1 citations · 3 across the 24 of their papers we have counts for
28 papers
S-CEReBrO: Breaking the Memory Barrier in Continuous EEG Monitoring
Glenn Anta Bucagu, Thorir Mar Ingolfsson, Yawei Li +1
Foundation models offer a promising paradigm for Electroencephalography (EEG) analysis, leveraging generalizable representations from vast unlabeled datasets. Yet, Transformer-base…
Quantizing Recursive Reasoning Models
Thorir Mar Ingolfsson, Wajeeha Tahir, Anna Tegon +3
Recursive reasoning models solve hard puzzles by applying compact, weight-tied blocks over many refinement steps. Because these blocks are reused many times, quantizing them create…
RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache
Junkai Zhang, Hang Guo, Luca Benini +1
Large language models (LLMs) have shown strong performance across diverse tasks, but their inference with long input contexts is bottlenecked by memory size and bandwidth. The Key-…
PanLUNA: An Efficient and Robust Query-Unified Multimodal Model for Edge Biosignal Intelligence
Marija Zelic, Anna Tegon, Yawei Li +2
Physiological foundation models (FMs) have shown promise for biosignal representation learning, yet most remain confined to a single modality such as EEG, ECG, or PPG, largely beca…
FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontroller
Anna Tegon, Nicholas Lehmann, Yawei Li +3
Objective: To enable continuous, long-term neuro-monitoring on wearable devices by overcoming the computational bottlenecks of Transformer-based Electroencephalography (EEG) founda…
LuMamba: Latent Unified Mamba for Electrode Topology-Invariant and Efficient EEG Modeling
Danaé Broustail, Anna Tegon, Thorir Mar Ingolfsson +2
Electroencephalography (EEG) enables non-invasive monitoring of brain activity across clinical and neurotechnology applications, yet building foundation models for EEG remains chal…
Revisiting Adaptive Rounding with Vectorized Reparameterization for LLM Quantization
Yuli Zhou, Qingxuan Chen, Luca Benini +2
Adaptive Rounding has emerged as an alternative to round-to-nearest (RTN) for post-training quantization by enabling cross-element error cancellation. Yet, dense and element-wise r…
TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edge
Matteo Fasulo, Giusy Spacone, Thorir Mar Ingolfsson +3
Objective: Surface electromyography (EMG) is a non-invasive sensing modality widely used in biomechanics, rehabilitation, prosthetic control, and human-machine interfaces. Despite…
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
Yanlong Chen, Amirhossein Habibian, Luca Benini +1
Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss. Despite its pot…
LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
Berkay Döner, Thorir Mar Ingolfsson, Luca Benini +1
Electroencephalography (EEG) offers a non-invasive lens into human brain activity, but building large-scale models is hampered by topological heterogeneity: each public EEG data de…
Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs
Hang Guo, Yawei Li, Luca Benini
Recent advances in Large Language Model (LLM) compression, such as quantization and pruning, have achieved notable success. However, as these techniques gradually approach their re…
HiM2SAM: Enhancing SAM2 with Hierarchical Motion Estimation and Memory Optimization towards Long-term Tracking
Ruixiang Chen, Guolei Sun, Yawei Li +2
This paper presents enhancements to the SAM2 framework for video object tracking task, addressing challenges such as occlusions, background clutter, and target reappearance. We int…
One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression
Mikołaj Janusz, Tomasz Wojnar, Yawei Li +2
Pruning is a core technique for compressing neural networks to improve computational efficiency. This process is typically approached in two ways: one-shot pruning, which involves…
A Compute&Memory Efficient Model-Driven Neural 5G Receiver for Edge AI-assisted RAN
Mahdi Abdollahpour, Marco Bertuletti, Yichao Zhang +3
Artificial intelligence approaches for base-band processing for radio receivers have demonstrated significant performance gains. Most of the proposed methods are characterized by h…
WaveFormer: A Lightweight Transformer Model for sEMG-based Gesture Recognition
Yanlong Chen, Mattia Orlandi, Pierangelo Maria Rapa +3
Human-machine interaction, particularly in prosthetic and robotic control, has seen progress with gesture recognition via surface electromyographic (sEMG) signals.However, classify…
PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation
Yanlong Chen, Mattia Orlandi, Pierangelo Maria Rapa +3
Physiological signals are often corrupted by motion artifacts, baseline drift, and other low-SNR disturbances, which pose significant challenges for analysis. Additionally, these s…
FlatAttention: Dataflow and Fabric Collectives Co-Optimization for Efficient Multi-Head Attention on Tile-Based Many-PE Accelerators
Chi Zhang, Luca Colagrande, Renzo Andri +6
Multi-Head Attention (MHA) is a critical computational kernel in transformer-based AI models. Emerging scalable tile-based accelerator architectures integrate increasing numbers of…
Fractal-IR: A Unified Framework for Efficient and Scalable Image Restoration
Yawei Li, Bin Ren, Jingyun Liang +5
While vision transformers achieve significant breakthroughs in various image restoration (IR) tasks, it is still challenging to efficiently scale them across multiple types of degr…
Towards Extreme Pruning of LLMs with Plug-and-Play Mixed Sparsity
Chi Xu, Gefei Zhang, Yantong Zhu +4
N:M structured pruning is essential for large language models (LLMs) because it can remove less important network weights and reduce the memory and computation requirements. Existi…
FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
Hang Guo, Yawei Li, Taolin Zhang +4
Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale s…
Q-MambaIR: Accurate Quantized Mamba for Efficient Image Restoration
Yujie Chen, Haotong Qin, Zhang Zhang +3
State-Space Models (SSMs) have attracted considerable attention in Image Restoration (IR) due to their ability to scale linearly sequence length while effectively capturing long-di…
CamSAM2: Segment Anything Accurately in Camouflaged Videos
Yuli Zhou, Yawei Li, Yuqian Fu +3
Video camouflaged object segmentation (VCOS), aiming at segmenting camouflaged objects that seamlessly blend into their environment, is a fundamental vision task with various real-…
Finetuning and Quantization of EEG-Based Foundational BioSignal Models on ECG and PPG Data for Blood Pressure Estimation
Bálint Tóth, Dominik Senti, Thorir Mar Ingolfsson +4
Blood pressure (BP) is a key indicator of cardiovascular health. As hypertension remains a global cause of morbidity and mortality, accurate, continuous, and non-invasive BP monito…
FEMBA: Efficient and Scalable EEG Analysis with a Bidirectional Mamba Foundation Model
Anna Tegon, Thorir Mar Ingolfsson, Xiaying Wang +2
Accurate and efficient electroencephalography (EEG) analysis is essential for detecting seizures and artifacts in long-term monitoring, with applications spanning hospital diagnost…