ArXiv TLDR

Bo Wang

4 papers · Latest:

Computer Vision

BAMI: Training-Free Bias Mitigation in GUI Grounding

BAMI is a training-free method that uses coarse-to-fine focus and candidate selection to mitigate precision and ambiguity biases in GUI grounding models.

2605.06664
Machine Learning

Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training

This paper interprets catastrophic overfitting in fast adversarial training as a backdoor mechanism and proposes new mitigation strategies.

2604.24350
Machine Learning

Mitigating Error Amplification in Fast Adversarial Training

A new method, DDG, mitigates catastrophic overfitting and improves robustness-accuracy in Fast Adversarial Training by dynamic guidance.

2604.24332
Software Engineering

TestDecision: Sequential Test Suite Generation via Greedy Optimization and Reinforcement Learning

TestDecision uses greedy optimization and RL to enable open-source LLMs to generate high-quality, sequential test suites, boosting coverage and bug detection.

2604.01799

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.