Uploaded August 2026 | Updated November 2026, 3 days ago
Krishna Balasubramanian (UC Davis)
https://simons.berkeley.edu/talks/krishna-balasubramanian-uc-davis-2026-08-03
Diffusion Generative Modeling: Progress and Next Steps
We view drifting from a Wasserstein gradient flow (WGF) perspective and propose a conservative method for one-step generative modeling, replacing the original displacement-based velocity with a KDE-gradient field given by the difference between kernel-smoothed data and model scores. Using a joint-entropy identity, we establish continuous-time finite-particle bounds on R^d, including a root residual-velocity rate of N^{-1/(d+4)} under bandwidth-uniform quadrature regularity. We also analyze the original non-conservative Laplace-kernel method through a sharp companion-kernel decomposition and show how the resulting residual-velocity bounds yield explicit one-step generation guarantees in terms of the drift size.
Krishna Balasubramanian (UC Davis)
https://simons.berkeley.edu/talks/krishna-balasubramanian-uc-davis-2026-08-03
Diffusion Generative Modeling: Progress and Next Steps
We view drifting from a Wasserstein gradient flow (WGF) perspective and propose a conservative method for one-step generative modeling, replacing the original displacement-based velocity with a KDE-gradient field given by the difference between kernel-smoothed data and model scores. Using a joint-entropy identity, we establish continuous-time finite-particle bounds on R^d, including a root residual-velocity rate of N^{-1/(d+4)} under bandwidth-uniform quadrature regularity. We also analyze the original non-conservative Laplace-kernel method through a sharp companion-kernel decomposition and show how the resulting residual-velocity bounds yield explicit one-step generation guarantees in terms of the drift size.


![In Search of Missing Mass: Disentangling Discoveries from Hallucinations
Eric Nalisnick (Johns Hopkins University)
https://simons.berkeley.edu/talks/eric-nalisnick-johns-hopkins-university-2026-10-07
Trustworthy AI: From Hallucinations to Reliable Autonomy
Large language models (LLMs) hold much promise for scientific discovery. However, many basic questions remain about when an LLM can reliably make discoveries. In this talk, I will discuss how to interpret and extend the hallucination results of Kalai & Vempala [STOC 2024] to characterize an LLMs potential for discovery. In particular, how might we identify prompts that are likely to yield discoveries rather than hallucinations? In Search of Missing Mass: Disentangling Discoveries from Hallucinations](https://i.ytimg.com/vi/ZNlZsI9kBm4/mqdefault.jpg)







