caption
arXiv (Cornell University)·2024Open Access
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning
arXiv (Cornell University)·2024· 1 citedOpen Access
Show-o: One Single Transformer to Unify Multimodal Understanding and Generation
arXiv (Cornell University)·2024· 3 citedOpen Access
OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation
arXiv (Cornell University)·2024· 2 citedOpen Access
Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency
2021· 36 cited
Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency
arXiv (Cornell University)·2021· 1 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Ram Nevatia(19), Peng Wang(12), Jiyang Gao(10), Wei Xu(6), Wei Xu(6), Yang Wang(5), Alan Yuille(5), Liang Zhao(4), Chenxu Luo(4), Ramakant Nevatia(4), Vignesh Ramanathan(4), Dhruv Mahajan(4), Weijia Mao(4), Mike Zheng Shou(4), Ying Tai(4), Chen Sun(3), Yi Yang(3), Yang Wang(3), Qihang Fan(3), Yuang Ai(3)