4 citations · 6 across the 3 of their papers we have counts for
3 papers
cs.CV2024★ 2 cited
Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models
Jifeng Wang, Kaouther Messaoud, Yuejiang Liu +2
Recent progress in motion forecasting has been substantially driven by self-supervised pre-training. However, adapting pre-trained models for specific downstream tasks, especially…
cs.LG2024
Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts
Yuejiang Liu, Alexandre Alahi
Steering the behavior of a strong model pre-trained on internet-scale data can be difficult due to the scarcity of competent supervisors. Recent studies reveal that, despite superv…
cs.LG2023★ 4 cited
On Pitfalls of Test-Time Adaptation
Hao Zhao, Yuejiang Liu, Alexandre Alahi +1
Test-Time Adaptation (TTA) has recently emerged as a promising approach for tackling the robustness challenge under distribution shifts. However, the lack of consistent settings an…