Huy Tran

The Diffusion Process as a Correlation Machine: Linear Denoising Insights

Dana Weitzner, Mauricio Delbracio, Peyman Milanfar, Raja Giryes

Action editor: Arno Solin

https://openreview.net/forum?id=FGDJOc27rt

#denoising #denoisers #denoiser

Mesh-Informed Neural Operator : A Transformer Generative Approach

Yaozhong Shi, Zachary E Ross, Domniki Asimaki, Kamyar Azizzadenesheli

Action editor: Andriy Mnih

https://openreview.net/forum?id=K8qAuRfv0G

#generative #mesh #functional

Improved seeding strategies for k-means and k-GMM

Guillaume Carrière, Frederic Cazals

Action editor: Kejun Huang

https://openreview.net/forum?id=4Ut2YnekhN

#seeding #clustering #randomized

Slicing the Gaussian Mixture Wasserstein Distance

Moritz Piening, Robert Beinert

Action editor: Makoto Yamada

https://openreview.net/forum?id=yPBtJ4JPwi

#wasserstein #generative #minimization

Yucen Lily Li, Daohan Lu, Polina Kirichenko, Shikai Qiu, Tim G. J. Rudner, C. Bayan Bruss, Andrew Gordon Wilson: Out-of-Distribution Detection Methods Answer the Wrong Questions https://arxiv.org/abs/2507.01831 https://arxiv.org/pdf/2507.01831 https://arxiv.org/html/2507.01831

Sloan Nietert, Ziv Goldfeld
Estimation of Stochastic Optimal Transport Maps
https://arxiv.org/abs/2512.09499

A Comprehensive Survey on Knowledge Distillation

Amir M. Mansourian, Rozhan Ahmadi, Masoud Ghafouri et al.

Action editor: Changyou Chen

https://openreview.net/forum?id=3cbJzdR78B

#distillation #dnns #knowledge

Survey of Video Diffusion Models: Foundations, Implementations, and Applications

Yimu Wang, Xuye Liu, Wei Pang, Li Ma, Shuai Yuan, Paul Debevec, Ning Yu

Action editor: Anurag Arnab

https://openreview.net/forum?id=2ODDBObKjH

#video #generative #visual

Open Problems in Mechanistic Interpretability

Lee Sharkey, Bilal Chughtai, Joshua Batson et al.

Action editor: Sarath Chandar

https://openreview.net/forum?id=91H76m9Z94

#interpretability #ai #mechanistic

Read last night. Very nice. arxiv.org/abs/2512.01868

Two Is Better Than One: Aligned Representation Pairs for Anomaly Detection

Alain Ryser, Thomas M. Sutter, Alexander Marx, Julia E Vogt

Action editor: Shinichi Nakajima

https://openreview.net/forum?id=Bt0zdsnWYc

#outliers #anomaly #anomalies

Wondering how DeepSeek v3.2 rivals SOTA models (e.g., GPT5/Gemini 3 pro) while being ~30x cheaper? 🤔

Let's learn how the base model works!

We'll focus on attention, the need for KV caching, and key ideas for improving attention (MQA/GQA/MLA/DSA).

youtu.be/Y-o545eYjXM

Label Embedding via Low-Coherence Matrices

Jianxin Zhang, Clayton Scott

Action editor: Jake C. Snell

https://openreview.net/forum?id=vrcWXcr4On

#embedding #classification #label

Hyperparameter Optimization in Machine Learning Hyperparameters are configuration variables controlling the behavior of machine learning algorithms. They are ubiquitous in machine learning and artificial intelligence and the choice of their values ...

🚨 OpenReview might have leaked names, but it won't leak the best hyperparameters, unfortunately! 😅

Tired of the drama? Solve your HPO problems before the ICML deadline with this new monograph by our own Luca Franceschi & Massimiliano Pontil (& colleagues).

arxiv.org/abs/2410.22854

Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference Variational inference (VI) is a cornerstone of modern Bayesian learning, enabling approximate inference in complex models that would otherwise be intractable. However, its formulation depends on expec...

I'm quite intrigued by possibility theory, so I must say this looks quite exciting!

arxiv.org/abs/2511.21223

😂😂😂

🔄 Updated Arxiv Paper

Title: Modelling Global Trade with Optimal Transport
Authors: Thomas Gaskin, Guven Demirel, Marie-Therese Wolfram, Andrew Duncan

Read more: https://arxiv.org/abs/2409.06554

A Mixture of Exemplars Approach for Efficient Out-of-Distribution Detection with Foundation Models

Evelyn Mannix, Howard Bondell

Action editor: Gabriel Loaiza-Ganem

https://openreview.net/forum?id=xpKqnSJtE4

#classifier #detection #classification

A Unified Approach Towards Active Learning and Out-of-Distribution Detection

Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Günnemann

Action editor: Chicheng Zhang

https://openreview.net/forum?id=HL75La10FN

#detection #deep #feature

Reading group tomorrow: "How to build a consistency model: Learning flow maps via self-distillation" with Nicholas Boffi! arxiv.org/abs/2505.18825

Join us on zoom at 9am PT, 12pm ET, 6pm CET: portal.valencelabs.com/starklyspeak...

Unifying Self-Supervised Clustering and Energy-Based Models

Emanuele Sansone, Robin Manhaeve

Action editor: Ole Winther

https://openreview.net/forum?id=NW0uKe6IZa

#generative #supervised #models

Entangled Schrödinger Bridge Matching

Figure 1

Figure 2

Figure 3

Entangled Schrödinger Bridge Matching][new]
Models interacting particle dynamics by entangling velocities via coupled bias forces, improving trajectory simulation for systems with evolving interactions.

Does equivariance matter at scale?

Johann Brehmer, Sönke Behrends, Pim De Haan, Taco Cohen

Action editor: Marcus Brubaker

https://openreview.net/forum?id=wilNute8Tn

#models #equivariance #equivariant

The Principles of Diffusion Models This monograph presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematical ideas. Diffu...

"The Principles of Diffusion Models" by Chieh-Hsin Lai, Yang Song, Dongjun Kim, Yuki Mitsufuji, Stefano Ermon. arxiv.org/abs/2510.21890
It might not be the easiest intro to diffusion models, but this monograph is an amazing deep dive into the math behind them and all the nuances

New paper on arXiv! And I think it's a good'un 😄

Meet the new Lattice Random Walk (LRW) discretisation for SDEs. It’s radically different from traditional methods like Euler-Maruyama (EM) in that each iteration can only move in discrete steps {-δₓ, 0, δₓ}.

Samuel Duffield, Maxwell Aifer, Denis Melanson, Zach Belateche, Patrick J. Coles
Lattice Random Walk Discretisations of Stochastic Differential Equations
https://arxiv.org/abs/2508.20883

Luca Ambrogioni
The Information Dynamics of Generative Diffusion
https://arxiv.org/abs/2508.19897

Amortized Sampling with Transferable Normalizing Flows Efficient equilibrium sampling of molecular conformations remains a core challenge in computational chemistry and statistical inference. Classical approaches such as molecular dynamics or Markov chain...

Great stuff: arxiv.org/abs/2508.18175

A random old one:

"Kernels and Decision Trees"
hackmd.io/@sp-monte-ca...

It’s a thing! www.microsoft.com/en-us/resear...