Non-Uniform Parameter-Wise Model Merging

Authors: Orozco Camacho, Albert M., Horoi, Stefan, Wolf, Guy, Belilovsky, Eugene

Source: 2024 IEEE International Conference on Big Data (BigData) Big Data (BigData), 2024 IEEE International Conference on. :5946-5954 Dec, 2024

Relation: 2024 IEEE International Conference on Big Data (BigData)

Continual Pre-training of MoEs: How robust is your router?

Authors: Thérien, Benjamin, Joseph, Charles-Étienne, Sarwar, Zain, Panda, Ashwinee, Das, Anirban, Zhang, Shi-Xiong, Rawls, Stephen, Sahu, Sambit, Belilovsky, Eugene, Rish, Irina

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2503.05029

Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training

Authors: Singh, Vaibhav, Janson, Paul, Mehrbod, Paria, Ibrahim, Adam, Rish, Irina, Belilovsky, Eugene, Thérien, Benjamin

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2503.02844

FairDropout: Using Example-Tied Dropout to Enhance Generalization of Minority Groups

Authors: Nanfack, Geraldin, Belilovsky, Eugene

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2502.06695

Learning Versatile Optimizers on a Compute Diet

Authors: Moudgil, Abhinav, Knyazev, Boris, Lajoie, Guillaume, Belilovsky, Eugene

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2501.12670

Non-Uniform Parameter-Wise Model Merging

Authors: Camacho, Albert Manuel Orozco, Horoi, Stefan, Wolf, Guy, Belilovsky, Eugene

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2412.15467

Towards motion from video diffusion models

Authors: Janson, Paul, Popa, Tiberiu, Belilovsky, Eugene

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2411.12831

Sketch-guided Cage-based 3D Gaussian Splatting Deformation

Authors: Xie, Tianhao, Aigerman, Noam, Belilovsky, Eugene, Popa, Tiberiu

Subject Terms: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Graphics

Access URL: http://arxiv.org/abs/2411.12168

Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting

Authors: Hameed, Humza Wajid, Nanfack, Geraldin, Belilovsky, Eugene

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2409.14637

Accelerating Training with Neuron Interaction and Nowcasting Networks

Authors: Knyazev, Boris, Moudgil, Abhinav, Lajoie, Guillaume, Belilovsky, Eugene, Lacoste-Julien, Simon

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2409.04434

Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis

Authors: Horoi, Stefan, Camacho, Albert Manuel Orozco, Belilovsky, Eugene, Wolf, Guy

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2407.05385

Controlling Forgetting with Test-Time Data in Continual Learning

Authors: Singh, Vaibhav, Aljundi, Rahaf, Belilovsky, Eugene

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2406.13653

PETRA: Parallel End-to-end Training with Reversible Architectures

Authors: Rivaud, Stéphane, Fournier, Louis, Pumir, Thomas, Belilovsky, Eugene, Eickenberg, Michael, Oyallon, Edouard

Subject Terms: Computer Science - Machine Learning, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2406.02052

From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation

Authors: Nanfack, Geraldin, Eickenberg, Michael, Belilovsky, Eugene

Subject Terms: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Cryptography and Security, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2406.01365

ACCO: Accumulate while you Communicate, Hiding Communications in Distributed LLM Training

Authors: Nabli, Adel, Fournier, Louis, Erbacher, Pierre, Serrano, Louis, Belilovsky, Eugene, Oyallon, Edouard

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2406.02613

Temporally Consistent Object Editing in Videos using Extended Attention

Authors: Zamani, AmirHossein, Aghdam, Amir G., Popa, Tiberiu, Belilovsky, Eugene

Subject Terms: Computer Science - Computer Vision and Pattern Recognition

Access URL: http://arxiv.org/abs/2406.00272

$\mu$LO: Compute-Efficient Meta-Generalization of Learned Optimizers

Authors: Thérien, Benjamin, Joseph, Charles-Étienne, Knyazev, Boris, Oyallon, Edouard, Rish, Irina, Belilovsky, Eugene

Subject Terms: Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2406.00153

WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average

Authors: Fournier, Louis, Nabli, Adel, Aminbeidokhti, Masih, Pedersoli, Marco, Belilovsky, Eugene, Oyallon, Edouard

Subject Terms: Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning

Access URL: http://arxiv.org/abs/2405.17517

AdaFisher: Adaptive Second Order Optimization via Fisher Information

Authors: Gomes, Damien Martins, Zhang, Yanlei, Belilovsky, Eugene, Wolf, Guy, Hosseini, Mahdi S.

Subject Terms: Computer Science - Machine Learning, Mathematics - Optimization and Control

Access URL: http://arxiv.org/abs/2405.16397

Automated liver segmentation and steatosis grading using deep learning on B-mode ultrasound images

Authors: Vianna, Pedro, Kulbay, Merve, Boustros, Pamela, Calce, Sara-Ivana, Larocque-Rigney, Cassandra, Patry-Beaudoin, Laurent, Luo, Yi Hui, Chaudary, Muawiz, Kadoury, Samuel, Nguyen, Bich, Montagnon, Emmanuel, Belilovsky, Eugene, Wolf, Guy, Chasse, Michael, Tang, An, Cloutier, Guy

Source: 2023 IEEE International Ultrasonics Symposium (IUS) Ultrasonics Symposium (IUS), 2023 IEEE International. :1-4 Sep, 2023

Relation: 2023 IEEE International Ultrasonics Symposium (IUS)