Rahul G. Krishnan
@rahulgk
Assistant Professor @UofTCompSci @LMP_UofT & @VectorInst ⚒️ 🏥 ML, AI, Causality and Medicine Also at http://rahulgk.bsky.social
We develop MDM-Prime to enable discrete diffusion models to hedge generation by partially unmasking tokens. ✅ Improved denoising & model utilization ✅ Outperforms autoregressive models (ARM) 📰 arxiv.org/abs/2505.18495… 🧑💻chen-hao-chao.github.io/mdm-prime/ @chenhao_chao's 🧵 👇
(1/5) 👑 New Discrete Diffusion Model — MDM-Prime Why restrict tokens to just masked or unmasked in masked diffusion models (MDM)? We introduce MDM-Prime, a generalized MDM framework that enables partially unmasked tokens during sampling. ✅ Fine-grained denoising ✅ Better…
Paper 📄: openreview.net/forum?id=0zKHU… Poster session: 10:15-11:15 am & 4:45 - 5:30 pm. Joint work w/ @EkanshSh @rahulgk @yanii
Come by the Scaling Interventions workshop today at West Meeting Room 223. Vahid’s Oral will present CausalPFNs to reliably meta learn causal effect estimation!
Can neural networks learn to map from observational datasets directly onto causal effects? YES! Introducing CausalPFN, a foundation model trained on simulated data that learns to do in-context heterogeneous causal effect estimation, based on prior-fitted networks (PFNs). Joint…
5/5 Last but definitely not least, I’m honored to be giving a keynote on Wednesday (7/23) titled "Towards Causal Artificial Intelligence." For details, see: auai.org/uai2025/keynot… Here’s a short abstract: While many AI scientists and engineers believe we are on the verge of…
Excited to be presenting our work at ICML next week! If you're interested in loss landscapes, weight symmetries, or sparse training, come check out our poster — we'd love to chat. 📍 East Exhibition Hall A-B, #E-2106. 📅 Tue, July 15 | 🕚 11:00 a.m. – 1:30 p.m PDT.
1/10 🧵 🔍Can weight symmetry provide insights into sparse training and the Lottery Ticket Hypothesis? 🧐We dive deep into this question in our latest paper, "Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry", accepted at #ICML2025
👨🎓🧾✨#icml2025 Paper: TabICL, A Tabular Foundation Model for In-Context Learning on Large Data With @JingangQu, @DHolzmueller and @MarineLeMorvan TL;DR: a well-designed architecture and pretraining gives best tabular learner, and more scalable 1/9
Would love help identifying amazing ML researchers with strong connections to Canada who are currently outside Canada (thus potentially targets for recruitment as US situation deteriorates). DMs please. Retweet please.
Where the bits really come from.
This is the syllabus of the course @geoffreyhinton and I taught in 1998 at the Gatsby Unit (just after it was founded). Notice anything?