Search Results for author:
Found 23 papers, 16 papers with code
Pixtral 12B
Unlike many open-source models, Pixtral is also a cutting-edge text model for its size, and does not compromise on natural language performance to excel in multimodal tasks.
Mixtral of Experts
In particular, Mixtral vastly outperforms Llama 2 70B on mathematics, code generation, and multilingual benchmarks.
Ranked #12 on
Question Answering
on PIQA
Mistral 7B
We introduce Mistral 7B v0. 1, a 7-billion-parameter language model engineered for superior performance and efficiency.
Ranked #5 on
Zero-Shot Video Question Answer
on NExT-GQA
Privately generating tabular data using language models
Privately generating synthetic data from a table is an important brick of a privacy-first world.
Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano
Differential privacy (DP) is by far the most widely accepted framework for mitigating privacy risks in machine learning.
TAN Without a Burn: Scaling Laws of DP-SGD
Differentially Private methods for training Deep Neural Networks (DNNs) have progressed recently, in particular with the use of massive batches and aggregated data augmentations for a large number of training steps.
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
We propose a novel method, CANIFE, that uses canaries - carefully crafted samples by a strong adversary to evaluate the empirical privacy of a training round.
Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms
A common countermeasure against MI attacks is to utilize differential privacy (DP) during model training to mask the presence of individual examples.
Defending against Reconstruction Attacks with Rényi Differential Privacy
Reconstruction attacks allow an adversary to regenerate data samples of the training set using access to only a trained model.
Watermarking Images in Self-Supervised Latent Spaces
We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches.
Nearest neighbor search with compact codes: A decoder perspective
Modern approaches for fast retrieval of similar vectors on billion-scaled datasets rely on compressed-domain approaches such as binary sketches or product quantization.
Opacus: User-Friendly Differential Privacy Library in PyTorch
We introduce Opacus, a free, open-source PyTorch library for training deep learning models with differential privacy (hosted at opacus. ai).
Gradient-based Adversarial Attacks against Text Transformers
We propose the first general-purpose gradient-based attack against transformer models.
Going deeper with Image Transformers
In particular, we investigate the interplay of architecture and optimization of such dedicated transformers.
Ranked #5 on
Image Classification
on Stanford Cars
Training data-efficient image transformers & distillation through attention
In this work, we produce a competitive convolution-free transformer by training on Imagenet only.
Ranked #4 on
Efficient ViTs
on ImageNet-1K (with DeiT-S)
Grafit: Learning fine-grained image representations with coarse labels
By jointly leveraging the coarse labels and the underlying fine-grained latent space, it significantly improves the accuracy of category-level retrieval methods.
Ranked #2 on
Learning with coarse labels
on cifar100
Fine-Grained Image Classification
Learning with coarse labels
+3
Radioactive data: tracing through training
The mark is robust to strong variations such as different architectures or optimization methods.
White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
Membership inference determines, given a sample and trained parameters of a machine learning model, whether the sample was part of the training set.
Large Memory Layers with Product Keys
In our experiments we consider a dataset with up to 30 billion words, and we plug our memory layer in a state-of-the-art transformer-based architecture.
Déjà Vu: an empirical evaluation of the memorization properties of ConvNets
Convolutional neural networks memorize part of their training data, which is why strategies such as data augmentation and drop-out are employed to mitigate overfitting.
Spreading vectors for similarity search
Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods.
Link and code: Fast indexing with graphs and compact regression codes
Similarity search approaches based on graph walks have recently attained outstanding speed-accuracy trade-offs, taking aside the memory requirements.
How should we evaluate supervised hashing?
Hashing produces compact representations for documents, to perform tasks like classification or retrieval based on these short codes.
