2 papers
cs.CL2026
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
DeepSeek-AI, :, Anyi Xu +585
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation…
cs.CR2026
The Invitation Trap: Proactive Availability Backdoor in LLMs via Conversational Induction
He Wang, Jun Feng, Hong Sun +1
Current backdoor attacks against LLMs are typically manipulated by the attacker and remain passive. In this paper, we introduce the \textbf{Proactive Availability Backdoor (PAB)},…