Yihao Xue
8 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (4) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (15) 🧭 Keyword Pioneer
🔥
Unstoppable
(5)
❓
The Questioner
Conferences
ICML (4)
ICLR (2)
AAAI (1)
UAI (1)
Top co-authors
Keywords
representation learning
(2)
contrastive learning
(2)
self-supervised learning
(1)
privacy preservation
(1)
label noise
(1)
gradient descent
(1)
singular value decomposition
(1)
noisy label
(1)
feature suppression
(1)
simplicity bia
(1)
global model
(1)
label noise robustness
(1)
class collapse
(1)
subclass representation
(1)
federated learning
(1)
client influence
(1)
adversarial robustness
(1)
Papers
Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions
ICML 2025
Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings
ICML 2024
Investigating the Benefits of Projection Head for Representation Learning
ICLR 2024
Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
ICLR 2024
Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise
UAI 2024
Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression
ICML 2023
Investigating Why Contrastive Learning Benefits Robustness against Label Noise
ICML 2022
Toward Understanding the Influence of Individual Clients in Federated Learning
AAAI 2021