Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
BasisKV: Value Latents for Communication and Key Routing
Lixun Zhang, Zishan Shao, Kangning Cui +3
Long-context large language model (LLM) inference is increasingly constrained by the cost of maintaining an ever-growing KV-cache. Low-rank K/V projections provide a promising way…
cs.AI2026
Seeing What Matters, Verifying What Pays: Load-Adaptive Speculative Decoding for Vision-Language Models
Hong Nie, Zhangchi Gao, Yuqian Liang +4
Speculative decoding accelerates vision-language model (VLM) inference without altering the output distribution, yet two factors limit its gains. Existing drafters either lack the…