6 papers
The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation
Nicolas Dufour, Alexei A. Efros, Patrick Pérez
The Frechet Inception Distance (FID) is the de facto arbiter of image generation, yet most papers report just a single number from a single trained model using a single sampling se…
Multiple Choice Learning of Low-Rank Adapters for Language Modeling
Victor Letzelter, Hugo Malard, Mathieu Fontaine +4
We propose LoRA-MCL, a training scheme that extends next-token prediction in language models with a method designed to decode diverse, plausible sentence continuations at inference…
Understanding Data Temporality Impact on Large Language Models Pre-training
Hippolyte Pilchen, Romain Fabre, Franck Signe Talla +2
Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding remains poorly understo…
CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion
Moritz Böhle, Amélie Royer, Juliette Marrie +2
Vision-language models (VLMs) are commonly trained by directly inserting image tokens from a pretrained vision encoder into the text stream of a language model. This allows text an…
ARC-Encoder: learning compressed text representations for large language models
Hippolyte Pilchen, Edouard Grave, Patrick Pérez
Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can…
Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling
Neil Zeghidour, Eugene Kharitonov, Manu Orsini +6
We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an off…