Janghyeon Kim — accepted AI-conference papers

2026

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

Janghyeon Kim, Minsoo Kim, Kyuhong Shim, Jungwook Choi

ICML 2026poster

Large Reasoning Models (LRMs) achieve superior problem-solving through extended chain-of-thought generation, but the resulting key-value (KV) cache grows linearly with sequence length and creates severe memory bottlenecks—often exceeding GPU capacity for long reasoning traces. Existing KV cache comp…

Cited by 0 Source ↗Scholar ↗

2023

An Approach to Design a Biomechanically-Inspired Reward Function to Solve a Patience Cube Under Reinforcement Learning Framework

Janghyeon Kim, Ho-Jin Jung, Dae Han Sim, Ji-Hyeon Yoo, Song Woo Kim, Han Ul Yoon

IROS 2023poster

This paper presents an approach to design a reward function by adopting both control theoretic and biomechanical perspectives. In reinforcement learning (RL), a reward function plays a crucial role for an RL agent training; especially, a task learning time and a task performance. Accordingly, design…

Cited by 2 Source ↗Scholar ↗