7 papers
Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
Haoming Wen, Shi Chen, Qingyu Shi +4
Current open-weight large language models (LLMs) are prone to malicious finetuning attacks, which could compromise the safety alignment of LLMs with only a few steps of supervised…
Reverse-Engineering Model Editing on Language Models
Zhiyu Sun, Minrui Luo, Yu Wang +2
Large language models (LLMs) are pretrained on corpora containing trillions of tokens and, therefore, inevitably memorize sensitive information. Locate-then-edit methods, as a main…
Personal Visual Context Learning in Large Multimodal Models
Zihui Xue, Ami Baid, Sangho Kim +2
As wearable devices like smart glasses integrate Large Multimodal Models (LMMs) into the continuous first-person visual streams of individual users, the evolution of these models i…
Differences in Text Generated by Diffusion and Autoregressive Language Models
Zeyang Zhang, Chengwei Liang, Xingyan Chen +4
Diffusion language models (DLMs) are promising alternatives to autoregressive language models (ARMs), yet the intrinsic differences in their generated text remain underexplored. We…
Causal Matrix Completion under Multiple Treatments via Mixed Synthetic Nearest Neighbors
Minrui Luo, Zhiheng Zhang
Synthetic Nearest Neighbors (SNN) provides a principled solution to causal matrix completion under missing-not-at-random (MNAR) by exploiting local low-rank structure through fully…
Global Convergence of Four-Layer Matrix Factorization under Random Initialization
Minrui Luo, Weihang Xu, Xiang Gao +2
Gradient descent dynamics on the deep matrix factorization problem is extensively studied as a simplified theoretical model for deep neural networks. Although the convergence theor…