arXiv:2606. 17500v1 Announce Type: new Abstract: Transformer-based models achieve strong performance for jet tagging at the CERN LHC, but deploying them in low-latency, resource-constrained trigger systems is challenging.
Transformer-based models achieve strong performance for jet tagging at the CERN LHC, but deploying them in low-latency, resource-constrained trigger systems is challenging. We present an initial implementation of a quantized, integer-only transformer for jet tagging on the AMD Versal AI Engine (AIE), mapping dense and multi-head attention (MHA) layers to AIE tiles.
arXiv:2606. 31938v1 Announce Type: cross Abstract: Deploying Vision Transformer (ViT) models on edge platforms remains challenging due to their high computational demands and the architectural heterogeneity of modern hybrid ViT models, which incorporate both fully connected and convolutional layers.
arXiv:2606. 14813v1 Announce Type: cross Abstract: Jet tagging at the Large Hadron Collider increasingly relies on deep learning models trained on massive simulated datasets, leading to high computational costs and limited robustness to detector mismodeling.
arXiv:2601. 16622v2 Announce Type: replace-cross Abstract: Equivariant Graph Neural Networks (EGNNs) have become a widely used approach for modeling 3D atomistic systems.
arXiv:2606. 16825v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures efficiently scale Large Language Models (LLMs) by activating only a small fraction of their experts per token, yet the full parameter count - dominated by the expert parameters - must be held in training and inference memory.
arXiv:2609.39361v1 Announce Type: new Abstract: While most attention logits can be computed in low precision without degrading numerical stability, current attention kernels fail to exploit this phen...
arXiv:2607. 20501v1 Announce Type: new Abstract: Despite rapid progress in LLM-based code generation, writing correct and performant kernels for hardware accelerators remains a key bottleneck in scaling modern ML workloads.
arXiv:2606. 11117v1 Announce Type: cross Abstract: Designing FPGA-based accelerators for modern artificial intelligence workloads requires exploring a large and complex hardware design space that involves architectural parameters, data flow strategies, and memory hierarchies, making the process very time consuming.
arXiv:2604. 21254v3 Announce Type: replace Abstract: LLM architecture research generally aims to maximize model quality subject to fixed compute/latency budgets.
arXiv:2509. 16248v4 Announce Type: replace-cross Abstract: This paper presents GraphMend, a compiler technique that automatically fixes FX graph breaks in PyTorch 2 programs.
Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring months of specialized effort. Even with high-level synthesis (HLS), designers still need extensive hardware expertise to build high-performance accelerators.
The paper introduces a hardware‑aware framework that uses genetic programming to evolve layer‑specific scalar functions for Vision Transformers, replacing traditional LayerNorm with efficient, heterogeneous approximations. By applying a post‑training re‑alignment strategy, the method eliminates the need for full model retraining while achieving 90‑93% variance capture and recovering over 84% of ImageNet‑1K Top‑1 accuracy for ViT‑B and ViT‑L. The resulting architecture removes the global reduction bottleneck, reducing arithmetic complexity and off‑chip memory traffic, thereby enabling efficient deployment of ViTs on edge accelerators.