2 papers
cs.LG2026
StepKV: Step-Aware KV Cache Compression for LLM Agents
Boyu Feng, Jiahong Liu, Yifan Li +7
Key-value (KV) caching is essential for efficient autoregressive large language model (LLM) inference, but the cache grows linearly with context length, increasing storage and deco…
cs.LG2026
Hyperbolic Multimodal Continual Learning
Jiahong Liu, Ming Shen, Xiaohao Liu +4
Hyperbolic geometry has recently emerged as a powerful representation space for multimodal learning, as it naturally captures hierarchical semantic structure across modalities. Des…