Search Results for author: Akash Gokul

Found 10 papers, 7 papers with code

OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows

no code implementations2 Dec 2024 Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Zichun Liao, Yusuke Kato, Kazuki Kozuka, Aditya Grover

We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis.

Audio Synthesis Image Generation +1

Aligning Diffusion Models by Optimizing Human Utility

2 code implementations6 Apr 2024 Shufan Li, Konstantinos Kallidromitis, Akash Gokul, Yusuke Kato, Kazuki Kozuka

We present Diffusion-KTO, a novel approach for aligning text-to-image diffusion models by formulating the alignment objective as the maximization of expected human utility.

BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities in Pretrained Diffusion Models

1 code implementation25 Jan 2024 Senthil Purushwalkam, Akash Gokul, Shafiq Joty, Nikhil Naik

We propose a novel architecture (BootPIG) that allows a user to provide reference images of an object in order to guide the appearance of a concept in the generated images.

Image Segmentation Personalized Image Generation +2

CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules

1 code implementation13 Oct 2023 Hung Le, Hailin Chen, Amrita Saha, Akash Gokul, Doyen Sahoo, Shafiq Joty

We find that by naturally encouraging the LLM to reuse the previously developed and verified sub-modules, CodeChain can significantly boost both modularity as well as correctness of the generated solutions, achieving relative pass@1 improvements of 35% on APPS and 76% on CodeContests.

Code Generation HumanEval

End-to-End Diffusion Latent Optimization Improves Classifier Guidance

1 code implementation ICCV 2023 Bram Wallace, Akash Gokul, Stefano Ermon, Nikhil Naik

Classifier guidance -- using the gradients of an image classifier to steer the generations of a diffusion model -- has the potential to dramatically expand the creative control over image generation and editing.

Denoising Image Generation

EDICT: Exact Diffusion Inversion via Coupled Transformations

2 code implementations CVPR 2023 Bram Wallace, Akash Gokul, Nikhil Naik

EDICT enables mathematically exact inversion of real and model-generated images by maintaining two coupled noise vectors which are used to invert each other in an alternating fashion.

Denoising Image Reconstruction +3

Refine and Represent: Region-to-Object Representation Learning

1 code implementation25 Aug 2022 Akash Gokul, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato, Kazuki Kozuka, Trevor Darrell, Colorado J Reed

Recent works in self-supervised learning have demonstrated strong performance on scene-level dense prediction tasks by pretraining with object-centric or region-based correspondence objectives.

Object Representation Learning +4

Cannot find the paper you are looking for? You can Submit a new open access paper.