Search Results for author:
Found 9 papers, 6 papers with code
Aligning Diffusion Models by Optimizing Human Utility
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
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.
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
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 #2 on
Code Generation
on CodeContests
(Test Set pass@1 metric)
REX: Rapid Exploration and eXploitation for AI Agents
In this paper, we propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX.
End-to-End Diffusion Latent Optimization Improves Classifier Guidance
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.
EDICT: Exact Diffusion Inversion via Coupled Transformations
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.
Prior Knowledge-Guided Attention in Self-Supervised Vision Transformers
SPAN operates by regularizing attention masks from separate transformer heads to follow various priors over semantic regions.
Refine and Represent: Region-to-Object Representation Learning
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.
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting
The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting.
