activity
20222026
most citedSuperAnimal pretrained pose estimation models for behavioral analysis

111 citations · 111 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2026

Scaling Categorical Flow Maps

Oscar Davis, Anastasiia Filippova, Pierre Ablin +4

Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they unlock a host of advantages c…

cs.LG2026

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing

Anastasiia Filippova, David Grangier, Marco Cuturi +1

Serving transformer language models with high throughput requires caching Key-Values (KVs) to avoid redundant computation during autoregressive generation. The memory footprint of…

cs.CL2026

Optimal Splitting of Language Models from Mixtures to Specialized Domains

Skyler Seto, Pierre Ablin, Anastasiia Filippova +4

Language models achieve impressive performance on a variety of knowledge, language, and reasoning tasks due to the scale and diversity of pretraining data available. The standard t…

cs.LG2025

Partial Parameter Updates for Efficient Distributed Training

Anastasiia Filippova, Angelos Katharopoulos, David Grangier +1

We introduce a memory- and compute-efficient method for low-communication distributed training. Existing methods reduce communication by performing multiple local updates between i…

cs.LG2024

No Need to Talk: Asynchronous Mixture of Language Models

Anastasiia Filippova, Angelos Katharopoulos, David Grangier +1

We introduce SMALLTALK LM, an innovative method for training a mixture of language models in an almost asynchronous manner. Each model of the mixture specializes in distinct parts…

cs.CV2022★ 111 cited

SuperAnimal pretrained pose estimation models for behavioral analysis

Shaokai Ye, Anastasiia Filippova, Jessy Lauer +5

Quantification of behavior is critical in applications ranging from neuroscience, veterinary medicine and animal conservation efforts. A common key step for behavioral analysis is…