263 citations · 392 across the 53 of their papers we have counts for
58 papers
On Trajectory-Aware Training for Masked Diffusion Language Models
Manuel Madeira, Amitis Shidani, Alice Bizeul +6
Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The model is trained on randomly mas…
Cartridges++: KV Cache Compression without Off-Context Derailment
Sonia Laguna, Joao Monteiro, Marco Cuturi +2
Serving long documents to a Large Language Model (LLM) repeatedly is expensive: computations grow with context length, and the memory footprint of the key-value (KV) cache balloons…
KV-Lingo: Learning KV-Cache Translators with Distillation
Valérie Castin, Keitaro Sakamoto, Anastasiia Filippova +3
Large language models represent context with a key-value (KV) cache. Caches are model-specific: for the same text, models with different architectures or weights produce incompatib…
Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
Valérie Castin, Kimia Nadjahi, Pierre Ablin +1
Low-Rank Adaptation (LoRA) is the most widely adopted method for fine-tuning large language models. Notably, LoRA is inherently overparameterized: multiple pairs of low-rank factor…
Scaling Laws for Mixture Pretraining Under Data Constraints
Anastasiia Sedova, Skyler Seto, Natalie Schluter +1
As language models scale, the amount of data they require grows -- yet many target data sources, such as low-resource languages or specialized domains, are inherently limited in si…
Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings
Paul Jeha, Anastasiia Sedova, Louis Béthune +4
For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization…