he definitely enjoys the process

I like huggingface.co/papers/2601....

it's not alice workshop it's alyssa workshop

We're about to start 🧑‍🔬

Awww yeah... I'm feeling rather **EXPLOSIVE** this morning... It's time to blow some stuff up!! Tick... tick... tick..... BOOM! 🐦🧵🧨💥 www.youtube.com/shorts/LSlvZ...

these days, it's harder to find a person that wouldn't lecture me on machine learning, artificial intelligence, and impact of then, rather than not we are all specialists

A factor of 10 billion since 2010 😮 A couple of eye-opening slides form @sloeschcke.bsky.social's presentation at today’s @belongielab.org meeting (1/2)

like so many places require letters of motivation if you even want to see what other people are doing and want to express interest.. Do I have to be motivated ?..

atp, it became undeniable how much imact african american and carribean dialects have had on english language, all of these "lowkey", "gyatt"... same situation with french, simplification thereof. afaik some institutions push for the control on public face of languages, but globalisation galore!

blog.google/innovation-a... #AI #artificialintelligence

idk who are Liv Boeree, Nick Schulman, Doug Polk, and Hikaru Nakamura but they'll be casting the event for you, if you're in show biz

CONGRATULATIONS @sharky6000.bsky.social !

:(

I am really sorry that I don't use Claude or another chatbot to answer your questions and take a month to research a thing

wanted to go there so hard, but not this time, not this time the programme is fire.

State Combinatorial Generalization In Decision Making With Conditional Diffusion Models Xintong Duan, Yutong He, Fahim Tajwar, Wentse Chen, Ruslan Salakhutdinov, Jeff Schneider Action editor: Marc Lanctot https://openreview.net/forum?id=XB1dd01Ozz #reinforcement #maze #driving

I forgot that there's a link in this post github.com/google-deepm... The link is the coolest part, actually

prism.openai.com >> how much might iclr acceptance rate jump up and how much may OAI benefit from collecting nice specialised data

L\'eonard Brice, Thomas A. Henzinger, K. S. Thejaswini Dicey Games: Shared Sources of Randomness in Distributed Systems https://arxiv.org/abs/2601.18303

LOOK !!! It's VILIAM LISY!

fire thesis btw @anastasiabzv.bsky.social naomi.princeton.edu/wp-content/u...

cool shi github.com/j-klawson/al...

read this book before marriage

with all those deadlines and working alone, I lowkey feel stressed af

so many papers

A fascinating (for me) paper about BNE in multi-agent systems: arxiv.org/abs/2506.08292

we will never get tired of: 1) fixing hallucinations in LLMs 2) fixing OOD drift in offline RL

link.springer.com/collections/... A cool ToM issue to submit to

ah agent modelling is a case of in-context learning...

bro are we deadass....

#AAAI26 on "Local Guidance for Configuration-Based Multi-Agent Pathfinding" (LG-LaCAM)! 🤖🛰️ Tomoki Arita and Keisuke Okumura are pushing the boundaries of MAPF by integrating local guidance into state-of-the-art LaCAM. @aaai.org

a very nice piece of information about debugging on a tpu cluster: cambrian-mllm.github.io/blog/tpu-tra... if one day I gain an access to this sort of hardware, might have employed the knowledge for a good cause

Just attended a fascinating talk on "Bandit Learning in Housing Markets" at #AAAI2026 🏠📊 @aaai.org Combining matching theory with multi-armed bandits to learn core allocations—both centralized and decentralized settings with provable regret bounds.

67

You can't just a person.

me bitch

Feedback, Learning, and Adaptation: A (tentative) syllabus.

It's really come to a point when I have to decide, if I want to do anything different. Because it's generally fun to code some cool things as a hobby, however, I don't see how I can make a meal out of that. The problem is, I can't see myself doing other things, and it's what I should do.

I think that opening ChatGPT to public happened too early and it tricked people too much. Moreover, these models should have never been accessible to general public.

I have been watching this video with face buried in my hands www.youtube.com/watch?v=jMSC...

some AISTATS workshops look virtual.aistats.org/virtual/2026...

Kaggle Arena does chose a stupideous approach to contributions: you can host a game only as an organisation. Seriously, it's just a pull request and documentation, even if you review them manually. Look at other hubs like Prime Intellect, textarena, or Nemo-Gym. How good you idea would have been!

C A N A D A 🇨🇦 🇨🇦 🇨🇦 🇨🇦 🇨🇦

Reading group TOMORROW 3-4pm UK! Joe Marino (Google DeepMind) will present SIMA 2, a generalist embodied agent designed to operate across a wide range of 3D virtual worlds 🌎 Join here: edinburgh-rl.github.io/reading-group

A cool paper by @cjdamato.bsky.social and his people "LLM Collaboration with Multi-Agent Reinforcement Learning" arxiv.org/abs/2508.04652 MAGRPO...

if somebody from gdm sees this post and knows edward, may you, please, suggest from friendly outside activites to him, not involving internet connection appreciate it

i still remeber how my english teacher made me stop constantly swearing in english

drunk image generation with nanobanana