ELLIS PhD program 2026 applications open
5 experts across 3 network communities independently surfaced this.
5 experts
3 communities
1 sources clustered
Markets & investment
1 expert
Capital, companies and commercial impact.
“Funding schemes: ELLIS - European Laboratory for Learning and Intelligent Systems 31 October 2026 ellis.eu/news/ellis-p... Dependable and Deployable AI for Robotics 27 November 2026 www.cdt-d2air.uk/apply Designing Responsible Natural Language Processing 30…”
Research & technical analysis
1 expert
Evidence, methods and technical implications.
“🚨 Apply now for the #ELLISPhD Program! 🎓 Work with leading AI/ML researchers across Europe, with exchange visits & joint supervision. The application deadline is 31 Oct. Get all info & apply now at ellis.eu/news/ellis-p...”
New
AI field signal
Resource
13h ago
⚡ 344 h early
ELLIS UnConference AI research event
3 experts across 2 network communities independently surfaced this.
3 experts
2 communities
1 sources clustered
“ELLIS UnConference 2026 - 𝗦𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱 𝗠𝗟: Discover the sessions on Neural Representations and Probabilistic ML. 🔎 Sessions: https://bit.ly/4dr7xUb ❗ Register: https://bit.ly/3TOh2WU 📅 ELLIS UnConference - 8 December in Paris, the day before @neuripseurope.bs…”
New
AI field signal
Signal
11h ago
⚡ 7 h early
2 directory members surfaced this signal.
2 experts
1 community
1 sources clustered
“🚨 New work with Adrien Ramanana, @nicolasdufour.bsky.social, Yutong Bai and Patrick Pérez collab @kyutai-labs.bsky.social CADRE: Rethinking Video Autoencoders for Interactive World Models We investigate what makes a good world model codec 📜 arxiv.org/abs/26…”
Ellis Alicante agentic AI postdoc
2 directory members surfaced this signal.
2 experts
2 communities
1 sources clustered
“🏹 Job alert: Postdoc Position on Agentic AI at ELLIS Alicante 📍 Alicante 🇪🇸 ⏰ 30 November 🔗 https://ellisalicante.org/job/postdoc/”
Established
AI field signal
Signal
3d ago
⚡ 9 h early
2 directory members surfaced this signal.
2 experts
2 communities
1 sources clustered
“🚨 New preprint: "Dino Forcing Flow Models: Do not denoise what you can predict" @arrijitghosh.bsky.social @lucasdegeorge.bsky.social P. Couairon, A.A. Efros, @vickykalogeiton.bsky.social and me 📜 arxiv.org/abs/2610.11751 🖥️ arijit-hub.github.io/projects/din…”
subquadratic 3SUM subcubic APSP sparse graphs paper
3 experts across 2 network communities independently surfaced this.
3 experts
2 communities
1 sources clustered
“Correct link: arxiv.org/abs/2610.067...”
predict-project-renoise diffusion hard constraints paper
2 directory members surfaced this signal.
2 experts
1 community
1 sources clustered
“Today my PhD student (for one last day) @orochman.bsky.social is defending his thesis on neural emulators. Check out his latest paper on sampling diffusion models under hard constraints arxiv.org/abs/2601.21033 (NeurIPS 2026)”
recurrent looped transformer architecture paper
2 directory members surfaced this signal.
2 experts
2 communities
1 sources clustered
“Recurrent Looped Transformer Zhang et al. Combine context/history transformer with recurrence: have a causal encoder with a recurrent decoder. arxiv.org/abs/2610.07591”
2 directory members surfaced this signal.
2 experts
2 communities
1 sources clustered
“Procedural Core: A Compact Recurrent Initialization for Vision Transformers By @damienteney.bsky.social 's group Idea: train a ViT with parameters tied over layers (="recurrent ViT") on abstract procedurally data. Then initialise models of ANY arch (!) with…”
MICCAI PhD positions structure-aware ML announced
2 directory members surfaced this signal.
2 experts
2 communities
2 sources clustered
“🏹 Job alert: 2 PhD Researchers in Machine Learning & Medical Image Analysis at Scads AI, Leipzig University 📍 Leipzig 🇩🇪 ⏰ 31 December 🔗 https://bit.ly/4z2MSyk”
PhD social RL agroecological transition posting
2 directory members surfaced this signal.
2 experts
2 communities
1 sources clustered
“🏹 Job alert: Fully-funded PhD on Social Reinforcement Learning to Support the Agroecological Transition 📍 Toulouse 🇫🇷 ⏰ 23 November 🔗 https://ellis.eu/research/jobs/2026-11-23-fully-funded-phd-on-social-reinforcement-learning-to-support-the”
RNN homunculus long-term memory gating paper
2 directory members surfaced this signal.
2 experts
1 community
1 sources clustered
“I really enjoy finding gaps in our understanding of text-book deep learning. The RNN Homunculus: Long-range input vanishes RNN gradients. Gates (GRU, LSTM) help, but gates are themselves an RNN. Ie: gates are not sufficient. We need short-range data to lear…”
Established
AI field signal
Signal
14d ago
⚡ 3188 h early
2 directory members surfaced this signal.
2 experts
1 community
1 sources clustered
“These results surprised me. There's more to do to fully understand which structures align! Here are some great readings on other perspectives: * local relational: arxiv.org/abs/2602.14486 * coarse-grained: arxiv.org/abs/2604.18572 * global relational: arxiv…”
ELLIS PhD 2026 applications open
2 directory members surfaced this signal.
2 experts
2 communities
1 sources clustered
“🎓 Work with TWO leading European researchers across borders while you achieve your research and career goals in the #ELLISPhD Program! Check out the value Dominika Długosz sees in joint supervision. Apply now to start your PhD in 2027 at https://bit.ly/3TrH…”
hyperparameter tuning on test set paper
3 experts are actively discussing the implications.
2 experts
1 community
1 sources clustered
“In addition to the research findings, this is the type of research I really enjoyed doing 😊 "On Hyperparameter Tuning on the Test Set" arxiv.org/abs/2610.05902”
3 experts discussed this · 6 posts
jvgemert.bsky.social: In addition to the research findings, this is the type of research I really enjoyed doing 😊 "On Hyperparameter Tuning on the Test Set" arxiv.org/abs/2610.05902
David Picard: In addition to the research findings, this is the type of research I really enjoyed doing 😊 "On Hyperparameter Tuning on the Test Set" arxiv.org/abs/2610.05902
David Picard: Joining the heresy, I see... But in all seriousness, I think the observation you make that test-tuning is just a uniform boost (fig 3) is an important lesson of deep learning (interpolation thresho…
Open the full discussion →
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
2 directory members surfaced this signal.
2 experts
1 community
1 sources clustered
“While studying the convergence of linear neural networks, I stumbled upon a nice conservation law that depends only on the distribution of neurons: a “mean-field” conservation law. www.gpeyre.com/blog/2026/10...”
weight averaging code RL frontiers paper
1 directory member surfaced this signal.
1 expert
1 community
1 sources clustered
“Funnily enough, I had this discussion with Benjamin Negrevergne earlier this week (during his habilitation, amazing talk btw) on one of his recent paper with people from Meta: arxiv.org/abs/2605.28751 In this, they show a trade-off between precision and rec…”
