activity
20242026
collaborators

12 papers

cs.LG2026

Nectar: Neural Estimation of Cached-Token Attention via Regression

João Monteiro, Michal Klein, Pierre Ablin +1

Evaluating softmax attention over a fixed long context requires reading every cached key-value pair for each new query token. For a given context (a book, a manual, a legal corpus)…

cs.LG2026

Amortized Maximum Inner Product Search with Learned Support Functions

Theo X. Olausson, João Monteiro, Michal Klein +1

Maximum inner product search (MIPS) is a crucial subroutine in machine learning, requiring the identification of a vector taken within a database (the keys) that best aligns with a…

cs.LG2026

The Coupling Within: Flow Matching via Distilled Normalizing Flows

David Berthelot, Tianrong Chen, Jiatao Gu +6

Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration ste…

cs.LG2026

Flow Matching with Semidiscrete Couplings

Alireza Mousavi-Hosseini, Stephen Y. Zhang, Michal Klein +1

Flow models parameterized as time-dependent velocity fields can generate data from noise by integrating an ODE. These models are often trained using flow matching, i.e. by sampling…

cs.CL2025

LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss

Pau Rodriguez, Michal Klein, Eleonora Gualdoni +5

The growing use of generative models in daily life calls for efficient mechanisms to control their generation, to e.g., produce safe content or provide users with tools to explore…

cs.LG2025

On Fitting Flow Models with Large Sinkhorn Couplings

Stephen Zhang, Alireza Mousavi-Hosseini, Michal Klein +1

Flow models transform data gradually from one modality (e.g. noise) onto another (e.g. images). Such models are parameterized by a time-dependent velocity field, trained to fit seg…