@annoyingreposter.bsky.social
Pinned
I might look smart, however, I am absolutely not.
David Silver didn't really announce his company and it's already being valued at some billions...
February 19, 2026 at 8:28 PM
David Silver didn't really announce his company and it's already being valued at some billions...
really awesome stuff and in-context best response arxiv.org/abs/2602.16301
Multi-agent cooperation through in-context co-player inference
Achieving cooperation among self-interested agents remains a fundamental challenge in multi-agent reinforcement learning. Recent work showed that mutual cooperation can be induced between "learning-aw...
arxiv.org
February 19, 2026 at 7:44 PM
really awesome stuff and in-context best response arxiv.org/abs/2602.16301
@sharky6000.bsky.social underrated tip to find some great articles/papers, aside from scholar inbox: subscribe to related articles to Ian Gemp on scholar
so much interesting stuff once in a couple of days
so much interesting stuff once in a couple of days
February 19, 2026 at 7:40 PM
@sharky6000.bsky.social underrated tip to find some great articles/papers, aside from scholar inbox: subscribe to related articles to Ian Gemp on scholar
so much interesting stuff once in a couple of days
so much interesting stuff once in a couple of days
Reposted
1/📢 Announcing our next ERA Journal Club session
📍Feb 28, 4:00 PM GMT on Discord: discord.gg/m3qvuXgkZ7
Topic: Evochora, an open-source lab for embodied digital evolution. 🧬🧱
Project: github.com/evochora/evo...
Demo: evochora.org
#ALife #Evolution #Evochora
📍Feb 28, 4:00 PM GMT on Discord: discord.gg/m3qvuXgkZ7
Topic: Evochora, an open-source lab for embodied digital evolution. 🧬🧱
Project: github.com/evochora/evo...
Demo: evochora.org
#ALife #Evolution #Evochora
February 18, 2026 at 1:47 PM
1/📢 Announcing our next ERA Journal Club session
📍Feb 28, 4:00 PM GMT on Discord: discord.gg/m3qvuXgkZ7
Topic: Evochora, an open-source lab for embodied digital evolution. 🧬🧱
Project: github.com/evochora/evo...
Demo: evochora.org
#ALife #Evolution #Evochora
📍Feb 28, 4:00 PM GMT on Discord: discord.gg/m3qvuXgkZ7
Topic: Evochora, an open-source lab for embodied digital evolution. 🧬🧱
Project: github.com/evochora/evo...
Demo: evochora.org
#ALife #Evolution #Evochora
reposting now with the gif
Call for papers! The 17th PCG Workshop will be held in Copenhagen in August 2026.
Submission deadline March 30th. Accepted papers will have the opportunity to be included in the FDG proceedings.
See all the practical information and the paper database on www.pcgworkshop.com
(repost now with gif)
Submission deadline March 30th. Accepted papers will have the opportunity to be included in the FDG proceedings.
See all the practical information and the paper database on www.pcgworkshop.com
(repost now with gif)
February 18, 2026 at 7:46 PM
reposting now with the gif
Reposted
What is the relationship between memorization and generalization in AI? Is there a fundamental tradeoff? In infinitefaculty.substack.com/p/memorizati... I’ve reviewed some of the evolving perspectives on memorization & generalization in machine learning, from classic perspectives through LLMs.
Memorization vs. generalization in deep learning: implicit biases, benign overfitting, and more
Or: how I learned to stop worrying and love the memorization
infinitefaculty.substack.com
February 18, 2026 at 3:54 PM
What is the relationship between memorization and generalization in AI? Is there a fundamental tradeoff? In infinitefaculty.substack.com/p/memorizati... I’ve reviewed some of the evolving perspectives on memorization & generalization in machine learning, from classic perspectives through LLMs.
Reposted
The tutorials for #AAMAS2026 are now available.
🔹 Explore the full list of topics
🔹 Plan your participation in advance
🔹 Stay informed about key developments in the field
Full details are available here
🔗 cyprusconferences.org/aamas2026/tu...
🔹 Explore the full list of topics
🔹 Plan your participation in advance
🔹 Stay informed about key developments in the field
Full details are available here
🔗 cyprusconferences.org/aamas2026/tu...
Tutorials | AAMAS
cyprusconferences.org
February 18, 2026 at 1:39 PM
The tutorials for #AAMAS2026 are now available.
🔹 Explore the full list of topics
🔹 Plan your participation in advance
🔹 Stay informed about key developments in the field
Full details are available here
🔗 cyprusconferences.org/aamas2026/tu...
🔹 Explore the full list of topics
🔹 Plan your participation in advance
🔹 Stay informed about key developments in the field
Full details are available here
🔗 cyprusconferences.org/aamas2026/tu...
Reposted
This year I'm teaching a new course on generative models for visual content (images, video, 3D, etc). It's mostly me rambling about recent papers, design choices I like/hate. The slides of the first lectures are here: davidpicard.github.io/teaching/
Use right arrow to navigate past the blank page.
Use right arrow to navigate past the blank page.
February 17, 2026 at 11:14 AM
This year I'm teaching a new course on generative models for visual content (images, video, 3D, etc). It's mostly me rambling about recent papers, design choices I like/hate. The slides of the first lectures are here: davidpicard.github.io/teaching/
Use right arrow to navigate past the blank page.
Use right arrow to navigate past the blank page.
Nice nice nice nice workshop, more of these !
Call for papers! The 17th PCG Workshop will be held in Copenhagen in August 2026.
Submission deadline March 30th. Accepted papers will have the opportunity to be included in the FDG proceedings.
See all the practical information and the paper database on www.pcgworkshop.com
Submission deadline March 30th. Accepted papers will have the opportunity to be included in the FDG proceedings.
See all the practical information and the paper database on www.pcgworkshop.com
PCG Workshop | News
www.pcgworkshop.com
February 17, 2026 at 3:04 PM
Nice nice nice nice workshop, more of these !
Reposted
Publication announcement! I can now retire in peace: together with my friend Bo Kampmann Walther, I have written a book about football (aka soccer, fodbold, or fútbol).
The book is out i April 15 from Routledge/CRC Press: www.routledge.com/The-Laws-of-...
(1/5)
The book is out i April 15 from Routledge/CRC Press: www.routledge.com/The-Laws-of-...
(1/5)
The Laws of the Game: A Game Studies Book about Soccer
This book applies theories, methods, and concepts from game studies to soccer. This is a game studies book about soccer that studies the rules and design of soccer and the impact that technology has o...
www.routledge.com
February 17, 2026 at 8:55 AM
Publication announcement! I can now retire in peace: together with my friend Bo Kampmann Walther, I have written a book about football (aka soccer, fodbold, or fútbol).
The book is out i April 15 from Routledge/CRC Press: www.routledge.com/The-Laws-of-...
(1/5)
The book is out i April 15 from Routledge/CRC Press: www.routledge.com/The-Laws-of-...
(1/5)
found on twitter a bit of cartesian philosophy of 2026
February 16, 2026 at 7:26 PM
found on twitter a bit of cartesian philosophy of 2026
yeah looking at recent GDM interns' project, it wasn't really worth to apply
February 16, 2026 at 4:22 PM
yeah looking at recent GDM interns' project, it wasn't really worth to apply
Reposted
🚨 🔬 PhD positions at Google DeepMind in France 🇫🇷
We are advertising Master Level Intern positions at Google DeepMind within our Frontier AI Unit.
These could lead to co-advised PhD positions with Google DeepMind and French academic institutions.
job-boards.greenhouse.io/deepmind/job...
We are advertising Master Level Intern positions at Google DeepMind within our Frontier AI Unit.
These could lead to co-advised PhD positions with Google DeepMind and French academic institutions.
job-boards.greenhouse.io/deepmind/job...
Stagiaire de niveau Master, France / Master Level Intern, France
Grenoble, France ; Paris, France
job-boards.greenhouse.io
February 16, 2026 at 12:41 PM
🚨 🔬 PhD positions at Google DeepMind in France 🇫🇷
We are advertising Master Level Intern positions at Google DeepMind within our Frontier AI Unit.
These could lead to co-advised PhD positions with Google DeepMind and French academic institutions.
job-boards.greenhouse.io/deepmind/job...
We are advertising Master Level Intern positions at Google DeepMind within our Frontier AI Unit.
These could lead to co-advised PhD positions with Google DeepMind and French academic institutions.
job-boards.greenhouse.io/deepmind/job...
To add:
1. bsky.app/profile/igil...
2. I guess there should be a version of PQN algorithm for continuous actions, but I can't find the paper.
TQC is cool, though.
1. bsky.app/profile/igil...
2. I guess there should be a version of PQN algorithm for continuous actions, but I can't find the paper.
TQC is cool, though.
The talk i gave about "Recent Advances in RL for Continuous Control" at CERN last year is now online =)
www.youtube.com/watch?v=Sb0d...
www.youtube.com/watch?v=Sb0d...
Recent Advances in RL for Continuous Control (SOTA 2025) | CERN ML Workshop
YouTube video by Antonin Raffin
www.youtube.com
February 15, 2026 at 2:42 PM
To add:
1. bsky.app/profile/igil...
2. I guess there should be a version of PQN algorithm for continuous actions, but I can't find the paper.
TQC is cool, though.
1. bsky.app/profile/igil...
2. I guess there should be a version of PQN algorithm for continuous actions, but I can't find the paper.
TQC is cool, though.
goated opinion of @sethkarten.ai for a reason
games are sort of meta-level of reasoning, and seeing how well meta-learning works in the recent GenAI advancements, it IS the next step, naturally
games are sort of meta-level of reasoning, and seeing how well meta-learning works in the recent GenAI advancements, it IS the next step, naturally
February 15, 2026 at 9:04 AM
goated opinion of @sethkarten.ai for a reason
games are sort of meta-level of reasoning, and seeing how well meta-learning works in the recent GenAI advancements, it IS the next step, naturally
games are sort of meta-level of reasoning, and seeing how well meta-learning works in the recent GenAI advancements, it IS the next step, naturally
can't wait for icml review drama after iclr review drama after neurips review drama after icml review drama
February 14, 2026 at 5:46 PM
can't wait for icml review drama after iclr review drama after neurips review drama after icml review drama
Reposted
Policy-Guided Search on Tree-of-Thoughts for Efficient Problem Solving with Bounded Language Mode...
Sumedh Pendurkar, Guni Sharon
Action editor: Branislav Kveton
https://openreview.net/forum?id=Rlk1bWe2ii
#heuristic #search #tasks
Sumedh Pendurkar, Guni Sharon
Action editor: Branislav Kveton
https://openreview.net/forum?id=Rlk1bWe2ii
#heuristic #search #tasks
February 14, 2026 at 1:20 PM
Policy-Guided Search on Tree-of-Thoughts for Efficient Problem Solving with Bounded Language Mode...
Sumedh Pendurkar, Guni Sharon
Action editor: Branislav Kveton
https://openreview.net/forum?id=Rlk1bWe2ii
#heuristic #search #tasks
Sumedh Pendurkar, Guni Sharon
Action editor: Branislav Kveton
https://openreview.net/forum?id=Rlk1bWe2ii
#heuristic #search #tasks
why do you humanise AI?
February 14, 2026 at 1:19 PM
why do you humanise AI?
please somebody do a multi-agent workshop I beg you on my knees
Workshops, held on the first day, are a primary feature of
@rl-conference.bsky.social and have set a delightfully inquisitive tone. Discussions started at both workshops I've been a part of in the past persisted through the week, with some still ongoing!
CfW here: rl-conference.cc/call_for_wor...
@rl-conference.bsky.social and have set a delightfully inquisitive tone. Discussions started at both workshops I've been a part of in the past persisted through the week, with some still ongoing!
CfW here: rl-conference.cc/call_for_wor...
RLJ | RLC Call for Workshops
rl-conference.cc
February 13, 2026 at 10:15 PM
please somebody do a multi-agent workshop I beg you on my knees
science is a tough job
February 13, 2026 at 9:55 PM
science is a tough job
brewing and roting
February 13, 2026 at 7:28 PM
brewing and roting
and this one, highlighting previous works of Kate Larson (fairness) and Ian Gemp (convex markov games)
arxiv.org/abs/2602.08389
arxiv.org/abs/2602.08389
February 13, 2026 at 7:28 PM
and this one, highlighting previous works of Kate Larson (fairness) and Ian Gemp (convex markov games)
arxiv.org/abs/2602.08389
arxiv.org/abs/2602.08389
A cheeky paper about value of latent collaboration: arxiv.org/abs/2511.20639
February 13, 2026 at 7:26 PM
A cheeky paper about value of latent collaboration: arxiv.org/abs/2511.20639
another paper that looks interesting arxiv.org/abs/2602.11865
Intelligent AI Delegation
AI agents are able to tackle increasingly complex tasks. To achieve more ambitious goals, AI agents need to be able to meaningfully decompose problems into manageable sub-components, and safely delega...
arxiv.org
February 13, 2026 at 7:19 PM
another paper that looks interesting arxiv.org/abs/2602.11865