11 15

Oğuzhan Ercan

oguzhanercan

AI & ML interests

Computer Vision, Generative Vision, first trajectory bender

Recent Activity

New activity 14 days ago

HighCWu/FLUX.1-dev-4bit:Questions about LoRA

upvoted a paper 20 days ago

CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes

commented a paper 20 days ago

Face Anonymization Made Simple

View all activity

Organizations

None yet

oguzhanercan's activity

New activity in HighCWu/FLUX.1-dev-4bit 14 days ago

Questions about LoRA

#5 opened 2 months ago by

tungdop2

upvoted a paper 20 days ago

CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes

Paper • 2411.00771 • Published 24 days ago • 9

commented 2 papers 20 days ago

Face Anonymization Made Simple

Paper • 2411.00762 • Published 24 days ago • 7 •

Face Anonymization Made Simple

Paper • 2411.00762 • Published 24 days ago • 7 •

New activity in PrunaAI/FLUX.1-schnell-4bit 21 days ago

Can't get attribute'EmbedND'

#3 opened 21 days ago by

oguzhanercan

upvoted a paper 24 days ago

MarDini: Masked Autoregressive Diffusion for Video Generation at Scale

Paper • 2410.20280 • Published about 1 month ago • 21

upvoted a paper about 1 month ago

Unbounded: A Generative Infinite Game of Character Life Simulation

Paper • 2410.18975 • Published Oct 24 • 34

New activity in sayakpaul/flux.1-dev-nf4-with-bnb-integration about 1 month ago

Bitsandbytes installation problem

#4 opened about 1 month ago by

oguzhanercan

upvoted a paper about 1 month ago

FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model

Paper • 2410.13925 • Published Oct 17 • 22

commented a paper about 1 month ago

MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models

Paper • 2410.13370 • Published Oct 17 • 35 •

upvoted a paper about 1 month ago

Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion

Paper • 2410.13674 • Published Oct 17 • 15

commented 2 papers about 1 month ago

MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models

Paper • 2410.13370 • Published Oct 17 • 35 •

Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models

Paper • 2410.11081 • Published Oct 14 • 18 •

upvoted 4 papers about 2 months ago

Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning

Paper • 2410.06373 • Published Oct 8 • 34

Pyramidal Flow Matching for Efficient Video Generative Modeling

Paper • 2410.05954 • Published Oct 8 • 38

IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

Paper • 2410.07171 • Published Oct 9 • 41

Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

Paper • 2410.05363 • Published Oct 7 • 44

commented 2 papers about 2 months ago

Addition is All You Need for Energy-efficient Language Models

Paper • 2410.00907 • Published Oct 1 • 144 •

Addition is All You Need for Energy-efficient Language Models

Paper • 2410.00907 • Published Oct 1 • 144 •

upvoted a paper about 2 months ago

Addition is All You Need for Energy-efficient Language Models

Paper • 2410.00907 • Published Oct 1 • 144