Research Director, NAVER AI Lab
3 papers at NeurIPS 2025
We introduce C-SEO Bench, the first benchmark to evaluate conversational search engine optimization (C-SEO) methods across tasks, domains, and multiple adopting actors. We reveal that C-SEO is mostly ineffective, in contrast to traditional SEO.
We introduces a simple yet effective pipeline called Token Bottleneck that facilitates conservative summarization of the observed scene into a bottleneck token while enable capturing of dynamic transitions through the bottleneck token.
We propose a novel query-agnostic KV cache eviction method for multi-query scenario.