Hyounghun Kim

@khsquared

Assistant professor at POSTECH GSAI/CSE | Prev. UNIST @unc @unccs @uncnlp @AdobeResearch @AmazonScience

hyounghk.github.io

Joined September 2009

524 Following

412 Followers

Replies Reposts Media

Hyounghun Kim
@khsquared
Jan 31, 2025
I am joining POSTECH after spending a couple of years at UNIST. I really appreciate the strong support from UNIST and am excited for this new journey at POSTECH🚀 Thanks to @mohitban47 for the always-thoughtful advice🙏
6
Hyounghun Kim
@khsquared
Oct 17, 2024
Multi-session + Multi-party = Mixed-session Conversation🧑‍🤝‍🧑 Check out the new #EMNLP2024 Findings paper from @jihyoungjang and @kty4119!
Jihyoung Jang
@jihyoungjang
Oct 17, 2024
Excited to share that "Mixed-Session Conversation with Egocentric Memory" has been accepted to #EMNLP2024 Findings🎉🎉🎉 Special thanks to @kty4119 and @khsquared for their collaboration! arxiv.org/abs/2410.02503
1
Hyounghun Kim
@khsquared
Oct 10, 2024
A new #EMNLP2024 paper on creative long story generation! Collaborative critics, guided by a leader, can significantly enhance the creativity of storytelling. Interesting work by @minwookbae!
Minwook Bae
@MinwookBae
Oct 10, 2024
📖 Excited to present our novel long-story generation framework, Collective Critics for Creative Story Generation (CritiCS)! Previous long-story generation research mainly focused on coherence, overlooking creative and captivating storytelling. However, what we truly want is to
Hyounghun Kim
@khsquared
Oct 4, 2024
Can LLMs be aligned using responses alone, without conditioning on instructions? - Yes! Establishing a response space is crucial for LLM alignment. Good work, @seokhyun_an!
Seokhyun An
@seokhyun_an
Oct 4, 2024
🚀 Excited to share our latest findings: LLMs can follow instructions and even refuse unsafe queries, despite being trained solely on responses without paired instructions! We explore how establishing an output space enables LLM alignment, revealing the extensive inherent
Hyounghun Kim
@khsquared
Oct 23, 2023
📢Conversation Chronicles: 1M multi-session conversation dataset! - Conversation Chronicles incorporates ⏲️temporal and 🧑‍🤝‍🧑Relational Dynamics. - ReBot, the dialogue model, can effectively manage temporal events and adapt to relationship shifts over time.
Jihyoung Jang
@jihyoungjang
Oct 23, 2023
🚨Excited to share Conversation Chronicles, a new high-quality multi-session conversation dataset that consists of 1M multi-session dialogues! #EMNLP2023 conversation-chronicles.github.io We have uploaded our dataset and model to @huggingface! w/ @HH22L1 @khsquared
GIF

Hyounghun Kim

Hyounghun Kim’s posts