8 papers
Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
Junhyuk So, Hyunho Kook, Chaeyeon Jang +1
Autoregressive (AR) modeling has recently emerged as a promising new paradigm in visual generation, but its practical adoption is severely constrained by the slow inference speed o…
Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient
Hyunho Kook, Byeongho Yu, Jeong Min Oh +1
Recent advancements in the direct training of Spiking Neural Networks (SNNs) have demonstrated high-quality outputs even at early timesteps, paving the way for novel energy-efficie…
Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
Junhyuk So, Chiwoong Lee, Shinyoung Lee +2
Generative Behavior Cloning (GBC) is a simple yet effective framework for robot learning, particularly in multi-task settings. Recent GBC methods often employ diffusion policies wi…
Grouped Speculative Decoding for Autoregressive Image Generation
Junhyuk So, Juncheol Shin, Hyunho Kook +1
Recently, autoregressive (AR) image models have demonstrated remarkable generative capabilities, positioning themselves as a compelling alternative to diffusion models. However, th…
The Oversmoothing Fallacy: A Misguided Narrative in GNN Research
MoonJeong Park, Sunghyun Choi, Jaeseung Heo +2
Oversmoothing has been recognized as a main obstacle to building deep Graph Neural Networks (GNNs), limiting the performance. This position paper argues that the influence of overs…
PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models
Junhyuk So, Jiwoong Shin, Chaeyeon Jang +1
Recently, diffusion models have achieved significant advances in vision, text, and robotics. However, they still face slow generation speeds due to sequential denoising processes.…