3 accepted papers
Task-specific data selection, which aims to identify the most relevant training instances from a large corpus to optimize performance on a target task, is a critical challenge in modern AI. Prevailing methods typically rely on either representation clustering or gradient-based influence estimation.
With the widespread adoption of Mixture-of-Experts (MoE) models, there is a growing demand for efficient inference on memory-constrained devices. While offloading expert parameters to CPU memory and loading activated experts on demand has emerged as a potential solution, the large size of activated…
Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce model outputs contrary to safety alignments. Existing black-bo…