SuFP: Piecewise Bit Allocation Floating-Point for Robust Neural Network Quantization
Geonwoo Ko, Sungyeob Yoo, Seri Ham, Seeyeon Kim, Minkyu Kim, Joo-Young Kim
KRAFTON AI Hits 100! Mini Interview Series🎉
KRAFTON AI Hits 100! Mini Interview Series🎉 KRAFTON AI has officially surpassed 100 members this year! (Cue applause and cheers 🎉) To celebrate this exciting milestone, we sat down for a short interview with the leaders who are driving KRAFTON AI forward 🥰 We’ll be hearing from Kangwook Lee, who oversees the entire …
Finding an LLM That’s Truly Good at Gaming! The Birth of the ‘Orak’ Benchmark
Finding an LLM That’s Truly Good at Gaming! The Birth of the ‘Orak’ Benchmark As technology evolves, the way games are developed and played continues to change. These days, language models (LLMs) are not only conversation partners within games but also help players with gameplay. But have you ever wondered: “Is this LLM actually good …
Finding an LLM That’s Truly Good at Gaming! The Birth of the ‘Orak’ Benchmark Read More »
Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games
Dongmin Park, Minkyu Kim, Beongjun Choi, Junhyuck Kim, Keon Lee, Jonghyun Lee, Inkyu Park, Byeong-Uk Lee, Jaeyoung Hwang, Jaewoo Ahn, Ameya S. Mahabaleshwarkar, Bilal Kartal, Pritam Biswas, Yoshi Suhara, Kangwook Lee, Jaewoong Cho
HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
Jongsung Lee, Harin Park, Byeong-Uk Lee, Kyungdon Joo
Imperceptible Protection against Style Imitation from Diffusion Models
Namhyuk Ahn, KiYoon Yoo, Wonhyuk Ahn, Daesik Kim, Seung-Hun Nam
Hyperspherical Normalization for Scalable Deep Reinforcement Learning
Hojoon Lee, Youngdo Lee, Takuma Seno, Donghu Kim, Peter Stone, Jaegul Choo
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal Dictionaries
Junhyuck Kim, Jongho Park, Jaewoong Cho, Dimitris Papailiopoulos
How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects
Wonkwang Lee, Jongwon Jeong, Taehong Moon, HyeonJong Kim, Jaehyeon Kim, Gunhee Kim, Byeong-Uk Lee
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
Jaehyeon Kim, Taehong Moon, Keon Lee, Jaewoong Cho