74 citations · 231 across the 27 of their papers we have counts for
30 papers
Diffusion-Based Auctions for Multi-Winner Banner Ads
Lilian Sun, Henry Huang, Fucheng Warren Zhu +2
We propose a new framework for banner ad auctions, leveraging diffusion models to allow for multiple bidders to co-win a single banner ad opportunity, and in particular influence t…
PoEM: Predicting RL Outcomes from Existing Policies
Kimia Hamidieh, Giannis Daras, Antonio Torralba
Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as human alignment, correctness, or instruction following. This post-training…
Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics
Adam Wei, Nicholas Pfaff, Thomas Cohn +4
We propose Ambient Diffusion Policy, a simple and principled method for imitation learning from suboptimal data in robotics. High-quality, task-specific robot data is expensive and…
Ambient Physics: Training Neural PDE Solvers with Partial Observations
Harris Abdul Majid, Giannis Daras, Francesco Tudisco +1
In many scientific settings, acquiring complete observations of PDE coefficients and solutions can be expensive, hazardous, or impossible. Recent diffusion-based methods can recons…
Ambient Dataloops: Generative Models for Dataset Refinement
Adrián Rodríguez-Muñoz, William Daspit, Adam Klivans +3
We propose Ambient Dataloops, an iterative framework for refining datasets that makes it easier for diffusion models to learn the underlying data distribution. Modern datasets cont…
Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
Loukas Sfountouris, Giannis Daras, Paris Giampouras
Enforcing alignment between the internal representations of diffusion or flow-based generative models and those of pretrained self-supervised encoders has recently been shown to pr…
DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
Danial Hosseintabar, Fan Chen, Giannis Daras +2
Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains…
Ambient Diffusion Omni: Training Good Models with Bad Data
Giannis Daras, Adrian Rodriguez-Munoz, Adam Klivans +2
We show how to use low-quality, synthetic, and out-of-distribution images to improve the quality of a diffusion model. Typically, diffusion models are trained on curated datasets t…
Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
Kulin Shah, Alkis Kalavasis, Adam R. Klivans +1
There is strong empirical evidence that the state-of-the-art diffusion modeling paradigm leads to models that memorize the training set, especially when the training set is small.…
How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion
Giannis Daras, Yeshwanth Cherapanamjeri, Constantinos Daskalakis
The quality of generative models depends on the quality of the data they are trained on. Creating large-scale, high-quality datasets is often expensive and sometimes impossible, e.…
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
Giannis Daras, Weili Nie, Karsten Kreis +4
Using image models naively for solving inverse video problems often suffers from flickering, texture-sticking, and temporal inconsistency in generated videos. To tackle these probl…
A Survey on Diffusion Models for Inverse Problems
Giannis Daras, Hyungjin Chung, Chieh-Hsin Lai +5
Diffusion models have become increasingly popular for generative modeling due to their ability to generate high-quality samples. This has unlocked exciting new possibilities for so…
DataComp-LM: In search of the next generation of training sets for language models
Jeffrey Li, Alex Fang, Georgios Smyrnis +56
We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardize…
Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data
Giannis Daras, Alexandros G. Dimakis, Constantinos Daskalakis
Ambient diffusion is a recently proposed framework for training diffusion models using corrupted data. Both Ambient Diffusion and alternative SURE-based approaches for learning dif…
Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data
Asad Aali, Giannis Daras, Brett Levac +3
We provide a framework for solving inverse problems with diffusion models learned from linearly corrupted data. Firstly, we extend the Ambient Diffusion framework to enable trainin…
Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models
Litu Rout, Negin Raoof, Giannis Daras +3
We present the first framework to solve linear inverse problems leveraging pre-trained latent diffusion models. Previously proposed algorithms (such as DPS and DDRM) only apply to…
Ambient Diffusion: Learning Clean Distributions from Corrupted Data
Giannis Daras, Kulin Shah, Yuval Dagan +3
We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where acce…
DataComp: In search of the next generation of multimodal datasets
Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang +31
Multimodal datasets are a critical component in recent breakthroughs such as Stable Diffusion and GPT-4, yet their design does not receive the same research attention as model arch…
Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplers
Sitan Chen, Giannis Daras, Alexandros G. Dimakis
We develop a framework for non-asymptotic analysis of deterministic samplers used for diffusion generative modeling. Several recent works have analyzed stochastic samplers using to…
Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent
Giannis Daras, Yuval Dagan, Alexandros G. Dimakis +1
Imperfect score-matching leads to a shift between the training and the sampling distribution of diffusion models. Due to the recursive nature of the generation process, errors in p…
Multiresolution Textual Inversion
Giannis Daras, Alexandros G. Dimakis
We extend Textual Inversion to learn pseudo-words that represent a concept at different resolutions. This allows us to generate images that use the concept with different levels of…
Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve
Giannis Daras, Negin Raoof, Zoi Gkalitsiou +1
We find a surprising connection between multitask learning and robustness to neuron failures. Our experiments show that bilingual language models retain higher performance under va…
Soft Diffusion: Score Matching for General Corruptions
Giannis Daras, Mauricio Delbracio, Hossein Talebi +2
We define a broader family of corruption processes that generalizes previously known diffusion models. To reverse these general diffusions, we propose a new objective called Soft S…
Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems
Giannis Daras, Yuval Dagan, Alexandros G. Dimakis +1
We prove fast mixing and characterize the stationary distribution of the Langevin Algorithm for inverting random weighted DNN generators. This result extends the work of Hand and V…