6 citations · 12 across the 14 of their papers we have counts for
16 papers
Characterizing and Mitigating Distributional Bias in Physics-Informed Generative Models
Tanja Bien, Samir Darouich, Lluís Pastor-Pérez +3
Physics-informed generative models augment a data-fitting objective with residual penalties that encourage physical constraints to hold in generated samples. However, improving con…
Fine-Tuning Diffusion Language Models with Context Selection and Target Weighting
Loay Mualem, Lluís Pastor-Pérez, Vinh Tong +4
Supervised fine-tuning of discrete diffusion language models masks some response tokens and trains the model to recover their original values from the visible context. The masking…
SPECTRA: Subspace-Preserving Embedding Calibration, Transport, and Replay for Fully Few-Shot Class-Incremental Audio Classification
Giries Abu Ayoub, Loay Mualem, Simon Korman
Fully few-shot class-incremental audio classification (FFCAC) requires recognizing new sound classes from only a handful of labeled examples per session, without forgetting previou…
ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillation
Loay Mualem, Vinh Tong, Samir Darouich +1
Distilling conditional diffusion models aims to transfer the behavior of a large teacher to a smaller student while preserving alignment across conditioning inputs. Unlike recognit…
Supportive Token Revealing for Fast Diffusion Language Model Decoding
Giries Abu Ayoub, Mario Barbara, Lluís Pastor-Pérez +4
Discrete diffusion language models can generate text efficiently by updating multiple masked positions in parallel, but this parallelism introduces a quality-latency trade-off. Agg…
SpurAudio: A Benchmark for Studying Shortcut Learning in Few-Shot Audio Classification
Giries Abu Ayoub, Morad Tukan, Loay Mualem
Few-shot classification (FSC) is widely used for learning from limited labeled data, yet most evaluations implicitly assume that target concepts are independent of contextual cues.…
SymDrift: One-Shot Generative Modeling under Symmetries
Samir Darouich, Vinh Tong, Lluís Pastor-Pérez +3
Generative modeling of physical systems, such as molecules, requires learning distributions that are invariant under global symmetries, such as rotations in three-dimensional space…
Improving Model Classification by Optimizing the Training Dataset
Morad Tukan, Loay Mualem, Eitan Netzer +1
In the era of data-centric AI, the ability to curate high-quality training data is as crucial as model design. Coresets offer a principled approach to data reduction, enabling effi…
Practical -Approximation for Submodular Maximization Subject to a Cardinality Constraint
Murad Tukan, Loay Mualem, Moran Feldman
Non-monotone constrained submodular maximization plays a crucial role in various machine learning applications. However, existing algorithms often struggle with a trade-off between…
Bridging the Gap Between General and Down-Closed Convex Sets in Submodular Maximization
Loay Mualem, Murad Tukan, Moran Fledman
Optimization of DR-submodular functions has experienced a notable surge in significance in recent times, marking a pivotal development within the domain of non-convex optimization.…
ORBSLAM3-Enhanced Autonomous Toy Drones: Pioneering Indoor Exploration
Murad Tukan, Fares Fares, Yotam Grufinkle +4
Navigating toy drones through uncharted GPS-denied indoor spaces poses significant difficulties due to their reliance on GPS for location determination. In such circumstances, the…
Submodular Minimax Optimization: Finding Effective Sets
Loay Mualem, Ethan R. Elenberg, Moran Feldman +1
Despite the rich existing literature about minimax optimization in continuous settings, only very partial results of this kind have been obtained for combinatorial settings. In thi…
Resolving the Approximability of Offline and Online Non-monotone DR-Submodular Maximization over General Convex Sets
Loay Mualem, Moran Feldman
In recent years, maximization of DR-submodular continuous functions became an important research field, with many real-worlds applications in the domains of machine learning, commu…
Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions
Murad Tukan, Loay Mualem, Alaa Maalouf
Pruning is one of the predominant approaches for compressing deep neural networks (DNNs). Lately, coresets (provable data summarizations) were leveraged for pruning DNNs, adding th…
Using Partial Monotonicity in Submodular Maximization
Loay Mualem, Moran Feldman
Over the last two decades, submodular function maximization has been the workhorse of many discrete optimization problems in machine learning applications. Traditionally, the study…
Online bin packing of squares and cubes
Leah Epstein, Loay Mualem
In the d-dimensional online bin packing problem, d-dimensional cubes of positive sizes no larger than 1 are presented one by one to be assigned to positions in d-dimensional unit c…