Adib (@adibvafa) 's Twitter Profile
Adib

@adibvafa

20. ML at @Cohere @VectorInst @Inserm @BorealisAI @UHN. Google Lead @googledevs. CS/Neuro @UofT. Founder of Canada's Largest AI Hackathon @GenAIGenesis 🍁

ID: 1756697799939215361

linkhttps://adibvafa.github.io calendar_today11-02-2024 15:13:00

2,2K Tweet

849 Followers

1,1K Following

Keyon Vafa (@keyonv) 's Twitter Profile Photo

Can an AI model predict perfectly and still have a terrible world model? What would that even mean? Our new ICML paper formalizes these questions One result tells the story: A transformer trained on 10M solar systems nails planetary orbits. But it botches gravitational laws 🧵

Albert Gu (@_albertgu) 's Twitter Profile Photo

impressive results on super long-form speech generation (> 10 minutes)! glad to see that the intuitions here closely track what I wrote about in my blog post about SSMs vs Transformers x.com/_albertgu/stat… 1. SSMs make more sense for long context where coherence matters more

Nikita Mounier (@nikitamounier) 's Twitter Profile Photo

How can we make truly self-correcting systems? 🧨Introducing R3, a powerful inference-time (!) self-correcting text diffusion framework. It's deceptively simple yet expressive. We: - Review text blocks with a PRM - Remask them as a function of their quality - Refine the output

How can we make truly self-correcting systems?

🧨Introducing R3, a powerful inference-time (!) self-correcting text diffusion framework. It's deceptively simple yet expressive. We:
- Review text blocks with a PRM
- Remask them as a function of their quality
- Refine the output
Julian Salazar (@julianslzr) 's Twitter Profile Photo

If you know the pain of sequence training<->inference, visit the #ICML25 Google booth 3-3:30 today (Tue.)! SequenceLayers is not just a layer library, but a new approach to defining and composing sequence architectures. Try it in Colab: colab.research.google.com/github/google/… See our report:

Jason Wei (@_jasonwei) 's Twitter Profile Photo

Becoming an RL diehard in the past year and thinking about RL for most of my waking hours inadvertently taught me an important lesson about how to live my own life. One of the big concepts in RL is that you always want to be “on-policy”: instead of mimicking other people’s

Isomorphic Labs (@isomorphiclabs) 's Twitter Profile Photo

We are at ICML in Vancouver this week! Come and meet us to chat about the work of the ML team, and find out more about opportunities at Isomorphic Labs: bit.ly/44ug6t4 Catch Benedek Rozemberczki @ICML2025 and Jack Lynch's talk later today, Wednesday, July 16 at 11:30 AM PDT at the

We are at ICML in Vancouver this week!
Come and meet us to chat about the work of the ML team, and find out more about opportunities at Isomorphic Labs: bit.ly/44ug6t4
Catch <a href="/benrozemberczki/">Benedek Rozemberczki @ICML2025</a> and <a href="/_lychrel/">Jack Lynch</a>'s talk later today, Wednesday, July 16 at 11:30 AM PDT at the
Julian Salazar (@julianslzr) 's Twitter Profile Photo

This is today at #ICML25. Come say hi! - Talk: 3:45pm-4pm in West Ballroom C (icml.cc/virtual/2025/o…) - Poster: 4:30pm-7pm in West Exhibit Hall B, #W-417 (icml.cc/virtual/2025/p…)

Sara Hooker (@sarahookr) 's Twitter Profile Photo

Every few years I think you should jump into a new deep-end by doing something that pushes you out of your comfort zone. However, people rarely do because it is easier to stick with what is known. I think this is true in research, life partners and big life decisions.