Johan Obando 👍🏽
@johanobandoc
Graduate student @Mila_Quebec @UMontrealDIRO | RL/Deep Learning/AI | De Cali/Colombia pal’ Mundo 🇨🇴 | #JuntosProsperamos⚡#TogetherWeThrive| 🌱🌎
I’m very happy to share our paper, Revisiting Rainbow, accepted in the Deep RL workshop @Neurips_Conf. I’ve been working with @pcastr for a few months, and I wanted to share my story, and how this work came to be, in the hope it motivates others in similar situations to mine.
Happy to share "Revisiting Rainbow" w/ @JS_Obando where we argue small/mid-scale envs can promote more insightful & inclusive deep RL research. 📜Paper: arxiv.org/abs/2011.14826 ✍️🏾Blog: bit.ly/2VkPJ4r 🐍Code: bit.ly/3mrCyuD 📽️Video: bit.ly/2I0BAXk 🧵1/X
Thank you all for stopping by our poster session at ICML! Due to visa issues, @tanghyyy couldn’t join us in person; however, he and the rest of the team are eager to hear more from you. Feel free to reach out via email if you have any questions! 🥳 #ICML2025
Come by West Exhibition Hall B2-B3 #W-702 at 11am to talk to @johanobandoc and me about churn and plasticity loss in RL!
⏰Happening in 20 minutes (4:30pm PDT) in West Exhibition Hall B2-B3, poster W-319, come chat with us!
I arrived in Vancouver 🇨🇦 yesterday for @icmlconf If you're interested in chatting about AI/RL for Bio, I would love to meet up! 📍I'll be presenting our ADIOS 👇 poster with @SebastianTower6 on Tue 15 Jul 4:30pm - 7pm PDT. Come chat to us about shaping viruses 🧬
We’re hitting the preparation home stretch for our #RLC2025 workshop. We’ll have an exciting panel with our invited speakers. If you have a hot take or question that you’d love them to adress, let us know!!
Finding the Frame workshop is coming up on Aug. 5 at #RLC2025!🚀 We’re excited to discuss the conceptual foundations of RL with our panelists: Erin Talvitie, George Konidaris, Mark Ho and Clare Lyle. Send in your questions! 📬
🚨New workshop alert 🚨 Calling all RL researchers in the New York area 🧠🗽 Present your work at the first-ever New York Reinforcement Learning Workshop (NYRL), co-organized by Amazon, Columbia Business School & NYU Tandon School of Engineering. ny-rl.com
I’m building a new team at @GoogleDeepMind to work on Open-Ended Discovery! We’re looking for strong Research Scientists and Research Engineers to help us push the frontier of autonomously discovering novel artifacts such as new knowledge, capabilities, or algorithms, in an…
We're releasing a cool paper! DLCs are image tokens that enable better diffusion modelling. For now, we show this is the right representation. But in the future, this can allow LLMs to "speak in images"🤯to enable visual reasoning and more powerful text-image generalization. ⬇️
🧵 Everyone is chasing new diffusion models—but what about the representations they model from? We introduce Discrete Latent Codes (DLCs): - Discrete representation for diffusion models - Uncond. gen. SOTA FID (1.59 on ImageNet) - Compositional generation - Integrates with LLM 🧱
🧵 Everyone is chasing new diffusion models—but what about the representations they model from? We introduce Discrete Latent Codes (DLCs): - Discrete representation for diffusion models - Uncond. gen. SOTA FID (1.59 on ImageNet) - Compositional generation - Integrates with LLM 🧱
Want to be part of the Veo team? Here's a great opportunity to work with us!
Want to be part of a team redefining SOTA for generative video models? Excited about building models that can reach billions of users? The Veo team is hiring! We are looking for amazing researchers and engineers, in North America and Europe. Details below:
Sometimes it is important to take a moment and celebrate -- we achieved all of this in 3 years. Pretty incredible impact from @Cohere_Labs 🔥
Reminder that this is happening tomorrow! Really excited for this! Both Steph and Scott have truly modelled our values in the open science community: from pushing for unconventional ideas to bridging disciplines to building communities! 🎉 Registration link in this thread!
🚨 Coming up! Research connections event on Tuesday, July 22! Are you interested in building AI agents with interpretable reinforcement learning? 🕵How about AI governance and how LLMs understand the political language of international diplomacy? 🏛️
Do you have a PhD (or equivalent) or will have one in the coming months (i.e. 2-3 months away from graduating)? Do you want to help build open-ended agents that help humans do humans things better, rather than replace them? We're hiring 1-2 Research Scientists! Check the 🧵👇
Gemini with advanced deep think achieved gold medal-level performance at IMO 2025!🥇 Very happy to have been a small part of this collaboration on the inference side, and congrats to everyone involved!
An advanced version of Gemini with Deep Think has officially achieved gold medal-level performance at the International Mathematical Olympiad. 🥇 It solved 5️⃣ out of 6️⃣ exceptionally difficult problems, involving algebra, combinatorics, geometry and number theory. Here’s how 🧵
👉 We are hiring!! How will AI agents interact with you, learn from you and empower you in the future? Reward signals will not always be clearly defined… Breakthroughs are needed in multi turn RL, self-evaluation and self-improvement - if you are excited by this, join us! 👇
Do you have a PhD (or equivalent) or will have one in the coming months (i.e. 2-3 months away from graduating)? Do you want to help build open-ended agents that help humans do humans things better, rather than replace them? We're hiring 1-2 Research Scientists! Check the 🧵👇
Jiashun couldn’t join us in person due to visa issues. He and the whole team would love to connect; feel free to reach out via email if you’d like to chat more. Thanks to everyone who stopped by our poster at #ICML2025, we really enjoyed speaking with you! 🎉🥳
🚨 Excited to share our #ICML2025 paper: "The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep RL" We train RL agents to know when to quit, cutting wasted effort and improving efficiency with our method LEAST. 📄Paper: arxiv.org/pdf/2506.13672 🧵Check the thread below👇🏾
As the field moves towards agents doing science, the ability to understand novel environments through interaction becomes critical. AutumnBench is an attempt at measuring this abstract capability in both humans and current LLMs. Check out the blog post for more insights!
We’re proud to announce the launch of AutumnBench, an open-source benchmark developed on our Autumn platform. This benchmark, led by our MARA team, provides a novel platform for evaluating world modeling and causal reasoning in both human and artificial intelligence.
Since there’s no full on RL workshop at #ICML2025, why not release new work to get us all excited?! 👏@c_voelcker + Axel + @marcel_hussing and others!
🔥🚨 Preprint alert: Relative Entropy Pathwise Policy Optimization #REPPO 🚨🔥 What if you could have on-policy training without the instability and parameter tuning that plagues #PPO? What if training with deterministic policy gradient just worked? With our new method it does!
Don't forget to tune in tomorrow, July 18th as @Theo_Vincent_ presents "Optimizing the Learning Trajectory of Reinforcement Learning Agents." Learn more: cohere.com/events/Cohere-…
Join our Reinforcement Learning Group next week on Friday, July 18th as they welcome @Theo_Vincent_ for a session on "Optimizing the Learning Trajectory of Reinforcement Learning Agents." Thanks to @rahul_narava and @gustiwinata_ for organizing this event ✨
Come to my ICML poster: West Exhibition Hall B2-B3 #W-809 / Thu 17 Jul 4:30 p.m. PDT — 7 p.m. PDT
Had a great time presenting our work and connecting with so many brilliant researchers! happy to chat more, feel free to reach out with any questions! 🥳 #ICML2025
Happening now!
Happening now!
Come by West Exhibition Hall B2-B3 W-711 at 11am to talk to @WalterMayor_T @johanobandoc and me about the impact of parallelized data collection for training RL agents! #ICML2025