Harry Zhao
@TheHarryZhao
PhD Candidate at @mcgillu x @Mila_Quebec, advised by Doina Precup & @Yoshua_Bengio Scientist @wayve_ai A true friend who roasts you and learns with you
Our paper on rejecting hallucinated planning targets is now accepted at @icmlconf 2025! 📜: arxiv.org/abs/2410.07096 💿: github.com/mila-iqia/delu… "Rejecting Hallucinated State Targets during Planning" - Authors: @TheHarryZhao, @TiSU32, @LarocheRomain, Doina Precup, @Yoshua_Bengio

My colleague Rupam Mahmood explains from first principles his groundbreaking work on Streaming Deep Reinforcement Learning: youtu.be/QOfkOl9QrZY?si…
Our Aeneas AI model gives historians valuable new insights into ancient inscriptions & ancient history that may have taken years to uncover otherwise. Published in @Nature today: deepmind.google/discover/blog/…
Undergraduate @TheZarifIkram spent two wonderful years with our team and witnessed how the team relocated to and laid our roots in Singapore. He explored GFlowNets, model based RL and LLM projects in our team and published/submitted 4 manuscripts as first author to top AI venues
👉 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 🧵👇
We're excited to announce the inaugural SMASH 2025 — Symposium on Model Accountability, Sustainability, and Healthcare — taking place @Mila_Quebec , Montreal on Nov 4–5, 2025! 🎉 Submission and registration: smashcon.org
worst part about this is you know it's gonna lead to him posting on linkedin something like "i got caught cheating at a coldplay concert. here's what it taught me about b2b sales"
Coldplay accidentally exposed an alleged affair between Astronomer CEO Andy Byron and his colleague Kristin Cabot at one of their recent concerts.
It turns out the Turing Award is actually a silvery bowl from Tiffanys.
Feel sorry for any first student authors whose months of handwork has been ruined by one irresponsible coauthor and such rather unreasonable policies which instead of punishing the culprit (e.g blacklisting/removing them from accepted papers ) chose to do this.
Out now! Sharing the old tweeprint nature.com/articles/s4159…
Excited to share our updated preprint characterizing a novel, slow recurrent circuit motif in raphe! biorxiv.org/content/10.110…