2 papers
cs.LG2026
TideKV: Delayed KV Eviction via Layer-Wise Chunked Prefill for Memory-Efficient Long-Context LLM Inference
Yu Wang, Zhu Wang, Ning Hu +4
Long-context large language model (LLM) inference is important for modern intelligent applications but remains constrained by peak memory during prompt prefill. Existing KV cache c…
cs.CL2026
ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker
Siqiao Xue, Shuxuan Liu, Ning Hu
Open rerankers trained for general web retrieval transfer imperfectly to e-commerce, where ranking decisions depend not only on topical relevance but also on user preferences, prod…