Yanqi Pan — accepted AI-conference papers

2026

ProphetKV: User-Query-Driven Selective Recomputation for Efficient KV Cache Reuse in Retrieval-Augmented Generation

Shihao Wang, Jiahao Chen, Yanqi Pan, Hao Huang, Yichen Hao, Xiangyu Zou +4

ICML 2026poster

The prefill stage of long-context Retrieval-Augmented Generation (RAG) is severely bottlenecked by computational overhead. To mitigate this, recent methods assemble pre-calculated KV caches of retrieved RAG documents (by a *user query*) and reprocess selected tokens to recover cross-attention betwee…

Cited by 0 Source ↗Scholar ↗

2026

RESA: Bringing Back What Sparse Attention Ignores with Residual Estimation

Weihao Yang, Hao Huang, Ningke Li, Shihao Wang, Darong Yang, Yanqi Pan +3

ICLR 2026poster

Large Language Models (LLM) have gained significant attention. KV cache, stored to avoid quadratic complexity of attention, becomes a bottleneck due to the demands for long-context. Sparse attention (SA) has been proposed to address this by only selecting critical KVs for attention, which ma…

Cited by 0 Source ↗Scholar ↗