2 papers
cs.CL2026
OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
Yuzhe Gu, Xiyu Liang, Jiaojiao Zhao +1
Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly…
cs.AI2026
Let the Agent Steer: Closed-Loop Ranking Optimization via Influence Exchange
Yin Cheng, Liao Zhou, Xiyu Liang +7
Recommendation ranking is fundamentally an influence allocation problem: a sorting formula distributes ranking influence among competing factors, and the business outcome depends o…