Zhanpeng Zeng
9 papers · 2021–2024 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird 🏆 Keyword Champion (2)
🌈
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Deep Learning
(9)
Machine Learning
(8)
Architectures
(7)
Application Areas
(6)
Techniques
(5)
Models
(2)
Artificial Intelligence
(1)
Computer Vision
(1)
Healthcare & Medicine
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Core AI · Computer Vision
(1)
Core AI · Artificial Intelligence
(1)
Core Methods
(1)
Generation
(1)
Keywords
efficient computing
(4)
transformer architecture
(3)
sequence length
(2)
transformer
(2)
wavelet transform
(2)
approximation algorithm
(1)
linear complexity
(1)
image generation
(1)
nyström method
(1)
nystrom method
(1)
temporal sequence
(1)
diffusion model
(1)
multi-resolution analysis
(1)
long sequence modeling
(1)
layer normalization
(1)
feed-forward network
(1)
locality sensitive hashing
(1)
quadratic complexity
(1)
neural controlled differential equation
(1)
self-attention mechanism
(1)
Papers
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
NeurIPS 2024
FrameQuant: Flexible Low-Bit Quantization for Transformers
ICML 2024
IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
ICML 2024
Controlled Differential Equations on Long Sequences via Non-standard Wavelets
ICML 2023
LookupFFN: Making Transformers Compute-lite for CPU inference
ICML 2023
VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
NeurIPS 2023
Multi Resolution Analysis (MRA) for Approximate Self-Attention
ICML 2022
Nyströmformer: A Nyström-based Algorithm for Approximating Self-Attention
AAAI 2021
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
ICML 2021