no code implementations • 2 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.
2 code implementations • 6 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.
1 code implementation • 25 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.
1 code implementation • 13 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.
Ranked #5 on
Code Generation
on CodeContests
no code implementations • 18 Jul 2023 • Rithesh Murthy, Shelby Heinecke, Juan Carlos Niebles, Zhiwei Liu, Le Xue, Weiran Yao, Yihao Feng, Zeyuan Chen, Akash Gokul, Devansh Arpit, ran Xu, Phil Mui, Huan Wang, Caiming Xiong, Silvio Savarese
In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX.
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.
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.
no code implementations • 7 Sep 2022 • Kevin Miao, Akash Gokul, Raghav Singh, Suzanne Petryk, Joseph Gonzalez, Kurt Keutzer, Trevor Darrell, Colorado Reed
SPAN operates by regularizing attention masks from separate transformer heads to follow various priors over semantic regions.
1 code implementation • 25 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.
1 code implementation • ICLR 2021 • Sayna Ebrahimi, Suzanne Petryk, Akash Gokul, William Gan, Joseph E. Gonzalez, Marcus Rohrbach, Trevor Darrell
The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting.