Xichen Ye
7 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(4)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(20)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
AAAI (4)
CVPR (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
noisy label
(2)
model robustness
(1)
direct preference optimization
(1)
noisy label learning
(1)
weakly supervised learning
(1)
knowledge distillation
(1)
neural network optimization
(1)
positive unlabeled learning
(1)
progressive learning
(1)
computational efficiency
(1)
label noise
(1)
generalization error
(1)
machine learning
(1)
subset selection
(1)
robust learning
(1)
generalization bound
(1)
deep neural network
(1)
loss function
(1)
gradient clipping
(1)
influence function
(1)
Papers
When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF
AAAI 2026
Investigating Data Pruning for Pretraining Biological Foundation Models at Scale
AAAI 2026
Towards Robust Influence Functions with Flat Validation Minima
ICML 2025
Optimized Gradient Clipping for Noisy Label Learning
AAAI 2025
DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation
CVPR 2024
Active Negative Loss Functions for Learning with Noisy Labels
NIPS 2023
GradPU: Positive-Unlabeled Learning via Gradient Penalty and Positive Upweighting
AAAI 2023