Xianzhi Du
18 papers · 2015–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (26) π Conference Polyglot (8) π Academic Marathon (10) π§ Keyword Pioneer
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
π₯
Mega-Team
(29)
π
Triple Crown
π
Trend Setter
π₯
Unstoppable
(6)
π
Century Club
(18)
β‘
Prolific Year
(7)
Conferences
ICLR (6)
ECCV (4)
CVPR (2)
NIPS (2)
EMNLP (1)
ICCV (1)
ICML (1)
WACV (1)
Top co-authors
Keywords
transfer learning
(4)
object detection
(2)
computer vision
(2)
image classification
(2)
contrastive learning
(1)
zero-shot learning
(1)
neural network pruning
(1)
multimodal learning
(1)
vision transformer
(1)
multi-task learning
(1)
domain generalization
(1)
spectral clustering
(1)
semi-supervised learning
(1)
latent dirichlet allocation
(1)
metric learning
(1)
representation learning
(1)
self-supervised learning
(1)
knowledge distillation
(1)
stochastic optimization
(1)
model compression
(1)
Papers
MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
ICLR 2025
CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling
EMNLP 2025
Guiding Instruction-based Image Editing via Multimodal Large Language Models
ICLR 2024
MOFI: Learning Image Representations from Noisy Entity Annotated Images
ICLR 2024
Compressing LLMs: The Truth is Rarely Pure and Never Simple
ICLR 2024
"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"
ECCV 2024
VeCLIP: Improving CLIP Training via Visual-enriched Captions
ECCV 2024
Ferret: Refer and Ground Anything Anywhere at Any Granularity
ICLR 2024
Empowering Unsupervised Domain Adaptation With Large-Scale Pre-Trained Vision-Language Models
WACV 2024
AdaMV-MoE: Adaptive Multi-Task Vision Mixture-of-Experts
ICCV 2023
Auto-scaling Vision Transformers without Training
ICLR 2022
A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation
ECCV 2022
Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance
ICML 2022
Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation
NIPS 2022
Revisiting ResNets: Improved Training and Scaling Strategies
NIPS 2021
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
CVPR 2020
Efficient Scale-Permuted Backbone with Learned Resource Distribution
ECCV 2020
A Graphical Model Approach for Matching Partial Signatures
CVPR 2015