← Search

Yeongseo Jung

2 accepted papers

2026

Context-Driven Incremental Compression for Multi-Turn Dialogue Generation

ICML 2026poster

Modern conversational agents condition on an ever-growing dialogue history at each turn, incurring redundant attention and encoding costs that grow with conversation length. Naive truncation or summarization degrades fidelity, while existing context compressors lack cross-turn memory sharing or revi…

Cited by 0SourceScholar
2023

Towards a Unified Conversational Recommendation System: Multi-task Learning via Contextualized Knowledge Distillation

EMNLP 2023long main

In Conversational Recommendation System (CRS), an agent is asked to recommend a set of items to users within natural language conversations. To address the need for both conversational capability and personalized recommendations, prior works have utilized separate recommendation and dialogue modules…

Cited by 0SourcecodeScholar