Yuxin Wen
16 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Conference Polyglot (4) π Academic Marathon (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (12)
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(30)
π
Keyword Champion
(2)
π
Triple Crown
π€
Dynamic Duo
(11)
π
Century Club
(16)
π₯
Unstoppable
(6)
β‘
Prolific Year
(5)
ποΈ
Keyword Collector
(66)
Conferences
ICLR (5)
ICML (4)
NIPS (4)
CVPR (3)
Top co-authors
Research topics
Keywords
copyright protection
(2)
privacy leakage
(2)
implicit surface
(2)
privacy attack
(2)
generative model
(2)
large language model
(2)
prompt engineering
(1)
gradient-based optimization
(1)
3d reconstruction
(1)
surface reconstruction
(1)
feature space
(1)
discrete optimization
(1)
shape modeling
(1)
generalization ability
(1)
implicit representation
(1)
adversarial robustness
(1)
decision boundary
(1)
point cloud
(1)
poisoning attack
(1)
backdoor attack
(1)
Papers
Stable-SCore: A Stable Registration-based Framework for 3D Shape Correspondence
CVPR 2025
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
NIPS 2024
NEFTune: Noisy Embeddings Improve Instruction Finetuning
ICLR 2024
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
NIPS 2024
WAVES: Benchmarking the Robustness of Image Watermarks
ICML 2024
Detecting, Explaining, and Mitigating Memorization in Diffusion Models
ICLR 2024
On the Reliability of Watermarks for Large Language Models
ICLR 2024
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
ICLR 2023
Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images
NIPS 2023
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
ICLR 2023
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
NIPS 2023
A Watermark for Large Language Models
ICML 2023
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
ICML 2022
Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction From Raw Point Clouds
CVPR 2021
Deep Optimized Priors for 3D Shape Modeling and Reconstruction
CVPR 2021
Towards Understanding the Regularization of Adversarial Robustness on Neural Networks
ICML 2020