MSR NE seminar: Probabilistic Inference for Controlling Diffusion Models
jmhernandez233 · x · 2026-09-07
Microsoft Research New England's Generative Modeling and Sampling Seminar next Tuesday features Jiajun He speaking on "Probabilistic Inference for Controlling Diffusion Models," exploring how probabilistic inference methods can steer diffusion model generation. Join info linked in the post.
More from Research
- The Jailbreak Argument Against LLM Values: Why Value Loading Isn't Solved — gleech · 2026-09-07
- ICML Paper: Reward Functions Are Only Partially Identifiable, Even With Infinite Data — gleech · 2026-09-07
- Goal Misgeneralization in Deep RL: Agents Keep Their Skills but Pursue the Wrong Goal — gleech · 2026-09-07
- Underdetermination in Alignment: Training Data Pins Down Capability but Not Goals — gleech · 2026-09-07
- Anthropic says Claude wrote the longest math proof ever, cracking a 358-year-old problem — basedjensen · 2026-09-07
- Differentiable rendering going LLM-based makes sense; video generation may replace path tracing — jongranskog · 2026-09-07