arXiv subjects

François Leduc-Primeau

Publications and source records attributed to François Leduc-Primeau.

At least 19 recordsLinked to original sources

arXiv2026

Quantized Transformers for Massive MIMO Precoding with Automatic Resolution Tuning

Deep learning precoders, particularly those based on Transformer architectures, offer superior spectral efficiency for Massive MIMO systems but may incur high computational cost. While existing mixed-precision quantization studies on convolutional neural networks establish important energy baselines, traditional discrete search methods fail to scale to the large parameter spaces of modern Transformers. To bridge this gap, we apply a differentiable precision learning technique to massive MIMO precoding. This approach autonomously and jointly optimizes weights, activations, quantization step sizes, and layer-wise bit-widths in a single training loop, directly optimizing for energy efficiency. We further expand this approach by incorporating Neural Architecture Search across various Transformer model sizes and evaluating the impact of random versus floating-point trained initializations on resolution tuning. Ultimately, we demonstrate that the proposed training method enables the deployment of highly compact Transformer precoders, improving energy efficiency by up to 288$\times$ compared to the classical Weighted Minimum Mean Square Error algorithm at equal sum-rate performance in a dense downtown environment.

eess.SP↗

arXiv2026

Sequential Automorphism Ensemble Decoding with Early Stopping

In this paper, a low-complexity approach for the automorphism ensemble decoder (AED) using successive cancellation (SC) as constituent decoders is proposed. The approach sequentially activates sub-decoders and terminates the decoding process based on pre-optimized parameters, derived from the strong correlation observed between the decoding outcome and the SC path metric. An algorithm is proposed to find a list of early termination thresholds that minimize average decoding complexity subject to a block-error rate (BLER) constraint. For various code parameters and a BLER below $10^{-3}$, simulation results show that average decoding complexity is reduced by a factor of at least $6 \times$, and up to $22 \times$, compared to the original AED complexity, with a negligible degradation in BLER.

cs.IT↗

arXiv2026

SLAD : Shared LoRA Adapters for Task Specific Distillation

In the context of resource-constrained environments such as embedded systems, adapting reduced-size foundation models to downstream tasks has become increasingly popular. This has recently motivated the emerging setting of task-specific distillation, where a larger and a smaller version of the same foundation model are both adapted to the same downstream task, with the goal of transferring knowledge from the former to the latter. Recent work has demonstrated the benefits of using a larger version of the same foundation model to assist the adaptation of a smaller one. Typically, the larger model (teacher) is first adapted via fine-tuning or linear probing before its knowledge is distilled into the smaller model (student). While fine-tuning the teacher often increases its performance, recent work showed that probing it leads to better knowledge distillation to the student. Our findings show that this is mainly due to a mis-alignment in feature representation between the teacher and the student which occurs during the teacher's fine-tuning. Inspired by existing efforts to preserve previously learned knowledge, we first propose leveraging low-rank adaptation, resulting in better feature alignment and therefore better knowledge transfer. Drawing from this insight, we further enhance the feature alignment through a parameter-sharing strategy of the adapters between the two encoders during joint training. Our proposed method, SLAD, shows better feature alignment between the teacher and student, which results in increased performance for not only the student but also the teacher model, while being 2x faster to train than fine-tuning. Through extensive experiments on multiple classification and segmentation datasets, we demonstrate the improved accuracy and transfer efficiency of our method, achieving state-of-the-art performance in the task-specific distillation framework.

cs.CV↗

arXiv2026

MUKA: Multi Kernel Audio Adaptation Of Audio-Language Models

Multimodal foundation models have demonstrated impressive generalization capabilities, yet efficiently adapting them to new tasks in a few-shot setting remains a critical challenge. In this work, we investigate the few-shot adaptation of Large Audio-Language Models (ALMs) through both training-based and training-free approaches. We introduce MUKA, a multi-kernel adaptation framework that combines the fine-grained, context-dependent representations of instruction-tuning based models like Pengi with the global semantic representations of contrastive pretraining methods like CLAP. By constructing a product kernel that aligns local similarity with global semantics, MUKA enhances representational power while preserving the theoretical guarantees of kernel methods and avoiding additional training. Extensive experiments across 11 diverse audio datasets demonstrate that MUKA achieves state-of-the-art performance among training-free methods and even surpasses training-based adapters in several scenarios, offering a compelling balance between adaptability and efficiency.

cs.SD↗

arXiv2026

TensLoRA: Tensor Alternatives for Low-Rank Adaptation

Low-Rank Adaptation (LoRA) is widely used to efficiently adapt Transformers by adding trainable low-rank matrices to attention projections. While effective, these matrices are considered independent for each attention projection (Query, Key, and Value) and each layer. Recent extensions have considered joint, tensor-based adaptations, but only in limited forms and without a systematic framework. We introduce TensLoRA, a unified framework that aggregates LoRA updates into higher-order tensors and models a broad family of tensor-based low-rank adaptations. Our formulation generalizes existing tensor-based methods and enables mode-specific compression rates, allowing parameter budgets to be tailored according to the modality and task. Experiments on vision and language benchmarks reveal that the tensor construction directly impacts performance, sometimes better than standard LoRA under similar parameter counts.

cs.LG↗

arXiv2026

A Low-Complexity Plug-and-Play Deep Learning Model for Generalizable Massive MIMO Precoding

Massive multiple-input multiple-output (mMIMO) downlink precoding offers high spectral efficiency but remains challenging to deploy in practice because near-optimal algorithms such as the weighted minimum mean squared error (WMMSE) are computationally expensive, and sensitive to SNR and channel-estimation quality, while existing deep learning (DL)-based solutions often lack robustness and require retraining for each deployment site. This paper proposes a plug-and-play precoder (PaPP), a DL framework with a backbone that can be trained for either fully digital (FDP) or hybrid beamforming (HBF) precoding and reused across sites, transmit-power levels, and with varying amounts of channel estimation error, avoiding the need to train a new model from scratch at each deployment. PaPP combines a high-capacity teacher and a compact student with a self-supervised loss that balances teacher imitation and normalized sum-rate, trained using meta-learning domain-generalization and transmit-power-aware input normalization. Numerical results on ray-tracing data from three unseen sites show that the PaPP FDP and HBF models both outperform conventional and deep learning baselines, after fine-tuning with a small set of local unlabeled samples. Across both architectures, PaPP achieves more than 21$\times$ reduction in modeled computation energy and maintains good performance under channel-estimation errors, making it a practical solution for energy-efficient mMIMO precoding.

cs.LG↗

arXiv2025

A Foundation Model for Massive MIMO Precoding with an Adaptive per-User Rate-Power Tradeoff

Deep learning (DL) has emerged as a solution for precoding in massive multiple-input multiple-output (mMIMO) systems due to its capacity to learn the characteristics of the propagation environment. However, training such a model requires high-quality, local datasets at the deployment site, which are often difficult to collect. We propose a transformer-based foundation model for mMIMO precoding that seeks to minimize the energy consumption of the transmitter while dynamically adapting to per-user rate requirements. At equal energy consumption, zero-shot deployment of the proposed foundation model significantly outperforms zero forcing, and approaches weighted minimum mean squared error performance with 8x less complexity. To address model adaptation in data-scarce settings, we introduce a data augmentation method that finds training samples similar to the target distribution by computing the cosine similarity between the outputs of the pre-trained feature extractor. Our work enables the implementation of DL-based solutions in practice by addressing challenges of data availability and training complexity. Moreover, the ability to dynamically configure per-user rate requirements can be leveraged by higher level resource allocation and scheduling algorithms for greater control over energy efficiency, spectral efficiency and fairness.

eess.SP↗

arXiv2025

A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models

Few-shot semantic segmentation (FSS) is a crucial challenge in computer vision, driving extensive research into a diverse range of methods, from advanced meta-learning techniques to simple transfer learning baselines. With the emergence of vision foundation models (VFM) serving as generalist feature extractors, we seek to explore the adaptation of these models for FSS. While current FSS benchmarks focus on adapting pre-trained models to new tasks with few images, they emphasize in-domain generalization, making them less suitable for VFM trained on large-scale web datasets. To address this, we propose a novel realistic benchmark with a simple and straightforward adaptation process tailored for this task. Using this benchmark, we conduct a comprehensive comparative analysis of prominent VFM and semantic segmentation models. To evaluate their effectiveness, we leverage various adaption methods, ranging from linear probing to parameter efficient fine-tuning (PEFT) and full fine-tuning. Our findings show that models designed for segmentation can be outperformed by self-supervised (SSL) models. On the other hand, while PEFT methods yields competitive performance, they provide little discrepancy in the obtained results compared to other methods, highlighting the critical role of the feature extractor in determining results. To our knowledge, this is the first study on the adaptation of VFM for FSS.

cs.CV↗

arXiv2025

A Low-Complexity Plug-and-Play Deep Learning Model for Massive MIMO Precoding Across Sites

Massive multiple-input multiple-output (mMIMO) technology has transformed wireless communication by enhancing spectral efficiency and network capacity. This paper proposes a novel deep learning-based mMIMO precoder to tackle the complexity challenges of existing approaches, such as weighted minimum mean square error (WMMSE), while leveraging meta-learning domain generalization and a teacher-student architecture to improve generalization across diverse communication environments. When deployed to a previously unseen site, the proposed model achieves excellent sum-rate performance while maintaining low computational complexity by avoiding matrix inversions and by using a simpler neural network structure. The model is trained and tested on a custom ray-tracing dataset composed of several base station locations. The experimental results indicate that our method effectively balances computational efficiency with high sum-rate performance while showcasing strong generalization performance in unseen environments. Furthermore, with fine-tuning, the proposed model outperforms WMMSE across all tested sites and SNR conditions while reducing complexity by at least 73$\times$.

eess.SP↗

arXiv2025

Compression of Site-Specific Deep Neural Networks for Massive MIMO Precoding

The deployment of deep learning (DL) models for precoding in massive multiple-input multiple-output (mMIMO) systems is often constrained by high computational demands and energy consumption. In this paper, we investigate the compute energy efficiency of mMIMO precoders using DL-based approaches, comparing them to conventional methods such as zero forcing and weighted minimum mean square error (WMMSE). Our energy consumption model accounts for both memory access and calculation energy within DL accelerators. We propose a framework that incorporates mixed-precision quantization-aware training and neural architecture search to reduce energy usage without compromising accuracy. Using a ray-tracing dataset covering various base station sites, we analyze how site-specific conditions affect the energy efficiency of compressed models. Our results show that deep neural network compression generates precoders with up to 35 times higher energy efficiency than WMMSE at equal performance, depending on the scenario and the desired rate. These results establish a foundation and a benchmark for the development of energy-efficient DL-based mMIMO precoders.

eess.SP↗

arXiv2024

SAGE-HB: Swift Adaptation and Generalization in Massive MIMO Hybrid Beamforming

Deep learning (DL)-based solutions have emerged as promising candidates for beamforming in massive Multiple-Input Multiple-Output (mMIMO) systems. Nevertheless, it remains challenging to seamlessly adapt these solutions to practical deployment scenarios, typically necessitating extensive data for fine-tuning while grappling with domain adaptation and generalization issues. In response, we propose a novel approach combining Meta-Learning Domain Generalization (MLDG) with novel data augmentation techniques during fine-tuning. This approach not only accelerates adaptation to new channel environments but also significantly reduces the data requirements for fine-tuning, thereby enhancing the practicality and efficiency of DL-based mMIMO systems. The proposed approach is validated by simulating the performance of a backbone model when deployed in a new channel environment, and with different antenna configurations, path loss, and base station height parameters. Our proposed approach demonstrates superior zero-shot performance compared to existing methods and also achieves near-optimal performance with significantly fewer fine-tuning data samples.

eess.SP↗

arXiv2023

Learning Energy-Efficient Hardware Configurations for Massive MIMO Beamforming

Hybrid beamforming (HBF) and antenna selection are promising techniques for improving the energy efficiency~(EE) of massive multiple-input multiple-output~(mMIMO) systems. However, the transmitter architecture may contain several parameters that need to be optimized, such as the power allocated to the antennas and the connections between the antennas and the radio frequency chains. Therefore, finding the optimal transmitter architecture requires solving a non-convex mixed integer problem in a large search space. In this paper, we consider the problem of maximizing the EE of fully digital precoder~(FDP) and hybrid beamforming~(HBF) transmitters. First, we propose an energy model for different beamforming structures. Then, based on the proposed energy model, we develop an unsupervised deep learning method to maximize the EE by designing the transmitter configuration for FDP and HBF. The proposed deep neural networks can provide different trade-offs between spectral efficiency and energy consumption while adapting to different numbers of active users. Finally, to ensure that the proposed method can be implemented in practice, we investigate the ability of the model to be trained exclusively using imperfect channel state information~(CSI), both for the input to the deep learning model and for the calculation of the loss function. Simulation results show that the proposed solutions can outperform conventional methods in terms of EE while being trained with imperfect CSI. Furthermore, we show that the proposed solutions are less complex and more robust to noise than conventional methods.

eess.SP↗

arXiv2023

Sparq: A Custom RISC-V Vector Processor for Efficient Sub-Byte Quantized Inference

Convolutional Neural Networks (CNNs) are used in a wide range of applications, with full-precision CNNs achieving high accuracy at the expense of portability. Recent progress in quantization techniques has demonstrated that sub-byte Quantized Neural Networks (QNNs) achieve comparable or superior accuracy while significantly reducing the computational cost and memory footprint. However, sub-byte computation on commodity hardware is sub-optimal due to the lack of support for such precision. In this paper, we introduce Sparq, a Sub-byte vector Processor designed for the AcceleRation of QNN inference. This processor is based on a modified version of Ara, an open-source 64-bit RISC-V ``V'' compliant processor. Sparq is implemented in GLOBAL FOUNDRIES 22FDX FD-SOI technology and extends the Instruction Set Architecture (ISA) by adding a new multiply-shift-accumulate instruction to improve sub-byte computation effciency. The floating-point unit is also removed to minimize area and power usage. To demonstrate Sparq performance, we implement an ultra-low-precision (1-bit to 4-bit) vectorized conv2d operation taking advantage of the dedicated hardware. We show that Sparq can significantly accelerate sub-byte computations with respectively 3.2 times, and 1.7 times acceleration over an optimized 16-bit 2D convolution for 2-bit and 4-bit quantization.

cs.AR↗

arXiv2023

SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness

Energy-efficient deep neural network (DNN) accelerators are prone to non-idealities that degrade DNN performance at inference time. To mitigate such degradation, existing methods typically add perturbations to the DNN weights during training to simulate inference on noisy hardware. However, this often requires knowledge about the target hardware and leads to a trade-off between DNN performance and robustness, decreasing the former to increase the latter. In this work, we show that applying sharpness-aware training, by optimizing for both the loss value and loss sharpness, significantly improves robustness to noisy hardware at inference time without relying on any assumptions about the target hardware. In particular, we propose a new adaptive sharpness-aware method that conditions the worst-case perturbation of a given weight not only on its magnitude but also on the range of the weight distribution. This is achieved by performing sharpness-aware minimization scaled by outlier minimization (SAMSON). Our approach outperforms existing sharpness-aware training methods both in terms of model generalization performance in noiseless regimes and robustness in noisy settings, as measured on several architectures and datasets.

cs.LG↗

arXiv2022

Flexible Unsupervised Learning for Massive MIMO Subarray Hybrid Beamforming

Hybrid beamforming is a promising technology to improve the energy efficiency of massive MIMO systems. In particular, subarray hybrid beamforming can further decrease power consumption by reducing the number of phase-shifters. However, designing the hybrid beamforming vectors is a complex task due to the discrete nature of the subarray connections and the phase-shift amounts. Finding the optimal connections between RF chains and antennas requires solving a non-convex problem in a large search space. In addition, conventional solutions assume that perfect CSI is available, which is not the case in practical systems. Therefore, we propose a novel unsupervised learning approach to design the hybrid beamforming for any subarray structure while supporting quantized phase-shifters and noisy CSI. One major feature of the proposed architecture is that no beamforming codebook is required, and the neural network is trained to take into account the phase-shifter quantization. Simulation results show that the proposed deep learning solutions can achieve higher sum-rates than existing methods.

cs.IT↗

arXiv2022

MemSE: Fast MSE Prediction for Noisy Memristor-Based DNN Accelerators

Memristors enable the computation of matrix-vector multiplications (MVM) in memory and, therefore, show great potential in highly increasing the energy efficiency of deep neural network (DNN) inference accelerators. However, computations in memristors suffer from hardware non-idealities and are subject to different sources of noise that may negatively impact system performance. In this work, we theoretically analyze the mean squared error of DNNs that use memristor crossbars to compute MVM. We take into account both the quantization noise, due to the necessity of reducing the DNN model size, and the programming noise, stemming from the variability during the programming of the memristance value. Simulations on pre-trained DNN models showcase the accuracy of the analytical prediction. Furthermore the proposed method is almost two order of magnitude faster than Monte-Carlo simulation, thus making it possible to optimize the implementation parameters to achieve minimal error for a given power constraint.

cs.LG↗

arXiv2021

Optimizing the Energy Efficiency of Unreliable Memories for Quantized Kalman Filtering

This paper presents a quantized Kalman filter implemented using unreliable memories. We consider that both the quantization and the unreliable memories introduce errors in the computations, and develop an error propagation model that takes into account these two sources of errors. In addition to providing updated Kalman filter equations, the proposed error model accurately predicts the covariance of the estimation error and gives a relation between the performance of the filter and its energy consumption, depending on the noise level in the memories. Then, since memories are responsible for a large part of the energy consumption of embedded systems, optimization methods are introduced so as to minimize the memory energy consumption under a desired estimation performance of the filter. The first method computes the optimal energy levels allocated to each memory bank individually, and the second one optimizes the energy allocation per groups of memory banks. Simulations show a close match between the theoretical analysis and experimental results. Furthermore, they demonstrate an important reduction in energy consumption of more than 50%.

cs.IT↗

arXiv2020

Noisy Density Evolution With Asymmetric Deviation Models

This paper considers low-density parity-check (LDPC) decoders affected by deviations introduced by the electronic device on which the decoder is implemented. Noisy density evolution (DE) that allows to theoretically study the performance of these LDPC decoders can only consider symmetric deviation models due to the all-zero codeword assumption. A novel DE method is proposed that admits the use of asymmetric deviation models, thus widening the range of faulty implementations that can be analyzed. DE equations are provided for three noisy decoders: belief propagation, Gallager B, and quantized min-sum (MS). Simulation results confirm that the proposed DE accurately predicts the performance of LDPC decoders with asymmetric deviations. Furthermore, asymmetric versions of the Gallager B and MS decoders are proposed to compensate the effect of asymmetric deviations. The parameters of these decoders are then optimized using the proposed DE, leading to better ensemble thresholds and improved finite-length performance in the presence of asymmetric deviations.

cs.IT↗