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.LG2026
Generative Query Suggestion via Intent Coverage and Query-Level Credit Assignment
Xinpeng Liu, Lu Ma, Jiayi Qiao +6
Generative query suggestion aims to enhance user engagement by anticipating user intents and recommending relevant follow-up queries. A central challenge is to generate slates whos…