Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
From Positionwise Confidence to Prefix Scheduling: Verifier Skipping in Speculative Decoding
Haoxuan Luo, Jameson Sandler, Ferdinando Fioretto
Speculative decoding is a leading technique to reduce the cost of autoregressive generation by using a small drafter to propose several tokens, which are then verified in parallel…
cs.CR2025
Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents
Saswat Das, Jameson Sandler, Ferdinando Fioretto
LLM agents have begun to appear as personal assistants, customer service bots, and clinical aides. While these applications deliver substantial operational benefits, they also requ…