Search Results for author:
Found 18 papers, 12 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
Common Sense Reasoning
on ARC (Easy)
Mistral 7B
We introduce Mistral 7B v0. 1, a 7-billion-parameter language model engineered for superior performance and efficiency.
Ranked #1 on
answerability prediction
on PeerQA
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Several post-training quantization methods have been applied to large language models (LLMs), and have been shown to perform well down to 8-bits.
Evaluating Privacy Leakage in Split Learning
In particular, on-device machine learning allows us to avoid sharing raw data with a third-party server during inference.
Green Federated Learning
The rapid progress of AI is fueled by increasingly large and computationally intensive machine learning models and datasets.
Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design
In private federated learning (FL), a server aggregates differentially private updates from a large number of clients in order to train a machine learning model.
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.
Reconciling Security and Communication Efficiency in Federated Learning
Cross-device Federated Learning is an increasingly popular machine learning setting to train a model by leveraging a large population of client devices with high privacy and security guarantees.
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.
An Embedding of ReLU Networks and an Analysis of their Identifiability
The overall objective of this paper is to introduce an embedding for ReLU neural networks of any depth, $\Phi(\theta)$, that is invariant to scalings and that provides a locally linear parameterization of the realization of the network.
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
We design a family of image classification architectures that optimize the trade-off between accuracy and efficiency in a high-speed regime.
Ranked #15 on
Image Classification
on Stanford Cars
Low Bandwidth Video-Chat Compression using Deep Generative Models
To unlock video chat for hundreds of millions of people hindered by poor connectivity or unaffordable data costs, we propose to authentically reconstruct faces on the receiver's device using facial landmarks extracted at the sender's side and transmitted over the network.
Training with Quantization Noise for Extreme Model Compression
A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator.
And the Bit Goes Down: Revisiting the Quantization of Neural Networks
In this paper, we address the problem of reducing the memory footprint of convolutional network architectures.
ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
ConvNets and Imagenet have driven the recent success of deep learning for image classification.
