Zangwei Zheng
13 papers · 2021–2025 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Conference Polyglot (9) π Cross-Pollinator (5) π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (31)
π
Cross-Pollinator
(5)
π
Grand Slam
π€
Dynamic Duo
(12)
π
Century Club
(13)
β‘
Prolific Year
(6)
ποΈ
Keyword Collector
(51)
β
The Questioner
Conferences
ICML (4)
NIPS (2)
AAAI (1)
ACL (1)
CVPR (1)
ECCV (1)
EMNLP (1)
ICCV (1)
ICLR (1)
Top co-authors
Keywords
continual learning
(1)
catastrophic forgetting
(1)
few-shot learning
(1)
domain adaptation
(1)
self-supervised learning
(1)
in-context learning
(1)
cross-domain learning
(1)
language model training
(1)
multimodal learning
(1)
unsupervised domain adaptation
(1)
semantic alignment
(1)
neural network optimization
(1)
gradient estimation
(1)
adaptive optimization
(1)
memory efficiency
(1)
model training
(1)
vision-language model
(1)
multimodal large language model
(1)
weight averaging
(1)
feature alignment
(1)
Papers
MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
ICML 2025
DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers
ICML 2025
How Does the Textual Information Affect the Retrieval of Multimodal In-Context Learning?
EMNLP 2024
Dataset Growth
ECCV 2024
InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
ICLR 2024
OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models
ICML 2024
A Study on Transformer Configuration and Training Objective
ICML 2023
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models
ICCV 2023
CowClip: Reducing CTR Prediction Model Training Time from 12 Hours to 10 Minutes on 1 GPU
AAAI 2023
To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis
NIPS 2023
CAME: Confidence-guided Adaptive Memory Efficient Optimization
ACL 2023
Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline
NIPS 2023
Prototypical Cross-Domain Self-Supervised Learning for Few-Shot Unsupervised Domain Adaptation
CVPR 2021