activity
20192026
most citedTransformers are RNNs: Fast Autoregressive Transformers with Linear Attention

310 citations · 360 across the 15 of their papers we have counts for

collaborators

24 papers

cs.CV2026

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising

Youssef Saied, François Fleuret

Normalization Equivariance (NE) is a structural prior that improves robustness to distribution shift in image-to-image tasks. A function is normalization equivariant iff $f(a y…

cs.LG2026

AA-SVD : Anchored and Adaptive SVD for Large Language Model Compression

Atul Kumar Sinha, François Fleuret

We introduce a fast low-rank factorization-based framework for compressing large language models that enables rapid compression of billion-parameter models without retraining. Unli…

cs.CV2026

Laminating Representation Autoencoders for Efficient Diffusion

Ramón Calvo-González, François Fleuret

Recent work has shown that diffusion models can generate high-quality images by operating directly on SSL patch features rather than pixel-space latents. However, the dense patch g…

cs.LG2025

The Free Transformer

François Fleuret

We propose an extension of the decoder Transformer that conditions its generative process on random latent variables which are learned without supervision thanks to a variational p…

cs.CL2025

Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners

Daniele Paliotta, Junxiong Wang, Matteo Pagliardini +6

Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common s…

cs.LG2025

Leveraging the true depth of LLMs

Ramón Calvo González, Daniele Paliotta, Matteo Pagliardini +2

The remarkable capabilities of Large Language Models (LLMs) are overshadowed by their immense computational cost. While recent work has shown that many LLM layers can be reordered…