Zhanpeng Zeng

Computer Science · Physical Sciences

4h-index347citations23works0.02yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

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

Research Topics

Advanced Image and Video Retrieval Techniques(4), Image and Video Quality Assessment(4), Domain Adaptation and Few-Shot Learning(4), Advanced Vision and Imaging(3), Topic Modeling(2)

Publications23 total

RQ-GMM: Residual Quantized Gaussian Mixture Model for Multimodal Semantic Discretization in CTR Prediction
ArXiv.org·2026Open Access
RQ-GMM: Residual Quantized Gaussian Mixture Model for Multimodal Semantic Discretization in CTR Prediction
arXiv (Cornell University)·2026Open Access
Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction
arXiv (Cornell University)·2026Open Access
Distribution-Aware End-to-End Embedding for Streaming Numerical Features in Click-Through Rate Prediction
arXiv (Cornell University)·2026Open Access
Research on the generation of deep-cold environment target temperature fields based on GAT-transformer network
2025
Infrared point target small-sample recognition based on temporal feature transfer: a study on the fusion of simulation and real data
2025
LightMotion: A Light and Tuning-free Method for Simulating Camera Motion in Video Generation
arXiv (Cornell University)·2025Open Access
Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
arXiv (Cornell University)·2024Open Access
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
arXiv (Cornell University)·2024Open Access
LookupFFN: Making Transformers Compute-lite for CPU inference
arXiv (Cornell University)·2024Open Access
IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
arXiv (Cornell University)·2024Open Access
FrameQuant: Flexible Low-Bit Quantization for Transformers
arXiv (Cornell University)·2024Open Access
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
2024
Controlled Differential Equations on Long Sequences via Non-standard Wavelets.
PubMed·2023Open Access
Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
arXiv (Cornell University)·2023· 1 citedOpen Access
Multi Resolution Analysis (MRA) for Approximate Self-Attention
arXiv (Cornell University)·2022· 1 citedOpen Access
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
arXiv (Cornell University)·2021· 3 citedOpen Access
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling.
2021
Nyströmformer: A Nyström-based Algorithm for Approximating Self-Attention
Proceedings of the AAAI Conference on Artificial Intelligence·2021· 286 citedOpen Access
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention
arXiv (Cornell University)·2021· 29 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Vikas Singh(6), Yunyang Xiong(4), Glenn Fung(4), Ziye Tong(4), Hongji Ruan(4), Derick Tang(4), Qinsong Zeng(4), Sathya N. Ravi(3), Rudrasis Chakraborty(2), Mingxing Tan(2), Alex J Watras(2), Hewei Liu(2), Yu Hen Hu(2), Hongrui Jiang(2), Shailesh Acharya(2), Sourav Pal(2), Vikas Pratap Singh(2), Rongrong Ji(2), Jiahao Liu(2), Weimin Zhang(2)