3 papers
cs.RO2026
Tri-Info: Generalizable, Interpretable Failure Prediction for VLA Models via Information Theory
Jinghan Yang, Yunchao Zhang, Wang Yuan +4
Vision-Language-Action (VLA) models are increasingly deployed across diverse tasks, yet they remain black boxes whose physical interactions can cause irreversible harm, making gene…
cs.LG2025
Detecting Mislabeled and Corrupted Data via Pointwise Mutual Information
Jinghan Yang, Jiayu Weng
Deep neural networks can memorize corrupted labels, making data quality critical for model performance, yet real-world datasets are frequently compromised by both label noise and i…
cs.LG2025
How to Achieve Higher Accuracy with Less Training Points?
Jinghan Yang, Anupam Pani, Yunchao Zhang
In the era of large-scale model training, the extensive use of available datasets has resulted in significant computational inefficiencies. To tackle this issue, we explore methods…