Hana Kim

Minjin Kim, Minju Kim, Hana Kim et al.

Conversational recommender system is an emerging area that has garnered an increasing interest in the community, especially with the advancements in large language models (LLMs) that enable diverse reasoning over conversational input. Despite the progress, the field has many aspects left to explore. The currently available public datasets for conversational recommendation lack specific user preferences and explanations for recommendations, hindering high-quality recommendations. To address such challenges, we present a novel conversational recommendation dataset named PEARL, synthesized with persona- and knowledge-augmented LLM simulators. We obtain detailed persona and knowledge from real-world reviews and construct a large-scale dataset with over 57k dialogues. Our experimental results demonstrate that utterances in PEARL include more specific user preferences, show expertise in the target domain, and provide recommendations more relevant to the dialogue context than those in prior datasets.

Yuyang Li, Swasthik Muloor, Jack Laudati et al.

Miniature imaging systems are essential for space-constrained applications but are limited by memory and power constraints. While machine learning can reduce data size by extracting key features, its high energy demands often exceed the capacity of small batteries. This paper presents a CNN hardware accelerator optimized for object classification in miniature imaging systems. It processes data from a spatial Dynamic Vision Sensor (DVS), reconfigurable to a temporal DVS via pixel sharing, minimizing sensor area. By using ternary DVS outputs and a ternary-input, binary-weight neural network, the design reduces computation and memory needs. Fabricated in 28 nm CMOS, the accelerator cuts data size by 81% and MAC operations by 27%. It achieves 440 ms inference time at just 1.6 mW power consumption, improving the Figure-of-Merit (FoM) by 7.3x over prior CNN accelerators for miniature systems.

Hana Kim, Kai Tzu-iunn Ong, Seoyeon Kim et al.

Memorizing and utilizing speakers' personas is a common practice for response generation in long-term conversations. Yet, human-authored datasets often provide uninformative persona sentences that hinder response quality. This paper presents a novel framework that leverages commonsense-based persona expansion to address such issues in long-term conversation. While prior work focuses on not producing personas that contradict others, we focus on transforming contradictory personas into sentences that contain rich speaker information, by refining them based on their contextual backgrounds with designed strategies. As the pioneer of persona expansion in multi-session settings, our framework facilitates better response generation via human-like persona refinement. The supplementary video of our work is available at https://caffeine-15bbf.web.app/.

Hana Kim, Seongil Yang, Huy Kang Kim

As item trading becomes more popular, users can change their game items or money into real money more easily. At the same time, hackers turn their eyes on stealing other users game items or money because it is much easier to earn money than traditional gold-farming by running game bots. Game companies provide various security measures to block account- theft attempts, but many security measures on the user-side are disregarded by users because of lack of usability. In this study, we propose a server-side account theft detection system base on action sequence analysis to protect game users from malicious hackers. We tested this system in the real Massively Multiplayer Online Role Playing Game (MMORPG). By analyzing users full game play log, our system can find the particular action sequences of hackers with high accuracy. Also, we can trace where the victim accounts stolen money goes.