Juan Ramirez
@juan43ramirez
Followers
240
Following
806
Media
19
Statuses
208
PhD Candidate @Mila_Quebec Constrained Deep Learning & Feasible Learning
Montréal
Joined February 2021
Seeking 2026 research/applied science internships. I am a PhD candidate in AI at @Mila_Quebec specializing in constrained learning and trustworthy AI. Website: https://t.co/YuSjYA1ZyX CV: https://t.co/d50fBHSKpC
#AI #ML #PhD #Internship #Optimization #TrustworthyAI
0
3
24
I am giving a talk on constraint-aware generative models at the hashtag#NeurIPS COML workshop today. I'll discuss our recent advances on grounding diffusion models and discrete LLMs into physical principles and constraints for scientific and engineering applications. 🚀 Very
2
7
54
As @NeurIPSConf comes to a close, Mila PhD student Juan Ramirez (@juan43ramirez) co-organized the workshop "Constrained Optimization for Machine Learning". Ballroom 6DE
0
1
6
We hope to see you tomorrow, December 7th, at the workshop! We will be at the Upper Level Ballroom 6D–6E of the San Diego Convention Center. Starting at 8:30 AM! What better way to close NeurIPS!
🚨 New Workshop Alert! 🚨 COML @NeurIPSConf 2025 — The first Workshop on Constrained Optimization for Machine Learning is coming to San Diego, Dec 2–7! 🌴 Website: https://t.co/R17UY1wnfY 🧵
0
2
2
Découvrez l'atelier "Les modèles fondamentaux pour le cerveau et le corps" co-organisé par un étudiant de Mila Nanda Harishankar Krishna (@nandahkrishna) à @NeurIPSConf dans la salle 24ABC.
0
2
9
Juan Ramirez (@juan43ramirezsible) PhD student at UdeM/Mila, will be at Mila’s booth at 11am to talk about his work on feasible learning. Come visit and chat with him! #625
0
4
14
Juan Ramirez (@juan43ramirez), doctorant à l’UdeM/Mila, sera au kiosque de Mila à 11 h pour parler de ses travaux sur le feasible learning. Venez le rencontrer et discuter avec lui ! #625
0
2
2
I will be attending #NeurIPS2025 in San Diego next week, from Thursday to Sunday. If you would like to chat about foundation models for science or AI safety, feel free to reach out. I will also be recruiting PhD students for Fall 2026. If you are interested and will be at
arxiv.org
Stable diffusion models represent the state-of-the-art in data synthesis across diverse domains and hold transformative potential for applications in science and engineering, e.g., by facilitating...
1
13
96
I’ll be at @NeurIPSConf 2025 next week! I’m keen to discuss constrained & feasible learning. 📍 You can find me at: • @_LXAI Workshop • @constrained_ml Workshop Feel free to reach out!
0
1
5
Nov. 25 (12-1pm), I will discuss rule extrapolation in language models @VectorInst. Come by if you're interested in OOD generalization, causality, identifiability, and more. I perhaps also share unsolicited lessons I learned during my PhD.
0
3
10
Excited about this speaker lineup!
🚀 Excited to announce our keynote speakers for the Constrained Optimization for Machine Learning (COML) Workshop at #NeurIPS2025! 📅 Dec 7, 2025 | 📍 San Diego Convention Center (Upper Level Ballroom 6D–6E) 🧵👇
0
0
1
I am deeply honored to be selected as an @RBCBorealis AI Fellow for 2024–2025!
1
1
13
ERM: Sacrifices the "one" for the "many" to get a good average loss. Feasible Learning: Finds models that are good enough **for every single sample.** Want to see the difference? Come to my talk!
Join us on Wednesday, November 19, at 1:00 PM EDT for a talk by @juan43ramirez (UdeM/Mila) on "Feasible Learning" at @Mila_Quebec
1
1
3
🚨I have received the "Best Thesis Award 2025" from the Université de Montréal in the "Natural Sciences and Engineering" category! 🚨 Thesis: https://t.co/kdraSXNoB6 Thesis defense: https://t.co/tff79g0lT8 Explainer for a wide audience (in French): https://t.co/RlmVJtPZDH
My thesis is now online! https://t.co/kdraSXMQLy This is more than just a list of publications. I invested a lot of time and passion writing this thesis in hope that it will make for an interesting read. Here's a summary of what you'll find in it.
5
4
23
This is a really elegant observation: https://t.co/dlcIWp6zMq -- in hindsight it makes so much sense!
arxiv.org
Constrained optimization is a powerful framework for enforcing requirements on neural networks. These constrained deep learning problems are typically solved using first-order methods on their...
1
2
7
The whole experience with the @NeurIPSConf position paper track has just been one big 😂 Missed every deadline, only to now announce (a week after the original notification deadline) that they'll only accept ~6% of submissions. Should have just submitted to main track...
5
5
125
want to help shape the future of AI in latin america? then don't miss out on @la_sala_ai next march! the past instances of this event have been truly fantastic, and i'm super pumped for the next one next year. don't miss out and apply today! hope to see you in quito!! ♥️🇪🇨
📢MARK YOUR CALENDARS!🗓️ The Summit of AI in Latin America (SALA, formerly @riiaa_org ) is happening in Quito, Ecuador, March 9-12, 2026, at USFQ! Want to attend and apply for travel grants? Do so here before October 1st: https://t.co/0d8jaJvJks More details in thread 👇🏾🧵
0
5
13
🎉 Good news! 🎉 The LXAI Workshop @ #NeurIPS2025 submission deadline has been extended 📝 📅 New deadline: Sept 8 (11:59 pm AoE) Don’t miss your chance to submit full papers & extended abstracts! 🌎🤝 🔗 https://t.co/KNi4aWCaYU
#LXAI #LatinxInAI #AIResearch #ML
0
2
7
Exciting news! We're thrilled to announce the appointment of Professor @hugo_larochelle as Mila's new Scientific Director! A deep learning pioneer and former head of Google's AI lab in Montreal, Hugo's leadership will be pivotal in advancing AI for the benefit of all. Read the
12
29
257