Chen-Hao (Lance) Chao
@chenhao_chao
PhD in CS @UofT
(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…
damn,.... this is so incredibly cool use case for discrete diffusion model
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…
🚀 Problem: Language models struggle with rapidly evolving info and context in fields like medicine & finance. We need ways to post-train LLMs to control how they absorb new knowledge. 🔍 Insight: Why not explain, and teach, LLMs how to learn? @YounwooC will be at #ICLR2025…
Large Language Diffusion Models introduce LLaDA, a diffusion model with an unprecedented 8B scale, trained entirely from scratch, rivaling LLaMA3 8B in performance. A text generation method different from the traditional left-to-right approach Prompt: Explain what artificial…
Finally, if you're interested in understanding how to leverage energy-based normalizing flows, check out @chenhao_chao 's work on Meow (chienfeng-hub.github.io/meow/) He'll be presenting on Dec. 12, 11:00 AM–2:00 PM at West Ballroom A-D #6403 🧵(7/7)
Excited to present a poster at #NeurIPS2024 in person. Join our session on Dec. 12, 11:00 AM–2:00 PM at West Ballroom A-D #6403. Details below: - NeurIPS Page: neurips.cc/virtual/2024/p… - Project Page: chienfeng-hub.github.io/meow/ #NeurIPS2024 #NVIDIA #RL
(3/3) Test-time demonstration of MEow on the NVIDIA Omniverse Isaac Gym environments. Code: github.com/ChienFeng-hub/… Paper: arxiv.org/abs/2405.13629 #NeurIPS2024 #NVIDIA #RL #generative
(2/3) MEow is the first MaxEnt RL framework that supports exact soft value function calculation and single loss function optimization. Superior performance on MuJoCo. Code: github.com/ChienFeng-hub/… Paper: arxiv.org/abs/2405.13629 #NeurIPS2024 #NVIDIA #RL #generative
(1/3) Thrilled to announce that our paper, "Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow" (MEow), has been accepted at NeurIPS 2024! Code: github.com/ChienFeng-hub/… Paper: arxiv.org/abs/2405.13629 #NeurIPS2024 #NVIDIA #RL #generative
📍Check out our updated blog post where we redefine the DLSM objective function for discrete variables. Read more: Blog: chen-hao-chao.github.io/dlsm/ Paper: arxiv.org/abs/2203.14206 #generative #AI #score #diffusion
[ICLR 2022] Denoising Likelihood Score Matching for Condition Score-Based Data Generation We propose a new denoising likelihood score-matching (DLSM) loss to deal with the score mismatch issue we found in the existing conditional score-based data generation methods.
Monte Carlo integration approximates integrals at a rate of 1/sqrt(n), independent of the dimension. en.wikipedia.org/wiki/Monte_Car…