IF-Guide: Influence Function-Guided Detoxification of LLMs
arXiv preprint, 2025.
Preprints
Jailbreaking Large Language Models with Fewer Than Twenty-Five Targeted Bit-flips
arXiv preprint, 2024.
Hard Work Does Not Always Pay Off: Poisoning Attacks on Neural Architecture Search
arXiv preprint, 2024.
2025
Harnessing Input-Adaptive Inference for Efficient VLN
ICCV, 2025.
2023
BERT Lost Patience Won't Be Robust to Adversarial Slowdown
NeurIPS, 2023.