32 citations · 104 across the 19 of their papers we have counts for
21 papers
VisionMX: Unlocking Microscaling Post-Training Quantization for Vision Models
Elad Dror Cohen, Ofir Gordon, Lior Dikstein +2
Microscaling (MX) formats are emerging as a hardware-supported approach to efficient training and inference. They combine low-precision elements with shared block scales, but their…
Adaptive Latent Capacity for World Models
Idan Achituve, Lior Dikstein, Idit Diamant +2
We introduce Adaptive LeWorldModel (ALeWM), a world model based on a joint-embedding predictive architecture (JEPA) that learns to concentrate predictive information in compact pre…
Diverse Sampling in Diffusion Models with Divergence-Free Particle Guidance
Gal Vinograd, Idan Achituve, Ethan Fetaya
Modern generative models can produce high-quality samples, but independent samples under the same condition often yields highly similar outputs. Particle-based methods increase div…
LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs
Ofir Gordon, Lior Dikstein, Arnon Netzer +2
Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invert…
Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes
Neta Glazer, David Chernin, Idan Achituve +2
Recent advancements in Text-to-Speech (TTS) models, particularly in voice cloning, have intensified the demand for adaptable and efficient deepfake detection methods. As TTS system…
Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo
Idan Achituve, Hai Victor Habi, Amir Rosenfeld +3
In image processing, solving inverse problems is the task of finding plausible reconstructions of an image that was corrupted by some (usually known) degradation operator. Commonly…
Efficient Image Restoration via Latent Consistency Flow Matching
Elad Cohen, Idan Achituve, Idit Diamant +2
Recent advances in generative image restoration (IR) have demonstrated impressive results. However, these methods are hindered by their substantial size and computational demands,…
Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors
Ohad Rahamim, Hilit Segev, Idan Achituve +3
Generating 3D visual scenes is at the forefront of visual generative AI, but current 3D generation techniques struggle with generating scenes with multiple high-resolution objects.…
Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
Idan Achituve, Idit Diamant, Arnon Netzer +2
As machine learning becomes more prominent there is a growing demand to perform several inference tasks in parallel. Running a dedicated model for each task is computationally expe…
De-Confusing Pseudo-Labels in Source-Free Domain Adaptation
Idit Diamant, Amir Rosenfeld, Idan Achituve +2
Source-free domain adaptation aims to adapt a source-trained model to an unlabeled target domain without access to the source data. It has attracted growing attention in recent yea…
Data Augmentations in Deep Weight Spaces
Aviv Shamsian, David W. Zhang, Aviv Navon +10
Learning in weight spaces, where neural networks process the weights of other deep neural networks, has emerged as a promising research direction with applications in various field…
GD-VDM: Generated Depth for better Diffusion-based Video Generation
Ariel Lapid, Idan Achituve, Lior Bracha +1
The field of generative models has recently witnessed significant progress, with diffusion models showing remarkable performance in image generation. In light of this success, ther…
Guided Deep Kernel Learning
Idan Achituve, Gal Chechik, Ethan Fetaya
Combining Gaussian processes with the expressive power of deep neural networks is commonly done nowadays through deep kernel learning (DKL). Unfortunately, due to the kernel optimi…
Equivariant Architectures for Learning in Deep Weight Spaces
Aviv Navon, Aviv Shamsian, Idan Achituve +3
Designing machine learning architectures for processing neural networks in their raw weight matrix form is a newly introduced research direction. Unfortunately, the unique symmetry…
Communication Efficient Distributed Learning over Wireless Channels
Idan Achituve, Wenbo Wang, Ethan Fetaya +1
Vertical distributed learning exploits the local features collected by multiple learning workers to form a better global model. However, the exchange of data between the workers an…
Functional Ensemble Distillation
Coby Penso, Idan Achituve, Ethan Fetaya
Bayesian models have many desirable properties, most notable is their ability to generalize from limited data and to properly estimate the uncertainty in their predictions. However…
Multi-Task Learning as a Bargaining Game
Aviv Navon, Aviv Shamsian, Idan Achituve +4
In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for several tasks. Joint training reduces computation costs and improves data efficiency;…
Personalized Federated Learning with Gaussian Processes
Idan Achituve, Aviv Shamsian, Aviv Navon +2
Federated learning aims to learn a global model that performs well on client devices with limited cross-client communication. Personalized federated learning (PFL) further extends…
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
Idan Achituve, Aviv Navon, Yochai Yemini +2
Gaussian processes (GPs) are non-parametric, flexible, models that work well in many tasks. Combining GPs with deep learning methods via deep kernel learning (DKL) is especially co…
Auxiliary Learning by Implicit Differentiation
Aviv Navon, Idan Achituve, Haggai Maron +2
Training neural networks with auxiliary tasks is a common practice for improving the performance on a main task of interest. Two main challenges arise in this multi-task learning s…
Self-Supervised Learning for Domain Adaptation on Point-Clouds
Idan Achituve, Haggai Maron, Gal Chechik
Self-supervised learning (SSL) is a technique for learning useful representations from unlabeled data. It has been applied effectively to domain adaptation (DA) on images and video…