2 citations · 5 across the 25 of their papers we have counts for
28 papers
Long-horizon Video Generation with Slot Memory Addressed By Region Tokens
Eren Cetin, Julius Erbach, Vukasin Bozic +6
Memory for long-horizon video generation must satisfy two competing requirements: it must remain bounded so generation can continue indefinitely, while still recovering what was ob…
GeoFix: Geometry Fixing for 4D Consistent Generation
Yeobin Hong, Hyojun Go, Dohun Lee +7
Video diffusion models increasingly serve as priors for 4D generation, but the generated videos often lack geometric consistency. Recent approaches address this through post-traini…
Stitched Value Model for Diffusion Alignment
Hyojun Go, Hyungjin Chung, Prune Truong +8
For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challen…
Understanding, Accelerating, and Improving MeanFlow Training
Jin-Young Kim, Hyojun Go, Lea Bogensperger +5
MeanFlow promises high-quality generative modeling in few steps, by jointly learning instantaneous and average velocity fields. Yet, the underlying training dynamics remain unclear…
Generating Human Motion Videos using a Cascaded Text-to-Video Framework
Hyelin Nam, Hyojun Go, Byeongjun Park +2
Human video generation is becoming an increasingly important task with broad applications in graphics, entertainment, and embodied AI. Despite the rapid progress of video diffusion…
Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator
Hyojun Go, Dominik Narnhofer, Goutam Bhat +3
The rapid progress of large, pretrained models for both visual content generation and 3D reconstruction opens up new possibilities for text-to-3D generation. Intuitively, one could…
Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
Hyungjin Chung, Hyelin Nam, Jiyeon Kim +6
Video Large Language Models (VideoLLMs) face a critical bottleneck: increasing the number of input frames to capture fine-grained temporal detail leads to prohibitive computational…
VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling
Hyojun Go, Byeongjun Park, Hyelin Nam +3
We propose VideoRFSplat, a direct text-to-3D model leveraging a video generation model to generate realistic 3D Gaussian Splatting (3DGS) for unbounded real-world scenes. To genera…
Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments
Soonwoo Kwon, Jin-Young Kim, Hyojun Go +1
We present a novel study on enhancing the capability of preserving the content in world models, focusing on a property we term World Stability. Recent diffusion-based generative mo…
SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering
Byeongjun Park, Hyojun Go, Hyelin Nam +3
Recent progress in 3D/4D scene generation emphasizes the importance of physical alignment throughout video generation and scene reconstruction. However, existing methods improve th…
SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis
Hyojun Go, Byeongjun Park, Jiho Jang +3
Text-based generation and editing of 3D scenes hold significant potential for streamlining content creation through intuitive user interactions. While recent advances leverage 3D G…
TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models
Hyeongmin Lee, Jin-Young Kim, Kyungjune Baek +18
In this work, we discuss evaluating video foundation models in a fair and robust manner. Unlike language or image foundation models, many video foundation models are evaluated with…
Diffusion Model Patching via Mixture-of-Prompts
Seokil Ham, Sangmin Woo, Jin-Young Kim +3
We present Diffusion Model Patching (DMP), a simple method to boost the performance of pre-trained diffusion models that have already reached convergence, with a negligible increas…
Pegasus-v1 Technical Report
Raehyuk Jung, Hyojun Go, Jaehyuk Yi +41
This technical report introduces Pegasus-1, a multimodal language model specialized in video content understanding and interaction through natural language. Pegasus-1 is designed t…
Denoising Task Difficulty-based Curriculum for Training Diffusion Models
Jin-Young Kim, Hyojun Go, Soonwoo Kwon +1
Diffusion-based generative models have emerged as powerful tools in the realm of generative modeling. Despite extensive research on denoising across various timesteps and noise lev…
Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts
Byeongjun Park, Hyojun Go, Jin-Young Kim +3
Diffusion models have achieved remarkable success across a range of generative tasks. Recent efforts to enhance diffusion model architectures have reimagined them as a form of mult…
HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D
Sangmin Woo, Byeongjun Park, Hyojun Go +2
Recent progress in single-image 3D generation highlights the importance of multi-view coherency, leveraging 3D priors from large-scale diffusion models pretrained on Internet-scale…
Denoising Task Routing for Diffusion Models
Byeongjun Park, Sangmin Woo, Hyojun Go +2
Diffusion models generate highly realistic images by learning a multi-step denoising process, naturally embodying the principles of multi-task learning (MTL). Despite the inherent…
Multi-Architecture Multi-Expert Diffusion Models
Yunsung Lee, Jin-Young Kim, Hyojun Go +3
In this paper, we address the performance degradation of efficient diffusion models by introducing Multi-architecturE Multi-Expert diffusion models (MEME). We identify the need for…
ScoreCL: Augmentation-Adaptive Contrastive Learning via Score-Matching Function
Jin-Young Kim, Soonwoo Kwon, Hyojun Go +3
Self-supervised contrastive learning (CL) has achieved state-of-the-art performance in representation learning by minimizing the distance between positive pairs while maximizing th…
Addressing Negative Transfer in Diffusion Models
Hyojun Go, JinYoung Kim, Yunsung Lee +4
Diffusion-based generative models have achieved remarkable success in various domains. It trains a shared model on denoising tasks that encompass different noise levels simultaneou…
Cross Encoding as Augmentation: Towards Effective Educational Text Classification
Hyun Seung Lee, Seungtaek Choi, Yunsung Lee +5
Text classification in education, usually called auto-tagging, is the automated process of assigning relevant tags to educational content, such as questions and textbooks. However,…
Evaluation of Question Generation Needs More References
Shinhyeok Oh, Hyojun Go, Hyeongdon Moon +4
Question generation (QG) is the task of generating a valid and fluent question based on a given context and the target answer. According to various purposes, even given the same co…
Towards Practical Plug-and-Play Diffusion Models
Hyojun Go, Yunsung Lee, Jin-Young Kim +4
Diffusion-based generative models have achieved remarkable success in image generation. Their guidance formulation allows an external model to plug-and-play control the generation…