Nakkwan Choi
Nakkwan
·
AI & ML interests
Computer Vision
Recent Activity
updated
a collection
about 14 hours ago
Editing
updated
a collection
about 14 hours ago
Diffusion
updated
a collection
3 days ago
Platform
Organizations
None yet
Diffusion
-
ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
Paper • 2512.13586 • Published • 87 -
TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
Paper • 2512.05150 • Published • 74 -
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper • 2512.16093 • Published • 63
VLM
Video
Platform
-
UFO^3: Weaving the Digital Agent Galaxy
Paper • 2511.11332 • Published • 18 -
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
Paper • 2512.02014 • Published • 68 -
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 183
Survey
Transformer
Image Generate
Image Generate
-
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
Paper • 2511.19365 • Published • 64 -
The Collapse of Patches
Paper • 2511.22281 • Published • 6 -
Flow Straighter and Faster: Efficient One-Step Generative Modeling via MeanFlow on Rectified Trajectories
Paper • 2511.23342 • Published • 14 -
Glance: Accelerating Diffusion Models with 1 Sample
Paper • 2512.02899 • Published • 28
Editing
-
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Paper • 2511.09611 • Published • 68 -
In-Video Instructions: Visual Signals as Generative Control
Paper • 2511.19401 • Published • 30 -
Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
Paper • 2512.17909 • Published • 35
Pretrain
Survey
Diffusion
-
ReFusion: A Diffusion Large Language Model with Parallel Autoregressive Decoding
Paper • 2512.13586 • Published • 87 -
TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
Paper • 2512.05150 • Published • 74 -
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper • 2512.16093 • Published • 63
Transformer
VLM
Image Generate
Image Generate
-
DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
Paper • 2511.19365 • Published • 64 -
The Collapse of Patches
Paper • 2511.22281 • Published • 6 -
Flow Straighter and Faster: Efficient One-Step Generative Modeling via MeanFlow on Rectified Trajectories
Paper • 2511.23342 • Published • 14 -
Glance: Accelerating Diffusion Models with 1 Sample
Paper • 2512.02899 • Published • 28
Video
Editing
-
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Paper • 2511.09611 • Published • 68 -
In-Video Instructions: Visual Signals as Generative Control
Paper • 2511.19401 • Published • 30 -
Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing
Paper • 2512.17909 • Published • 35
Platform
-
UFO^3: Weaving the Digital Agent Galaxy
Paper • 2511.11332 • Published • 18 -
TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
Paper • 2512.02014 • Published • 68 -
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 183