65 citations · 171 across the 25 of their papers we have counts for
25 papers
Gemma 4 Technical Report
Gemma Team, Sherif El Abd, Vaibhav Aggarwal +320
We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemm…
Decoupled DiLoCo for Resilient Distributed Pre-training
Arthur Douillard, Keith Rush, Yani Donchev +14
Modern large-scale language model pre-training relies heavily on the single program multiple data (SPMD) paradigm, which requires tight coupling across accelerators. Due to this co…
FoodSense: A Multisensory Food Dataset and Benchmark for Predicting Taste, Smell, Texture, and Sound from Images
Sabab Ishraq, Aarushi Aarushi, Juncai Jiang +1
Humans routinely infer taste, smell, texture, and even sound from food images a phenomenon well studied in cognitive science. However, prior vision language research on food has fo…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
MedGemma Technical Report
Andrew Sellergren, Sahar Kazemzadeh, Tiam Jaroensri +78
Artificial intelligence (AI) has significant potential in healthcare applications, but its training and deployment faces challenges due to healthcare's diverse data, complex tasks,…
Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style
Debdeep Sanyal, Agniva Maiti, Umakanta Maharana +4
Effective teaching requires adapting instructional strategies to accommodate the diverse cognitive and behavioral profiles of students, a persistent challenge in education and teac…
Gemma 3 Technical Report
Gemma Team, Aishwarya Kamath, Johan Ferret +209
We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters. This version introduces vision underst…
SPOT: Text Source Prediction from Originality Score Thresholding
Edouard Yvinec, Gabriel Kasser
The wide acceptance of large language models (LLMs) has unlocked new applications and social risks. Popular countermeasures aim at detecting misinformation, usually involve domain…
PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Deep neural networks (DNNs) are ubiquitous in computer vision and natural language processing, but suffer from high inference cost. This problem can be addressed by quantization, w…
Archtree: on-the-fly tree-structured exploration for latency-aware pruning of deep neural networks
Rémi Ouazan Reboul, Edouard Yvinec, Arnaud Dapogny +1
Deep neural networks (DNNs) have become ubiquitous in addressing a number of problems, particularly in computer vision. However, DNN inference is computationally intensive, which c…
Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
The massive interest in deep neural networks (DNNs) for both computer vision and natural language processing has been sparked by the growth in computational power. However, this le…
Gradient-Based Post-Training Quantization: Challenging the Status Quo
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Quantization has become a crucial step for the efficient deployment of deep neural networks, where floating point operations are converted to simpler fixed point operations. In its…
NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Deep neural network (DNN) deployment has been confined to larger hardware devices due to their expensive computational requirements. This challenge has recently reached another sca…
SAfER: Layer-Level Sensitivity Assessment for Efficient and Robust Neural Network Inference
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly +1
Deep neural networks (DNNs) demonstrate outstanding performance across most computer vision tasks. Some critical applications, such as autonomous driving or medical imaging, also r…
Designing strong baselines for ternary neural network quantization through support and mass equalization
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Deep neural networks (DNNs) offer the highest performance in a wide range of applications in computer vision. These results rely on over-parameterized backbones, which are expensiv…
Fighting over-fitting with quantization for learning deep neural networks on noisy labels
Gauthier Tallec, Edouard Yvinec, Arnaud Dapogny +1
The rising performance of deep neural networks is often empirically attributed to an increase in the available computational power, which allows complex models to be trained upon l…
PowerQuant: Automorphism Search for Non-Uniform Quantization
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord +1
Deep neural networks (DNNs) are nowadays ubiquitous in many domains such as computer vision. However, due to their high latency, the deployment of DNNs hinges on the development of…
SInGE: Sparsity via Integrated Gradients Estimation of Neuron Relevance
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord +1
The leap in performance in state-of-the-art computer vision methods is attributed to the development of deep neural networks. However it often comes at a computational price which…
To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding
Edouard Yvinec, Arnaud Dapogny, Kevin Bailly
Batch-Normalization (BN) layers have become fundamental components in the evermore complex deep neural network architectures. Such models require acceleration processes for deploym…
SPIQ: Data-Free Per-Channel Static Input Quantization
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord +1
Computationally expensive neural networks are ubiquitous in computer vision and solutions for efficient inference have drawn a growing attention in the machine learning community.…
REx: Data-Free Residual Quantization Error Expansion
Edouard Yvinec, Arnaud Dapgony, Matthieu Cord +1
Deep neural networks (DNNs) are ubiquitous in computer vision and natural language processing, but suffer from high inference cost. This problem can be addressed by quantization, w…
Multi-label Transformer for Action Unit Detection
Gauthier Tallec, Edouard Yvinec, Arnaud Dapogny +1
Action Unit (AU) Detection is the branch of affective computing that aims at recognizing unitary facial muscular movements. It is key to unlock unbiased computational face represen…
RED++ : Data-Free Pruning of Deep Neural Networks via Input Splitting and Output Merging
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord +1
Pruning Deep Neural Networks (DNNs) is a prominent field of study in the goal of inference runtime acceleration. In this paper, we introduce a novel data-free pruning protocol RED+…
RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks
Edouard Yvinec, Arnaud Dapogny, Matthieu Cord +1
Deep Neural Networks (DNNs) are ubiquitous in today's computer vision land-scape, despite involving considerable computational costs. The mainstream approaches for runtime accelera…