Sanghyun Byun
YOU?
Author Swipe
View article: 3-Model Speculative Decoding
3-Model Speculative Decoding Open
Speculative Decoding (SD) accelerates inference in large language models by using a smaller draft model to propose tokens, which are then verified by a larger target model. However, the throughput gains of SD are fundamentally limited by a…
View article: Unifying Vision-Language Latents for Zero-label Image Caption Enhancement
Unifying Vision-Language Latents for Zero-label Image Caption Enhancement Open
Vision-language models (VLMs) achieve remarkable performance through large-scale image-text pretraining. However, their reliance on labeled image datasets limits scalability and leaves vast amounts of unlabeled image data underutilized. To…
View article: Single-pass Adaptive Image Tokenization for Minimum Program Search
Single-pass Adaptive Image Tokenization for Minimum Program Search Open
According to Algorithmic Information Theory (AIT) -- Intelligent representations compress data into the shortest possible program that can reconstruct its content, exhibiting low Kolmogorov Complexity (KC). In contrast, most visual represe…
View article: CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression
CARVQ: Corrective Adaptor with Group Residual Vector Quantization for LLM Embedding Compression Open
View article: OneNet: A Channel-Wise 1D Convolutional U-Net
OneNet: A Channel-Wise 1D Convolutional U-Net Open
Many state-of-the-art computer vision architectures leverage U-Net for its adaptability and efficient feature extraction. However, the multi-resolution convolutional design often leads to significant computational demands, limiting deploym…
View article: MultiDepth: Multi-Sample Priors for Refining Monocular Metric Depth Estimations in Indoor Scenes
MultiDepth: Multi-Sample Priors for Refining Monocular Metric Depth Estimations in Indoor Scenes Open
Monocular metric depth estimation (MMDE) is a crucial task to solve for indoor scene reconstruction on edge devices. Despite this importance, existing models are sensitive to factors such as boundary frequency of objects in the scene and s…
View article: Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application
Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application Open
In this paper, we first present the character texture generation system \textit{Minecraft-ify}, specified to Minecraft video game toward in-game application. Ours can generate face-focused image for texture mapping tailored to 3D virtual c…
View article: Transfer Learning based Parameterized 3D Mesh Deformation with 2D Stylized Cartoon Character
Transfer Learning based Parameterized 3D Mesh Deformation with 2D Stylized Cartoon Character Open
As interest in the metaverse has grown, there has been a demand for avatars that can represent individual users.Consequently, research has been conducted to reduce the time and cost required for the current 3D human modeling process.Howeve…