3 accepted papers
Deploying multiple models within shared GPU clusters is a key strategy to improve resource efficiency in large language model (LLM) serving. Existing multi-LLM serving systems improve GPU utilization at the cost of degraded inference performance, particularly time-to-first-token (TTFT). We attribute…
Recent advancements in integrating large language models (LLMs) with application programming interfaces (APIs) have gained significant interest in both academia and industry. Recent work demonstrates that these API-based agents exhibit relatively strong autonomy and planning capabilities. However, t…
Visual backdoor attack is a recently-emerging task which aims to implant trojans in a deep neural model. A trojaned model responds to a trojan-invoking trigger in a fully predictable manner while functioning normally otherwise. As a key motivating fact to this work, most triggers adopted in existing…