Burak Varıcı
78 posts
@VariciBurak
Postdoc at @mldcmu / PhD at @rpi / representation learning and causality
Hi I along with @pranamyapk will be presenting our work on ROPES: Robotic Pose Estimation via Score-Based Causal Representation Learning (arxiv.org/pdf/2510.20884) at Embodied World Models for Decision Making Workshop #NeurIPS 📍Upper Level Room 30A-E ⏲️ Dec 6
STARFlow gets an upgrade—it now works on videos🎥 We present STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows, a invertible, causal video generator built on autoregressive flows! 📄 Paper huggingface.co/papers/2511.20… 💻 Code github.com/apple/ml-starf… (1/10)
I will be admitting a select few highly motivated PhD students to join the CausalML Lab @JHUCompSci in Fall 2026. If you are interested in causal inference, generative models, and ML, apply to the JHU CS PhD program and list me as a potential advisor.
Hi, I'll be presenting Matryoshka Quantization (arxiv.org/abs/2502.06786) on 16th July at #ICML2025 📍East Exhibition Hall A-B #3606 ⏲️ 11 AM - 1:30 PM
I'll be at ICML this week to present our take on "what we're really learning in representation learning and why it works." Our central argument: "Representations are learned from the association between input 𝑋 and context variable 𝐴"
Why can foundation models transfer to so many downstream tasks? Will the scaling law end? Will pretraining end like Ilya Sutskever predicted? My PhD thesis builds the contexture theory to answer the above. Blog: runtianzhai.com/thesis Paper: arxiv.org/abs/2504.19792 🧵1/12
Jayson Tatum today underwent successful surgery to repair a ruptured right Achilles tendon. No timetable is currently available for his return, but he is expected to make a full recovery. Further updates will be provided when appropriate.
Exciting new PhD position at Utrecht University on the #causal effects of communication in #multi-agent #RL with Shihan Wang, Mehdi Dastani and me 🎉 Deadline 20 May uu.nl/en/organisatio…
In our #AISTATS2025 paper, we ask: when it is possible to recover a consistent joint distribution from conditionals? We propose path consistency and autoregressive path consistency—necessary and easily verifiable conditions. See you at Poster session 3, Monday 5th May.
