53 citations · 65 across the 11 of their papers we have counts for
11 papers
Sample-Efficient Alignment for LLMs
Zichen Liu, Changyu Chen, Chao Du +2
We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the fr…
Purifying Large Language Models by Ensembling a Small Language Model
Tianlin Li, Qian Liu, Tianyu Pang +4
The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to d…
Test-Time Backdoor Attacks on Multimodal Large Language Models
Dong Lu, Tianyu Pang, Chao Du +3
Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase. In this work, we presen…
Smith-Purcell radiation from time grating
Juan-Feng Zhu, Ayan Nussupbekov, Wenjie Zhou +8
Smith-Purcell radiation (SPR) occurs when an electron skims above a spatial grating, but the fixed momentum compensation from the static grating imposes limitations on the emission…
Gaussian Mixture Solvers for Diffusion Models
Hanzhong Guo, Cheng Lu, Fan Bao +4
Recently, diffusion models have achieved great success in generative tasks. Sampling from diffusion models is equivalent to solving the reverse diffusion stochastic differential eq…
Exploring Model Dynamics for Accumulative Poisoning Discovery
Jianing Zhu, Xiawei Guo, Jiangchao Yao +6
Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve…