Zineng Tang

University of California, Berkeley — United States

Computer Science · Physical Sciences

9h-index279citations22works2.22yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Multimodal Machine Learning Applications(13), Natural Language Processing Techniques(7), Topic Modeling(6), Domain Adaptation and Few-Shot Learning(5), Advanced Image and Video Retrieval Techniques(4)

Publications22 total

TULIP: Contrastive Image-Text Learning with Richer Vision Understanding
2025
Evaluating Model Perception of Color Illusions in Photorealistic Scenes
2025
Evaluating Model Perception of Color Illusions in Photorealistic Scenes
arXiv (Cornell University)·2024Open Access
Grounding Language in Multi-Perspective Referential Communication
arXiv (Cornell University)·2024Open Access
CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation
2024· 13 cited
Grounding Language in Multi-Perspective Referential Communication
2024Open Access
CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation
arXiv (Cornell University)·2023· 3 citedOpen Access
Unifying Vision, Text, and Layout for Universal Document Processing
2023· 90 cited
Any-to-Any Generation via Composable Diffusion
arXiv (Cornell University)·2023· 29 citedOpen Access
Paxion: Patching Action Knowledge in Video-Language Foundation Models
arXiv (Cornell University)·2023· 9 citedOpen Access
PERCEIVER-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)·2023· 13 cited
Unifying Vision, Text, and Layout for Universal Document Processing
arXiv (Cornell University)·2022· 8 citedOpen Access
Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention
arXiv (Cornell University)·2022· 1 citedOpen Access
TVLT: Textless Vision-Language Transformer
arXiv (Cornell University)·2022· 16 citedOpen Access
VidLanKD: Improving Language Understanding via Video-Distilled Knowledge\n Transfer
arXiv (Cornell University)·2021· 10 citedOpen Access
VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
arXiv (Cornell University)·2021· 3 citedOpen Access
Continuous Language Generative Flow
2021· 3 citedOpen Access
DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy Minimization
2021· 45 citedOpen Access
Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA
arXiv (Cornell University)·2020· 2 citedOpen Access
Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA
2020· 31 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Mohit Bansal(15), Jaemin Cho(6), Ziyi Yang(5), Alane Suhr(5), Chenguang Zhu(4), Michael Zeng(3), Hyounghun Kim(3), Guoxin Wang(2), Yuwei Fang(2), Cha Zhang(2), Jie Lei(2), Mahmoud Khademi(2), Hao Tan(2), Lingjun Mao(2), Lingjun Mao(2), Yang Liu(1), Chenguang Zhu(1), Yixin Nie(1), Yang Liu(1), Zhenhailong Wang(1)