Publications

SkeleShare: Algorithmic Skeletons and Equality Saturation for Hardware Resource Sharing
Jonathan Van der Cruysse
Tzung-Han Juang
Shakiba Bolbolian Khah
Christophe Dubach
Compiling functional programs into efficient Field Programmable Gate Array (FPGA) designs is difficult. Hardware resources must be explicitl… (voir plus)y allocated and shared to maximize resource efficiency. This requires careful orchestration of several transformations to expose and exploit sharing opportunities.This paper introduces SkeleShare, a novel approach that automates the problem of resource allocation and sharing. It leverages equality saturation and algorithmic skeletons to expose sharing opportunities across abstraction levels. A solver-based extractor then selects a design that consolidates computations, meeting resource constraints while maintaining performance.This approach is evaluated on neural networks and image processing targeting a real FPGA. The paper shows how SkeleShare is used to express the various algorithmic patterns and transformation rules inherent in neural network operators. The experimental evaluation demonstrates that SkeleShare’s fully automated resource allocation and sharing matches and exceeds the performance of prior work, which involves expert manual extraction of sharing opportunities.
2026-01-30
IEEE/ACM Symposium on Code Generation and Optimization (publié)
doi.org
Synthesizing Specialized Sparse Tensor Accelerators for FPGAs via High-Level Functional Abstractions
Hamza Javed
Christophe Dubach
Sparsity is inherent in many applications such as machine learning and graph analytics. However, achieving high efficiency in sparse computa… (voir plus)tions requires specialized hardware accelerators like FPGAs, as traditional accelerators typically cater to dense data. While high level synthesis enables the automatic generation of FPGA-based accelerators, generic solutions produced via C-based synthesis flows often demand extensive development time, leading designers to prioritize broad applicability over fine-grained structural specialization. Consequently, these accelerators fail to fully exploit FPGA’s reconfigurablility, leaving substantial performance and efficiency gains untapped.This paper pushes the boundary by automatically generating specialized accelerators that match a given fixed sparse structure (e.g., in static graph analytics and pruned neural networks). It achieves this by leveraging functional abstractions within high level synthesis, an approach that has already proven effective in automating the generation of specialized dense tensor accelerator. Tensor shapes are encoded directly in the type system and specialized primitives for irregular data are introduced. Together, these innovations enable a concise specification of sparse accelerators and drive advanced optimizations—including dynamic partitioning and vector sharding—to produce hardware precisely tailored to the sparsity pattern of the underlying tensors.Compared to state-of-the-art generic accelerators (HiSparse, HiSpMV and GraphLily), the approach achieves up to a 2.8× improvement in bandwidth efficiency for sparse matrix computations and a 1.8× speedup on graph algorithms. Against the hls4ml neural network acceleration framework, it achieves up to a 1.8× improvement in throughput with a 4× reduction in resource usage, enabling scaling to larger networks. These results establish this approach as a flexible, powerful, and rapid solution for designing high-performance specialized sparse accelerators.
2026-01-30
IEEE/ACM Symposium on Code Generation and Optimization (publié)
doi.org
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization
Luca Della Libera
Yusuf Cem Sübakan
Mirco Ravanaelli
Neural audio codecs are at the core of modern conversational speech technologies, converting continuous speech into sequences of discrete to… (voir plus)kens that can be processed by LLMs. However, existing codecs typically operate at fixed frame rates, allocating tokens uniformly in time and producing unnecessarily long sequences. In this work, we introduce DyCAST, a Dynamic Character-Aligned Speech Tokenizer that enables variable-frame-rate tokenization through soft character-level alignment and explicit duration modeling. DyCAST learns to associate tokens with character-level linguistic units during training and supports alignment-free inference with direct control over token durations at decoding time. To improve speech resynthesis quality at low frame rates, we further introduce a retrieval-augmented decoding mechanism that enhances reconstruction fidelity without increasing bitrate. Experiments show that DyCAST achieves competitive speech resynthesis quality and downstream performance while using significantly fewer tokens than fixed-frame-rate codecs. Code and checkpoints will be released publicly at https://github.com/lucadellalib/dycast.
2026-01-29
ArXiv (prépublication)
arxiv.org
arxiv.org
Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models
Chen Liu
Xingzhi Sun
Xi Xiao
Alexandre Van Tassel
Ke Xu
Kristof Reimann
Danqi Liao
Mark B. Gerstein
Tianyang Wang
Xiao Wang
Smita Krishnaswamy
Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational… (voir plus) costs. To better understand LLM scaling, we study representational differences between LLMs and their smaller counterparts, with the goal of replicating the representational qualities of larger models in the smaller models. We observe a geometric phenomenon which we term
2026-01-29
ArXiv (prépublication)
arxiv.org
arxiv.org
Dual-Phase Continual Learning: Supervised Adaptation Meets Unsupervised Retention
Vaibhav Singh
Rahaf Aljundi
Eugene Belilovsky
Foundational vision-language models (VLMs) excel across diverse tasks, but adapting them to new domains without forgetting prior knowledge r… (voir plus)emains a critical challenge. Continual Learning (CL) addresses this challenge by enabling models to learn sequentially from new data while mitigating the forgetting of prior information, typically under supervised settings involving label shift. Nonetheless, abrupt distribution shifts can still cause substantial forgetting, potentially nullifying the benefits of supervised updates, especially when storing or replaying past data is infeasible. In this work, we propose leveraging unlabeled test-time data in an unsupervised manner to reinforce prior task performance without requiring replay or stored examples. Unlike traditional Test-Time Adaptation (TTA), which primarily focuses on domain shift or corruption, our method improves performance on earlier tasks by exploiting representative test samples encountered during deployment. We introduce a simple teacher-student framework with gradient-based sparse parameter updates, and show that it effectively mitigates forgetting in class-incremental CL for VLMs, offering a memory-free alternative to episodic replay with strong empirical results.
2026-01-29
Transactions on Machine Learning Research (accepté)
doi.org
openreview.net
Localized, High-resolution Geographic Representations with Slepian Functions
Arjun Rao
Ruth Crasto
Tessa Ooms
David Rolnick
Konstantin Klemmer
Marc Rußwurm
Geographic data is fundamentally local. Disease outbreaks cluster in population centers, ecological patterns emerge along coastlines, and ec… (voir plus)onomic activity concentrates within country borders. Machine learning models that encode geographic location, however, distribute representational capacity uniformly across the globe, struggling at the fine-grained resolutions that localized applications require. We propose a geographic location encoder built from spherical Slepian functions that concentrate representational capacity inside a region-of-interest and scale to high resolutions without extensive computational demands. For settings requiring global context, we present a hybrid Slepian-Spherical Harmonic encoder that efficiently bridges the tradeoff between local-global performance, while retaining desirable properties such as pole-safety and spherical-surface-distance preservation. Across five tasks spanning classification, regression, and image-augmented prediction, Slepian encodings outperform baselines and retain performance advantages across a wide range of neural network architectures.
2026-01-29
arXiv (prépublication)
doi.org
arxiv.org
Perplexity Cannot Always Tell Right from Wrong
Petar Veličković
Federico Barbero
Christos Perivolaropoulos
Simon Kayode Osindero
Razvan Pascanu
Perplexity -- a function measuring a model's overall level of"surprise"when encountering a particular output -- has gained significant tract… (voir plus)ion in recent years, both as a loss function and as a simple-to-compute metric of model quality. Prior studies have pointed out several limitations of perplexity, often from an empirical manner. Here we leverage recent results on Transformer continuity to show in a rigorous manner how perplexity may be an unsuitable metric for model selection. Specifically, we prove that, if there is any sequence that a compact decoder-only Transformer model predicts accurately and confidently -- a necessary pre-requisite for strong generalisation -- it must imply existence of another sequence with very low perplexity, but not predicted correctly by that same model. Further, by analytically studying iso-perplexity plots, we find that perplexity will not always select for the more accurate model -- rather, any increase in model confidence must be accompanied by a commensurate rise in accuracy for the new model to be selected.
2026-01-29
ArXiv (prépublication)
arxiv.org
arxiv.org
Secure Tool Manifest and Digital Signing Solution for Verifiable MCP and LLM Pipelines
Saeid Jamshidi
Kawser Wazed Nafi
Arghavan Moradi Dakhel
Foutse Khomh
Amin Nikanjam
Mohammad Hamdaqa
2026-01-29
ArXiv (prépublication)
arxiv.org
arxiv.org
Securing Time in Energy IoT: A Clock-Dynamics-Aware Spatio-Temporal Graph Attention Network for Clock Drift Attacks and Y2K38 Failures
Saeid Jamshidi
Omar Abdel Wahab
Rolando Herrero
Foutse Khomh
The integrity of time in distributed Internet of Things (IoT) devices is crucial for reliable operation in energy cyber-physical systems, su… (voir plus)ch as smart grids and microgrids. However, IoT systems are vulnerable to clock drift, time-synchronization manipulation, and timestamp discontinuities, such as the Year 2038 (Y2K38) Unix overflow, all of which disrupt temporal ordering. Conventional anomaly-detection models, which assume reliable timestamps, fail to capture temporal inconsistencies. This paper introduces STGAT (Spatio-Temporal Graph Attention Network), a framework that models both temporal distortion and inter-device consistency in energy IoT systems. STGAT combines drift-aware temporal embeddings and temporal self-attention to capture corrupted time evolution at individual devices, and uses graph attention to model spatial propagation of timing errors. A curvature-regularized latent representation geometrically separates normal clock evolution from anomalies caused by drift, synchronization offsets, and overflow events. Experimental results on energy IoT telemetry with controlled timing perturbations show that STGAT achieves 95.7% accuracy, outperforming recurrent, transformer, and graph-based baselines with significant improvements (d>1.8, p0.001). Additionally, STGAT reduces detection delay by 26%, achieving a 2.3-time-step delay while maintaining stable performance under over
2026-01-29
ArXiv (prépublication)
arxiv.org
arxiv.org
Tri-LLM Cooperative Federated Zero-Shot Intrusion Detection with Semantic Disagreement and Trust-Aware Aggregation
Saeid Jamshidi
Omar Abdel Wahab
Foutse Khomh
Kawser Wazed Nafi
Federated learning (FL) has become an effective paradigm for privacy-preserving, distributed Intrusion Detection Systems (IDS) in cyber-phys… (voir plus)ical and Internet of Things (IoT) networks, where centralized data aggregation is often infeasible due to privacy and bandwidth constraints. Despite its advantages, most existing FL-based IDS assume closed-set learning and lack mechanisms such as uncertainty estimation, semantic generalization, and explicit modeling of epistemic ambiguity in zero-day attack scenarios. Additionally, robustness to heterogeneous and unreliable clients remains a challenge in practical applications. This paper introduces a semantics-driven federated IDS framework that incorporates language-derived semantic supervision into federated optimization, enabling open-set and zero-shot intrusion detection for previously unseen attack behaviors. The approach constructs semantic attack prototypes using a Tri-LLM ensemble of GPT-4o, DeepSeek-V3, and LLaMA-3-8B, aligning distributed telemetry features with high-level attack concepts. Inter-LLM semantic disagreement is modeled as epistemic uncertainty for zero-day risk estimation, while a trust-aware aggregation mechanism dynamically weights client updates based on reliability. Experimental results show stable semantic alignment across heterogeneous clients and consistent convergence. The framework achieves over 80% zero-shot detection accuracy on unseen attack patterns, improving zero-day discrimination by more than 10% compared to similarity-based baselines, while maintaining low aggregation instability in the presence of unreliable or compromised clients.
2026-01-29
ArXiv (prépublication)
arxiv.org
arxiv.org
Boosting CVaR Policy Optimization with Quantile Gradients
Yudong Luo
Erick Delage
Optimizing Conditional Value-at-risk (CVaR) using policy gradient (a.k.a CVaR-PG) faces significant challenges of sample inefficiency. This … (voir plus)inefficiency stems from the fact that it focuses on tail-end performance and overlooks many sampled trajectories. We address this problem by augmenting CVaR with an expected quantile term. Quantile optimization admits a dynamic programming formulation that leverages all sampled data, thus improves sample efficiency. This does not alter the CVaR objective since CVaR corresponds to the expectation of quantile over the tail. Empirical results in domains with verifiable risk-averse behavior show that our algorithm within the Markovian policy class substantially improves upon CVaR-PG and consistently outperforms other existing methods.
2026-01-28
arXiv (prépublication)
doi.org
arxiv.org
CNeuroMod-THINGS, a densely-sampled fMRI dataset for visual neuroscience
Marie St-Laurent
Basile Pinsard
Oliver Contier
Elizabeth DuPre
Katja Seeliger
Valentina Borghesani
Julie A. Boyle
Lune Bellec
Martin N. Hebart
Data-hungry neuro-AI modelling requires ever larger neuroimaging datasets. CNeuroMod-THINGS meets this need by capturing neural representati… (voir plus)ons for a wide set of semantic concepts using well-characterized images in a new densely-sampled, large-scale fMRI dataset. Importantly, CNeuroMod-THINGS exploits synergies between two existing projects: the THINGS initiative (THINGS) and the Courtois Project on Neural Modelling (CNeuroMod). THINGS has developed a common set of thoroughly annotated images broadly sampling natural and man-made objects which is used to acquire a growing collection of multimodal neural responses. Meanwhile, CNeuroMod is acquiring hundreds of hours of fMRI data from a core set of participants during controlled and naturalistic tasks, including visual tasks like movie watching and videogame playing. For CNeuroMod-THINGS, four CNeuroMod participants each completed 33-36 sessions of a continuous recognition paradigm using 4320 images from the THINGS stimulus set spanning 720 categories. We report behavioural and neuroimaging metrics that showcase the quality of the data. By bridging together large existing resources, CNeuroMod-THINGS expands our capacity to model human vision in controlled and naturalistic settings.
2026-01-28
Scientific Data (publié)
doi.org
arxiv.org