Publications

For the most updated version of my publications page, see my Google Scholar profile.

Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics

Published in RSS 2026 Workshops on Data-Centric Robotics and "It's the Demos" [Paper]

🏆 Best Paper Award — Data-Centric Robotics Workshop, RSS 2026

🏆 Most Useful Practical Information Award — "It's the Demos" Workshop, RSS 2026

Citation: Adam Wei, Nicholas Pfaff, Thomas Cohn, Arif Kerem Dayı, Constantinos Daskalakis, Giannis Daras, Russ Tedrake, "Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics", RSS 2026 Workshops on Data-Centric Robotics and "It's the Demos"

Diffusion Based Auctions for Banner Ads

Published in EC 2026

Citation: Lillian Sun, Henry Huang, Fucheng Warren Zhu, Giannis Daras, Constantinos Daskalakis, "Diffusion Based Auctions for Banner Ads", EC 2026

Ambient Physics: Training Neural PDE Solvers with Partial Observations

Preprint [Paper]

Citation: Harris Abdul Majid, Giannis Daras, Francesco Tudisco, Steven McDonagh, "Ambient Physics: Training Neural PDE Solvers with Partial Observations"

Ambient Dataloops: Generative Models for Dataset Refinement

Published in ICML 2026 [Paper]

Citation: Adrián Rodríguez-Muñoz, William Daspit, Adam Klivans, Antonio Torralba, Constantinos Daskalakis, Giannis Daras, "Ambient Dataloops: Generative Models for Dataset Refinement", ICML 2026

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization

Preprint [Paper] [Code]

Citation: Danial Hosseintabar, Fan Chen, *Giannis Daras*, Antonio Torralba, Constantinos Daskalakis, "DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization"

Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment

Preprint [Paper] [Code]

Citation: Loukas Sfountouris, Giannis Daras, Paris Giampouras, "Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment"

Ambient Proteins: Training Diffusion Models on Low Quality Structures

Published as an Spotlight in NeurIPS 2025 [Paper] [Code]

Citation: Giannis Daras*, Jeffrey Ouyang-Zhang*, Krithika Ravishankar, William Daspit, Costis Daskalakis, Qiang Liu, Adam Klivans, Daniel J. Diaz, "Ambient Proteins: Training Diffusion Models on Low Quality Structures", NeurIPS 2025

Ambient Diffusion Omni: Training Good Models with Bad Data

Published as an Spotlight in NeurIPS 2025 [Paper] [Code]

Citation: Giannis Daras*, Adrian Rodriguez-Munoz*, Adam Klivans, Antonio Torralba, Constantinos Daskalakis, "Ambient Diffusion Omni: Training Good Models with Bad Data", NeurIPS 2025

How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion

Published in ICLR 2025 [Paper] [Code]

Citation: Giannis Daras, Yeshwanth Cherapanamjeri, Constantinos Daskalakis, "How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion", ICLR 2025

Opt-In Art: Learning Art Styles Only from Few Examples

Published in NeurIPS 2025 Creative AI Track [Paper] [Code]

Citation: Hui Ren (*), Joanna Materzynska (*), Rohit Gandikota, Giannis Daras, David Bau, Antonio Torralba, "Opt-In Art: Learning Art Styles Only from Few Examples", NeurIPS 2025 Creative AI Track

Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models

Published in ICLR 2025 [Paper]

Citation: Negin Raoof, Litu Rout, Giannis Daras, Sujay Sanghavi, Constantine Caramanis, Sanjay Shakkottai, Alexandros G. Dimakis, "Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models", ICLR 2025

Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Data

Published in ICLR 2025 [Paper] [Code]

Citation: Asad Aali, Giannis Daras, Brett Levac, Sidharth Kumar, Alexandros G. Dimakis, Jonathan I. Tamir', "Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Data", ICLR 2025

DataComp-LM: In search of the next generation of training sets for language models

Published in NeurIPS 2024 Track Datasets and Benchmarks [Paper] [Code]

Citation: Jeffrey Li, Alex Fang, Georgios Smyrnis, Maor Ivgi, Matt Jordan, Samir Gadre, Hritik Bansal, Etash Guha, Sedrick Keh, Kushal Arora, Saurabh Garg, Rui Xin, Niklas Muennighoff, Reinhard Heckel, Jean Mercat, Mayee Chen, Suchin Gururangan, Mitchell Wortsman, Alon Albalak, Yonatan Bitton, Marianna Nezhurina, Amro Abbas, Cheng-Yu Hsieh, Dhruba Ghosh, Josh Gardner, Maciej Kilian, Hanlin Zhang, Rulin Shao, Sarah Pratt, Sunny Sanyal, Gabriel Ilharco, Giannis Daras, Kalyani Marathe, Aaron Gokaslan, Jieyu Zhang, Khyathi Chandu, Thao Nguyen, Igor Vasiljevic, Sham Kakade, Shuran Song, Sujay Sanghavi, Fartash Faghri, Sewoong Oh, Luke Zettlemoyer, Kyle Lo, Alaaeldin El-Nouby, Hadi Pouransari, Alexander Toshev, Stephanie Wang, Dirk Groeneveld, Luca Soldaini, Pang Wei Koh, Jenia Jitsev, Thomas Kollar, Alexandros G. Dimakis, Yair Carmon, Achal Dave, Ludwig Schmidt, Vaishaal Shankar, "DataComp-LM: In search of the next generation of training sets for language models", NeurIPS 2024 Track Datasets and Benchmarks

Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data

Published in ICML 2024 [Paper] [Code]

Citation: Giannis Daras, Alexandros G. Dimakis, Constantinos Daskalakis, "Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data", ICML 2024

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

Published in NeurIPS 2023 [Paper] [Code]

Citation: Litu Rout, Negin Raoof, Giannis Daras, Constantine Caramanis, Alexandros G. Dimakis, Sanjay Shakkottai, "Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models", NeurIPS 2023

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

Published in NeurIPS 2023 [Paper] [Code]

Citation: Giannis Daras, Kulin Shah, Yuval Dagan, Aravind Gollakota, Alexandros G. Dimakis, Adam Klivans, "Ambient Diffusion: Learning Clean Distributions from Corrupted Data", NeurIPS 2023

DataComp: In search of the next generation of multimodal datasets

Published as an Oral in NeurIPS 2023 [Paper] [Code]

Citation: Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt, "DataComp: In search of the next generation of multimodal datasets", NeurIPS 2023

Giannis Daras

Publications

Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics

Diffusion Based Auctions for Banner Ads

Ambient Physics: Training Neural PDE Solvers with Partial Observations

Ambient Dataloops: Generative Models for Dataset Refinement

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization

Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment

Ambient Proteins: Training Diffusion Models on Low Quality Structures

Ambient Diffusion Omni: Training Good Models with Bad Data

How much is a noisy image worth? Data Scaling Laws for Ambient Diffusion

Opt-In Art: Learning Art Styles Only from Few Examples

Infilling Score: A Pretraining Data Detection Algorithm for Large Language Models

Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models trained on Corrupted Data

DataComp-LM: In search of the next generation of training sets for language models

Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

DataComp: In search of the next generation of multimodal datasets

Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis for DDIM-Type Samplers

Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent

Multiresolution Textual Inversion

Soft Diffusion: Score Matching for General Corruptions

Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems

Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve

Discovering the Hidden Vocabulary of DALLE-2

Solving Inverse Problems with NerfGANs

Robust Compressed Sensing MRI with Deep Generative Priors

Intermediate Layer Optimization for Inverse Problems using Deep Generative Models

SMYRF: Efficient Attention using Asymmetric Clustering

Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models