2.6k citations · 5k across the 50 of their papers we have counts for
64 papers
Lossy Compressive Text Autoencoders
Vinko Sabolčec, Angelos Katharopoulos, David Grangier
Our work explores learning a compressed latent representation of text, at the intersection of data compression and representation learning. We propose an autoencoder architecture t…
KV-Kaizen: Learning Context-Adaptive Cache Compression Choices
Joao Monteiro, Louis Béthune, Anastasiia Filippova +3
As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This impacts LLM throughput negativ…
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…
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…
Which Data Matter? Embedding-Based Data Selection for Speech Recognition
Zakaria Aldeneh, Skyler Seto, Maureen de Seyssel +8
Modern ASR systems are typically trained on large-scale pseudo-labeled, in-the-wild data spanning multiple domains. While such heterogeneous data benefit generalist models designed…
Pretraining with hierarchical memories: separating long-tail and common knowledge
Hadi Pouransari, David Grangier, C Thomas +2
The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all wor…