4 accepted papers
Transferable jailbreaking attacks enable red-teaming of black-box large language models by optimizing adversarial prompts on open-source surrogates. A natural approach to improve transferability is multi-model training---optimizing against multiple source models simultaneously. Yet this approach has…
Continual post-training (CPT) is a popular and effective technique for adapting foundation models like multimodal large language models to ever-evolving downstream tasks. While existing research primarily focus on methods like data replay, model expansion, or parameter regularization, the fundamenta…
Sequential recommenders predict users’ next interactions based on historical behavior and are essential in modern recommendation systems. While Large Language Models (LLMs) show promise, their size and high inference costs limit deployment on resource-constrained devices. Small Language Models (SLMs…
Online Continual Learning (OCL) requires models to learn sequentially from data streams with limited memory. Rehearsal-based methods, particularly Experience Replay (ER), are commonly used in OCL scenarios. This paper revisits ER through the lens of $\epsilon$-constraint optimization, revealing that…