10 papers · 1 filter
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)…
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…
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…
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…
The Geometries of Truth Are Orthogonal Across Tasks
Waiss Azizian, Michael Kirchhof, Eugene Ndiaye +4
Large Language Models (LLMs) have demonstrated impressive generalization capabilities across various tasks, but their claim to practical relevance is still mired by concerns on the…
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…
Controlling Language and Diffusion Models by Transporting Activations
Pau Rodriguez, Arno Blaas, Michal Klein +4
The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To addr…
Simple ReFlow: Improved Techniques for Fast Flow Models
Beomsu Kim, Yu-Guan Hsieh, Michal Klein +4
Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps, this slows inference and limits applicability to time-critical…
Contrasting Multiple Representations with the Multi-Marginal Matching Gap
Zoe Piran, Michal Klein, James Thornton +1
Learning meaningful representations of complex objects that can be seen through multiple () views or modalities is a core task in machine learning. Existing methods use lo…
Careful with that Scalpel: Improving Gradient Surgery with an EMA
Yu-Guan Hsieh, James Thornton, Eugene Ndiaye +3
Beyond minimizing a single training loss, many deep learning estimation pipelines rely on an auxiliary objective to quantify and encourage desirable properties of the model (e.g. p…