Publications (8)
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
Mustafa Shukor, Alexandre Rame, Corentin Dancette +1
Following the success of Large Language Models (LLMs), Large Multimodal Models (LMMs), such as the Flamingo model and its subsequent competitors, have started to emerge as natural…
CoRe: Color Regression for Multicolor Fashion Garments
Alexandre Rame, Arthur Douillard, Charles Ollion
Developing deep networks that analyze fashion garments has many real-world applications. Among all fashion attributes, color is one of the most important yet challenging to detect.…
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
Alexandre Rame, Corentin Dancette, Matthieu Cord
Learning robust models that generalize well under changes in the data distribution is critical for real-world applications. To this end, there has been a growing surge of interest…
DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation
Alexandre Rame, Matthieu Cord
Deep ensembles perform better than a single network thanks to the diversity among their members. Recent approaches regularize predictions to increase diversity; however, they also…
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks
Alexandre Rame, Remy Sun, Matthieu Cord
Recent strategies achieved ensembling "for free" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork lea…
OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation
Alexandre Rame, Emilien Garreau, Hedi Ben-Younes +1
Object detectors tend to perform poorly in new or open domains, and require exhaustive yet costly annotations from fully labeled datasets. We aim at benefiting from several dataset…
UnIVAL: Unified Model for Image, Video, Audio and Language Tasks
Mustafa Shukor, Corentin Dancette, Alexandre Rame +1
Large Language Models (LLMs) have made the ambitious quest for generalist agents significantly far from being a fantasy. A key hurdle for building such general models is the divers…
Direct Language Model Alignment from Online AI Feedback
Shangmin Guo, Biao Zhang, Tianlin Liu +9
Direct alignment from preferences (DAP) methods, such as DPO, have recently emerged as efficient alternatives to reinforcement learning from human feedback (RLHF), that do not requ…