Zhanpeng Zeng
9 papers · 2021–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (3) 🐝 Cross-Pollinator (5) 🌈 Renaissance Researcher (6)
🗺️
Taxonomy Completionist
(13)
🌉
Interdisciplinary Bridge
🏆
Keyword Champion
(2)
Conferences
ICML (6)
NIPS (2)
AAAI (1)
Top co-authors
Research topics
Keywords
efficient computing
(4)
transformer architecture
(3)
wavelet transform
(2)
sequence length
(2)
nystrom method
(1)
nyström method
(1)
multiresolution analysis
(1)
linear complexity
(1)
diffusion model
(1)
approximation algorithm
(1)
long sequence modeling
(1)
feed-forward network
(1)
layer normalization
(1)
multi-resolution analysis
(1)
quadratic complexity
(1)
neural controlled differential equation
(1)
token compression
(1)
wavelet decomposition
(1)
cpu inference
(1)
self attention mechanism
(1)
Papers
FrameQuant: Flexible Low-Bit Quantization for Transformers
ICML 2024
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization
NIPS 2024
IM-Unpack: Training and Inference with Arbitrarily Low Precision Integers
ICML 2024
VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
NIPS 2023
Controlled Differential Equations on Long Sequences via Non-standard Wavelets
ICML 2023
LookupFFN: Making Transformers Compute-lite for CPU inference
ICML 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