Yifei Wang
8
Papers
79
Total Citations
Papers (8)
Do Generated Data Always Help Contrastive Learning?
ICLR 2024
35
citations
On the Emergence of Position Bias in Transformers
ICML 2025
33
citations
Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
NeurIPS 2025
4
citations
Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness
ICLR 2025
4
citations
Semi-IIN: Semi-Supervised Intra-Inter Modal Interaction Learning Network for Multimodal Sentiment Analysis
AAAI 2025
3
citations
OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift
ICML 2024
0
citations
Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretraining
ICML 2024
0
citations
On the Duality Between Sharpness-Aware Minimization and Adversarial Training
ICML 2024
0
citations