1 citations · 1 across the 6 of their papers we have counts for
7 papers
Flow Matching for Robot Foundation Models
Kuangji Zuo, Tuo An, Xinying Guo +9
Flow matching is a common generative recipe for robot foundation models. Vision-language-action models (VLAs) generate action chunks, while world-action models (WAMs) additionally…
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…
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…
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…
Auto-ICL: In-Context Learning without Human Supervision
Jinghan Yang, Shuming Ma, Furu Wei
With in-context learning ability, the performance of large language models can be significantly boosted when provided with appropriate context. However, existing in-context learnin…
Relabeling Minimal Training Subset to Flip a Prediction
Jinghan Yang, Linjie Xu, Lequan Yu
When facing an unsatisfactory prediction from a machine learning model, users can be interested in investigating the underlying reasons and exploring the potential for reversing th…
How Many and Which Training Points Would Need to be Removed to Flip this Prediction?
Jinghan Yang, Sarthak Jain, Byron C. Wallace
We consider the problem of identifying a minimal subset of training data such that if the instances comprising had been removed prior to training, t…