Fredrik K. Gustafsson's Avatar

Fredrik K. Gustafsson

@fregu856.bsky.social

Postdoc at IBME in Oxford. Machine learning for healthcare. https://www.fregu856.com/

217 Followers  |  861 Following  |  25 Posts  |  Joined: 30.11.2024
Posts Following

Posts by Fredrik K. Gustafsson (@fregu856.bsky.social)

Post image

My year of reading in 2025: www.fregu856.com/post/year_of...

I read 113 papers in 2025, complete list: github.com/fregu856/pap...

Top 25 papers that I found particularly interesting and/or well written (in alphabetical order):

18.01.2026 12:09 — 👍 5    🔁 0    💬 0    📌 0
Post image

New preprint, work led together with Erik Thiringer:

Scanner-Induced Domain Shifts Undermine the Robustness of Pathology Foundation Models.

arxiv.org/abs/2601.04163

12.01.2026 12:59 — 👍 3    🔁 0    💬 0    📌 0

Isn't there a lot of noise in these decisions, just like for conference papers etc?

31.10.2025 16:02 — 👍 1    🔁 0    💬 1    📌 0

Grattis!

10.10.2025 04:29 — 👍 1    🔁 0    💬 0    📌 0
GitHub - fregu856/papers: I categorize, annotate and write comments for all research papers I read (500+ papers since 2018). I categorize, annotate and write comments for all research papers I read (500+ papers since 2018). - fregu856/papers

I just reached 500 read papers on the Github repository I use to track and organize my reading:
github.com/fregu856/pap...

07.08.2025 08:28 — 👍 4    🔁 0    💬 0    📌 0
Post image

Very happy to have joined the group of David Clifton at IBME in Oxford as a postdoc, to work on machine learning for healthcare!

The group is also recruiting multiple new postdocs, please apply before August 18:
eng.ox.ac.uk/jobs/job-det...

21.07.2025 07:59 — 👍 4    🔁 0    💬 0    📌 0

The waiting area is also quite dull and gets really crowded, probably the worst part of my entire trip.

16.07.2025 10:08 — 👍 0    🔁 0    💬 1    📌 0

I think it was already in the batch of papers I was given to rate, basically no pathology-related papers, for example. ICML was definitely better in this regard.

04.07.2025 04:16 — 👍 1    🔁 0    💬 1    📌 0

Not super happy with my assigned NeurIPS papers this year, I found them less interesting/relevant than I usually do. But oh well, still quite solid papers overall, and I do think it's good to be forced to read papers from slightly different areas sometimes.

03.07.2025 11:48 — 👍 0    🔁 0    💬 1    📌 0
Post image

Our paper "Taming Diffusion Models for Image Restoration: A Review" has now been published, work led by Ziwei Luo:

royalsocietypublishing.org/doi/10.1098/...

25.06.2025 07:02 — 👍 9    🔁 1    💬 0    📌 0
Post image

New preprint, work lead by Ziwei Luo:

Forward-only Diffusion Probabilistic Models.

arxiv.org/abs/2505.16733
github.com/Algolzw/FoD
algolzw.github.io/fod/

23.05.2025 11:35 — 👍 6    🔁 0    💬 0    📌 0

Looks very useful, thanks for sharing!

02.04.2025 06:57 — 👍 1    🔁 0    💬 0    📌 0

Nice, saw this on arxiv and thought it seemed interesting, might read this as well, thanks!

24.03.2025 07:42 — 👍 0    🔁 0    💬 0    📌 0

Nice, thanks!

I actually wrote "The one proper method change that seems to have the biggest effect is probably adding the KoLeo regularization loss term?" in my notes, so would be nice to read more about how that works.

23.03.2025 15:46 — 👍 1    🔁 0    💬 1    📌 0

The main thing definitely seems to be that they scale iBOT from ViT-L/16 trained on ImageNet-22k (14 million images) to ViT-g/14 trained on their LVD-142M dataset (142 million images).

Their model distillation approach is also interesting, distilling their ViT-g down to ViT-L and smaller models.

23.03.2025 15:21 — 👍 2    🔁 0    💬 1    📌 0

"We revisit existing discriminative self-supervised approaches [...] such as iBOT, and we reconsider some of their design choices under the lens of a larger dataset. Most of our technical contributions are tailored toward stabilizing and accelerating [...] when scaling in model and data sizes"

23.03.2025 15:21 — 👍 1    🔁 0    💬 1    📌 0

iBOT: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)

DINOv2: Learning Robust Visual Features without Supervision (TMLR, 2024)

DINOv2 doesn't really add much methodological difference compared to iBOT, they give a good summary of what they do:

23.03.2025 15:21 — 👍 1    🔁 0    💬 1    📌 0

I've been trying to properly understand how/why DINOv2 works, and I think this is a good sequence of papers to read for that:

(BYOL) Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning (NeurIPS 2020)

(DINO) Emerging Properties in Self-Supervised Vision Transformers (ICCV 2021)

23.03.2025 15:21 — 👍 24    🔁 4    💬 2    📌 0

I really didn't like the ICML review template though, why do we have to make things overly complicated? Please just give me some variation of Summary, Strenghts, Weaknesses, Questions, Detailed comments and Justification of rating!

14.03.2025 13:20 — 👍 0    🔁 0    💬 0    📌 0
Fredrik K. Gustafsson | Postdoc | Machine Learning for Computational Pathology Postdoc | Machine Learning for Computational Pathology

102 papers to be exact: www.fregu856.com#service

14.03.2025 13:19 — 👍 0    🔁 0    💬 0    📌 0

Finished my 5 #ICML reviews, and realized that I now have passed 100 reviewed papers in total during my career. Actually feels like a pretty cool milestone!

14.03.2025 13:12 — 👍 6    🔁 0    💬 1    📌 0

First time I'm reviewing for MIDL. Quite interetsing papers overall, and I like the review template.

But, 8 pages in this template seems too short. Not enough space to actually do things properly (e.g., explain the method in detail ~and~ have an extensive experimental evaluation).

22.02.2025 09:41 — 👍 0    🔁 0    💬 0    📌 0
Post image

My year of reading in 2024: www.fregu856.com/post/year_of...

I read 99 papers in 2024. Complete list: github.com/fregu856/pap...

Top 15 favorite papers that I found particularly interesting and/or well-written (in alphabetical order):

04.01.2025 07:04 — 👍 5    🔁 0    💬 0    📌 0
Post image

Recent preprint: Evaluating Deep Regression Models for WSI-Based Gene-Expression Prediction.

arxiv.org/abs/2410.00945

30.11.2024 06:28 — 👍 2    🔁 1    💬 0    📌 0
Post image

Recent preprint: Evaluating Computational Pathology Foundation Models for Prostate Cancer Grading under Distribution Shifts

arxiv.org/abs/2410.06723

30.11.2024 06:27 — 👍 2    🔁 0    💬 0    📌 0