Maitreya Patel's picture

Maitreya Patel

mpatel57

·

https://maitreyapatel.com

AI & ML interests

Text to Image Generative Models, Vision-Language Representation Learning

Recent Activity

liked a Space 3 days ago

briaai/BRIA-RMBG-1.4

liked a Space 3 days ago

VAST-AI/MV-Adapter-I2MV-SDXL

commented a paper 14 days ago

FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models

View all activity

Organizations

mpatel57's activity

upvoted 2 papers 24 days ago

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation

Paper • 2412.00100 • Published 29 days ago • 16

TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives

Paper • 2411.02545 • Published Nov 4 • 1

upvoted 2 collections 26 days ago

TripletCLIP

TripletCLIP Checkpoints • 2 items • Updated 26 days ago • 3

Benchmark Checkpoints

Weights of the TripletCLIP and baselines on custom training scripts • 9 items • Updated 26 days ago • 2

upvoted a collection 27 days ago

FlowChef

Steering Rectified Flow Models in the Vector Field for Controlled Image Generation • 3 items • Updated 27 days ago • 1

upvoted a paper 4 months ago

Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing

Paper • 2409.01322 • Published Sep 2 • 94

upvoted 5 papers 5 months ago

Transformer Explainer: Interactive Learning of Text-Generative Models

Paper • 2408.04619 • Published Aug 8 • 155

TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models

Paper • 2408.00735 • Published Aug 1 • 16

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

Paper • 2408.00653 • Published Aug 1 • 28

Tora: Trajectory-oriented Diffusion Transformer for Video Generation

Paper • 2407.21705 • Published Jul 31 • 27

FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention

Paper • 2407.19918 • Published Jul 29 • 49

upvoted 2 papers 7 months ago

An Image is Worth 32 Tokens for Reconstruction and Generation

Paper • 2406.07550 • Published Jun 11 • 57

Zero-shot Image Editing with Reference Imitation

Paper • 2406.07547 • Published Jun 11 • 31

upvoted 2 papers 9 months ago

Bigger is not Always Better: Scaling Properties of Latent Diffusion Models

Paper • 2404.01367 • Published Apr 1 • 21

Streaming Dense Video Captioning

Paper • 2404.01297 • Published Apr 1 • 11

upvoted a collection 9 months ago

Representative Papers

Collection of research papers published by the organization members • 4 items • Updated Mar 30 • 1

upvoted a collection 10 months ago

ECLIPSE Series Priors

ECLIPSE priors for kandinsky v2.2 for T2I and Personalized T2I. • 3 items • Updated Apr 12 • 1

upvoted a paper 11 months ago

Magic-Me: Identity-Specific Video Customized Diffusion

Paper • 2402.09368 • Published Feb 14 • 27

upvoted a collection 11 months ago

ECLIPSE Stack

5 items • Updated Aug 7 • 1

upvoted a paper 11 months ago

λ-ECLIPSE: Multi-Concept Personalized Text-to-Image Diffusion Models by Leveraging CLIP Latent Space

Paper • 2402.05195 • Published Feb 7 • 18