How does AI interact with culture?
We’re thrilled to have Dr. Maria Antoniak (@mariaa.bsky.social) join us at FGVC! Her interdisciplinary work on AI in the humanities brings a new perspective to our workshop: the fine-grained categorization of the intangible parts of culture. See you at #CVPR2026!
FGVC13 submissions are OPEN NOW!
Whether you have new or existing work, we have a track for you:
1. Proceedings: Due Feb 27
2. Non-archival: Due April 3
3. Nectar (Already published): Due April 30
Full details: sites.google.com/view/fgvc13/...
#AI #CVPR2026 #MachineLearning #DeepLearning
We will be running the 13th iteration of the workshop on Fine-Grained Visual Categorization (FGVC) at CVPR this summer. We have an open call for papers that explore questions in visual recognition.
Please see our website for more information:
sites.google.com/view/fgvc13/...
AI-Integrated Network Ecosystem Models for Predicting Biodiversity Change
www.findaphd.com/phds/project...
Based at University College London
Supervision Team: Kate Jones (@profkatej.bsky.social), Oisin Mac Aodha, Drew Purves
Deadline Jan 19th
Identifying Emerging Zoonotic Disease Hotspots
www.findaphd.com/phds/project...
Based at University of Edinburgh
Supervision Team: Oisin Mac Aodha, Rowland Kao (@rowlandkao.bsky.social)
Deadline Jan 20th
We have two open PhD positions at the interface of AI and ecology. Start dates are Sept 2026.
We are looking for candidates with a background in AI/CS, Math, Stats, or Physics that are passionate about solving challenging problems in these domains.
Application deadline is in two weeks.
Very cool!
Thank you to everyone who joined us at #NeurIPS2025 for the inaugural AI for Non-Human Animal Communication workshop!
Seeing a room full of researchers from ML, bioacoustics, and ethology gather around shared questions was such an exciting moment for the field.
The full paper can be found here:
Jamais Vu: Exposing the Generalization Gap in Supervised Semantic Correspondence
arxiv.org/abs/2506.08220
This work was led by Octave Mariotti, postdoc at the University of Edinburgh:
omariott.github.io
With the help of a new dataset set we demonstrate this issue and show that it can be mitigated with the help of a learned 3D prior.
Stop by poster #4403 today from 4:30pm to 7:30pm at #NuerIPS2025 in San Diego to learn more.
The goal of semantic correspondence estimation is to establish semantically meaningful matches across different images of an object. It turns out however that recent supervised methods generalize poorly beyond the annotated keypoints seen during training. #NeurIPS2025
The full paper can be found here:
The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
openreview.net/pdf?id=w98hM...
Thanks to the NanoGPT speedrun team for the inspiration:
github.com/KellerJordan...
Today at #NeurIPS2025, Bingchen Zhao will be presenting our new LLM Speedrunning Benchmark which evaluates an LLM agent's ability to reproduce scientific finding in the context of LLM training.
Stop by poster #3313 from 4:30pm to 7:30pm at #NuerIPS2025 today in San Diego to learn more.
Leonie @bossemel.bsky.social will be presenting CleverBirds, our new human visual learning dataset, at #NeurIPS2025 in San Diego today.
Stop by poster #2012 from 11am-2pm to learn more.
Want to discover and visualise the differences between two different machine learning models?
We will be presenting Neehar's work on "Representational Difference Explanations" at #NeurIPS2025 in San Diego from 4:30pm to 7:30pm PT today. Poster #1115.
Full paper:
arxiv.org/abs/2505.23917
We will be presenting Elle Miller's (@elle-miller.bsky.social) work on Enhancing Tactile-based Reinforcement Learning for Robotic Control at #NeurIPS2025 in San Diego today.
Stop by poster #2317 from 11am to 2pm PT today to learn more.
Full paper:
arxiv.org/abs/2510.21609
Hi Ben. Yes indeed, they require a certain number of observations. However, crucially, it is not trivial to "influence" what criteria are used perform the clustering (e.g. in the case of images, the visual features). Our approach enables the discovery of interpretable features that can be clustered.
There is more info in our new preprint:
INQUIRE-Search: A Framework for Interactive Discovery in Large-Scale Biodiversity Databases
arxiv.org/abs/2511.15656
Check out this fantastic TED talk from Sara Beery @sarameghanbeery.bsky.social
In it, she talks about how computer vision techniques can assist with extracting a wealth of information and insights from large image collections that depict the natural world.
The full paper can be found here:
Interpretable Text-Guided Image Clustering via Iterative Search
arxiv.org/abs/2506.12514
Today at #BMVC2025, Bingchen Zhao will present our new text-guided clustering approach uses an iterative discovery process, guided by an unsupervised clustering objective, to generate interpretable visual concepts that better capture the criteria expressed in a user's instructions.
Traditional clustering methods aim to group unlabelled data points based on their similarity to each other. However, clustering, in the absence of additional information, is an ill-posed problem as there may be many different, yet equally valid, ways to partition a dataset.
This project is in collaboration with Rowland Kao @rowlandkao.bsky.social
The PhD Programme has some information sessions coming up (including one today).
21st November, 14:30-15:30 GMT
9th December, 10:00-11:00 GMT
lnkd.in/egccTN2d
We have PhD opportunity (start date Sep 2026) at the University of Edinburgh at the intersection of biodiversity mapping and zoonotic disease prediction.
It is part of the UKRI AI Centre for Doctoral Training in Biomedical Innovation based in the School of Informatics:
ai4bi-cdt.ed.ac.uk
Check out Neehar's (@therealpaneni.bsky.social) upcoming #NeurIPS2025 paper titled:
Representational Difference Explanations
He has a cool new approach for enabling more direct and interpretable model comparisons by isolating representational differences between models.
arxiv.org/abs/2505.23917
Check out Leonie's (@bossemel.bsky.social) upcoming NeurIPS Datasets and Benchmarks paper about a really interesting new dataset for evaluating models of human visual learning.
Great PhD opportunity to work with Serge and Toke on a really interesting computer vision / machine learning problem.
Our speakers for the inaugural AI for Non-Human Animal Communication workshop at NeurIPS 2025, including Laela Sayigh, Oisin Mac Aodha, and Julie Elie.
Meet our speakers for the AI for Non-Human Animal Communication workshop at
@NeurIPSConf!
🐬 Laela Sayigh – decoding dolphin communication
🦇 Oisin Mac Aodha – AI for biodiversity monitoring
🐦 Julie Elie – neural mechanisms of songbird & bat vocal learning
Learn more and join: aiforanimalcomms.org
Viacheslav's group does fantastic work in machine learning in geometric learning and uncertainty quantification.
For those looking to start a PhD in the near future this is a brilliant opportunity to work with a great advisor!
#phd #ml #edinburgh
