Xinyi Shang
6 papers · 2022–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🧭
Keyword Pioneer
🌍
Conference Polyglot
(5)
🐝
Cross-Pollinator
(14)
🌉
Interdisciplinary Bridge
🐣
Hot Topic Early Bird
Conferences
ACL (1)
CVPR (1)
ICCV (1)
ICLR (1)
ICML (1)
IJCAI (1)
Top co-authors
Keywords
federated learning
(4)
data heterogeneity
(3)
feature representation
(1)
neural collapse
(1)
heterogeneous datum
(1)
model generalization
(1)
long-tailed distribution
(1)
global model
(1)
weighted aggregation
(1)
classifier bia
(1)
client coherence
(1)
aggregation weight
(1)
neural network
(1)
federated semi-supervised learning
(1)
simplex equiangular tight frame
(1)
classifier re-training
(1)
confidence discrepancy
(1)
local-global ensemble
(1)
data mixture surgery
(1)
pretraining data mixture
(1)
Papers
LLMSurgeon: Diagnosing Data Mixture of Large Language Models
ACL 2026
Mind the Gap: Confidence Discrepancy Can Guide Federated Semi-Supervised Learning Across Pseudo-Mismatch
CVPR 2025
GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost
ICLR 2025
No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
ICCV 2023
Revisiting Weighted Aggregation in Federated Learning with Neural Networks
ICML 2023
Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features
IJCAI 2022