Raman Dutt
@ramandutt4.bsky.social
Generative AI @Noah's Ark Lab, Huawei & @TuringInstitute | PhD candidate in Biomedical AI @ University of Edinburgh | Efficient Fine-Tuning in Medical AI, Diffusion Models, Autoregressive Image Generation
Pinned
Raman Dutt
@ramandutt4.bsky.social
· Nov 26
GitHub - Raman1121/Diffusion_Memorization_HPO: A framework to reduce memorization in text-to-image diffusion models using HPO
A framework to reduce memorization in text-to-image diffusion models using HPO - Raman1121/Diffusion_Memorization_HPO
github.com
Delighted to share our work "𝐌𝐞𝐦𝐂𝐨𝐧𝐭𝐫𝐨𝐥" now accepted at 𝐖𝐀𝐂𝐕 '𝟐𝟓. We show strong results for medical image generation and also establish an initial benchmark for generative quality and memorization of synthetic chest x-rays!
Paper: arxiv.org/abs/2405.19458
Code: github.com/Raman1121/Di...
More👇
Paper: arxiv.org/abs/2405.19458
Code: github.com/Raman1121/Di...
More👇
Are you working on Text-to-Image generation of Chest X-Rays using the MIMIC dataset?
Here is something I found over the last weekend. 🧵
Observations documented in this preprint -
arxiv.org/abs/2502.07516
Here is something I found over the last weekend. 🧵
Observations documented in this preprint -
arxiv.org/abs/2502.07516
arxiv.org
February 22, 2025 at 3:21 PM
Are you working on Text-to-Image generation of Chest X-Rays using the MIMIC dataset?
Here is something I found over the last weekend. 🧵
Observations documented in this preprint -
arxiv.org/abs/2502.07516
Here is something I found over the last weekend. 🧵
Observations documented in this preprint -
arxiv.org/abs/2502.07516
Hello all,
What’s the best tool to make nice figures for academic AI papers?
What’s the best tool to make nice figures for academic AI papers?
December 7, 2024 at 3:53 PM
Hello all,
What’s the best tool to make nice figures for academic AI papers?
What’s the best tool to make nice figures for academic AI papers?
Not an ML-related post but I am just as happy to share this
December 6, 2024 at 1:48 PM
Not an ML-related post but I am just as happy to share this
1000 followers on Bluesky already that’s crazy
December 5, 2024 at 3:21 PM
1000 followers on Bluesky already that’s crazy
November 27, 2024 at 11:05 PM
Sharing with people who might find this relevant - go.bsky.app/r5eVvT, go.bsky.app/PJKJ8vK, bsky.app/profile/berk...
Delighted to share our work "𝐌𝐞𝐦𝐂𝐨𝐧𝐭𝐫𝐨𝐥" now accepted at 𝐖𝐀𝐂𝐕 '𝟐𝟓. We show strong results for medical image generation and also establish an initial benchmark for generative quality and memorization of synthetic chest x-rays!
Paper: arxiv.org/abs/2405.19458
Code: github.com/Raman1121/Di...
More👇
Paper: arxiv.org/abs/2405.19458
Code: github.com/Raman1121/Di...
More👇
GitHub - Raman1121/Diffusion_Memorization_HPO: A framework to reduce memorization in text-to-image diffusion models using HPO
A framework to reduce memorization in text-to-image diffusion models using HPO - Raman1121/Diffusion_Memorization_HPO
github.com
November 26, 2024 at 6:34 PM
Sharing with people who might find this relevant - go.bsky.app/r5eVvT, go.bsky.app/PJKJ8vK, bsky.app/profile/berk...
Delighted to share our work "𝐌𝐞𝐦𝐂𝐨𝐧𝐭𝐫𝐨𝐥" now accepted at 𝐖𝐀𝐂𝐕 '𝟐𝟓. We show strong results for medical image generation and also establish an initial benchmark for generative quality and memorization of synthetic chest x-rays!
Paper: arxiv.org/abs/2405.19458
Code: github.com/Raman1121/Di...
More👇
Paper: arxiv.org/abs/2405.19458
Code: github.com/Raman1121/Di...
More👇
GitHub - Raman1121/Diffusion_Memorization_HPO: A framework to reduce memorization in text-to-image diffusion models using HPO
A framework to reduce memorization in text-to-image diffusion models using HPO - Raman1121/Diffusion_Memorization_HPO
github.com
November 26, 2024 at 6:21 PM
Delighted to share our work "𝐌𝐞𝐦𝐂𝐨𝐧𝐭𝐫𝐨𝐥" now accepted at 𝐖𝐀𝐂𝐕 '𝟐𝟓. We show strong results for medical image generation and also establish an initial benchmark for generative quality and memorization of synthetic chest x-rays!
Paper: arxiv.org/abs/2405.19458
Code: github.com/Raman1121/Di...
More👇
Paper: arxiv.org/abs/2405.19458
Code: github.com/Raman1121/Di...
More👇
For my fellow medical AI researchers, here is a starter pack - go.bsky.app/r5eVvT
November 25, 2024 at 3:23 PM
For my fellow medical AI researchers, here is a starter pack - go.bsky.app/r5eVvT
A starter pack I would highly recommend (not biased at all 😉)
Starter pack for University of Edinburgh researchers done by the amazing ramandutt4.bsky.social - go.bsky.app/KRNDkN7
University of Edinburgh Starter Pack
Join the conversation
go.bsky.app
November 25, 2024 at 8:39 AM
A starter pack I would highly recommend (not biased at all 😉)
November 24, 2024 at 4:28 PM
Migration to BlueSky successful! Thank you @mmbronstein.bsky.social 🙏
November 24, 2024 at 3:12 PM
Migration to BlueSky successful! Thank you @mmbronstein.bsky.social 🙏
Computer Vision starter pack!
Here we grow again. Introducing my 2nd AWESOME #ComputerVision Starter Pack.
Missed you? Let me know in the thread.
go.bsky.app/Gjcs339
Missed you? Let me know in the thread.
go.bsky.app/Gjcs339
November 24, 2024 at 3:22 AM
Computer Vision starter pack!
Reposted by Raman Dutt
The return of the Autoregressive Image Model: AIMv2 now going multimodal.
Excellent work by @alaaelnouby.bsky.social & team with code and checkpoints already up:
arxiv.org/abs/2411.14402
Excellent work by @alaaelnouby.bsky.social & team with code and checkpoints already up:
arxiv.org/abs/2411.14402
November 22, 2024 at 9:44 AM
The return of the Autoregressive Image Model: AIMv2 now going multimodal.
Excellent work by @alaaelnouby.bsky.social & team with code and checkpoints already up:
arxiv.org/abs/2411.14402
Excellent work by @alaaelnouby.bsky.social & team with code and checkpoints already up:
arxiv.org/abs/2411.14402
Here is a starter pack of researchers from the University of Edinburgh working on all areas of AI!
go.bsky.app/KRNDkN7
go.bsky.app/KRNDkN7
November 21, 2024 at 11:05 PM
Here is a starter pack of researchers from the University of Edinburgh working on all areas of AI!
go.bsky.app/KRNDkN7
go.bsky.app/KRNDkN7
Here is a well-curated list of researchers working on image/ video generation
Started a list of some researchers working on image/video generation. (Not comprehensive at all)
Reply with a paper link and TLDR to get added to the list! I request all grad students to not feel imposter-y and just reply if you work in this field!
#computervision #diffusion
go.bsky.app/SP1uWoE
Reply with a paper link and TLDR to get added to the list! I request all grad students to not feel imposter-y and just reply if you work in this field!
#computervision #diffusion
go.bsky.app/SP1uWoE
November 21, 2024 at 11:04 PM
Here is a well-curated list of researchers working on image/ video generation
Hello Bluesky 👋
Is there a Medical Image Analysis starter pack that I can follow?
Is there a Medical Image Analysis starter pack that I can follow?
November 20, 2024 at 2:32 PM
Hello Bluesky 👋
Is there a Medical Image Analysis starter pack that I can follow?
Is there a Medical Image Analysis starter pack that I can follow?
Controlling the capacity of your diffusion model during fine-tuning strongly helps in reducing memorization!
Work accepted at the GenLaw workshop at #ICML2025
Work accepted at the GenLaw workshop at #ICML2025
Raman Dutt, Pedro Sanchez, Ondrej Bohdal, Sotirios A. Tsaftaris, Timothy Hospedales
Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models
https://arxiv.org/abs/2410.22149
Capacity Control is an Effective Memorization Mitigation Mechanism in Text-Conditional Diffusion Models
https://arxiv.org/abs/2410.22149
November 18, 2024 at 3:58 PM
Controlling the capacity of your diffusion model during fine-tuning strongly helps in reducing memorization!
Work accepted at the GenLaw workshop at #ICML2025
Work accepted at the GenLaw workshop at #ICML2025
Check out our new work that (1) Mitigates Memorization, (2) Improves generative quality, (3) While fine-tuning only 0.019% of the parameters
To appear at #WACV2025 ✨✨
To appear at #WACV2025 ✨✨
Raman Dutt, Pedro Sanchez, Ondrej Bohdal, Sotirios A. Tsaftaris, Timothy Hospedales
MemControl: Mitigating Memorization in Medical Diffusion Models via Automated Parameter Selection
https://arxiv.org/abs/2405.19458
MemControl: Mitigating Memorization in Medical Diffusion Models via Automated Parameter Selection
https://arxiv.org/abs/2405.19458
November 18, 2024 at 3:56 PM
Check out our new work that (1) Mitigates Memorization, (2) Improves generative quality, (3) While fine-tuning only 0.019% of the parameters
To appear at #WACV2025 ✨✨
To appear at #WACV2025 ✨✨
Reposted by Raman Dutt
Raman Dutt, Linus Ericsson, Pedro Sanchez, Sotirios A. Tsaftaris, Timothy Hospedales
Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity
https://arxiv.org/abs/2305.08252
Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity
https://arxiv.org/abs/2305.08252
June 11, 2024 at 7:01 PM
Raman Dutt, Linus Ericsson, Pedro Sanchez, Sotirios A. Tsaftaris, Timothy Hospedales
Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity
https://arxiv.org/abs/2305.08252
Parameter-Efficient Fine-Tuning for Medical Image Analysis: The Missed Opportunity
https://arxiv.org/abs/2305.08252