arXiv:2510.14871v1 Announce Type: cross Abstract: General-purpose compilers abstract away parallelism, locality, and synchronization, limiting their effectiveness on modern spatial architectures. As modern computing architectures increasingly rely on fine-grained control over data movement, execution order, and compute placement for performance, compiler…
arXiv:2510.13999v1 Announce Type: new Abstract: Sparsely-activated Mixture-of-Experts (SMoE) models offer efficient pre-training and low latency but their large parameter counts create significant memory overhead, motivating research into expert compression. Contrary to recent findings favouring expert merging on discriminative benchmarks, we…
arXiv:2510.14968v1 Announce Type: cross Abstract: To tackle long-horizon tasks, recent hierarchical vision-language-action (VLAs) frameworks employ vision-language model (VLM)-based planners to decompose complex manipulation tasks into simpler sub-tasks that low-level visuomotor policies can easily handle. Typically, the VLM planner is finetuned…
arXiv:2510.14007v1 Announce Type: new Abstract: Clifford-Steerable CNNs (CSCNNs) provide a unified framework that allows incorporating equivariance to arbitrary pseudo-Euclidean groups, including isometries of Euclidean space and Minkowski spacetime. In this work, we demonstrate that the kernel basis of CSCNNs is…
arXiv:2501.12706v2 Announce Type: replace Abstract: Explainable Artificial Intelligence (XAI) techniques hold significant potential for enhancing the causal discovery process, which is crucial for understanding complex systems in areas like healthcare, economics, and artificial intelligence. However, no causal discovery methods currently…
arXiv:2510.14009v1 Announce Type: new Abstract: Geometry-aware optimization algorithms, such as Muon, have achieved remarkable success in training deep neural networks (DNNs). These methods leverage the underlying geometry of DNNs by selecting appropriate norms for different layers and updating parameters via…
arXiv:2506.00799v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has become the de facto parameter-efficient fine-tuning (PEFT) method for large language models (LLMs) by constraining weight updates to low-rank matrices. Recent works such as Tied-LoRA, VeRA, and VB-LoRA push efficiency further…
arXiv:2510.14027v1 Announce Type: new Abstract: Transformers, powered by the attention mechanism, are the backbone of most foundation models, yet they suffer from quadratic complexity and difficulties in dealing with long-range dependencies in the input sequence. Recent work has shown that…
arXiv:2509.00102v2 Announce Type: replace Abstract: Transformer-based foundation models for Electrocardiograms (ECGs) have recently achieved impressive performance in many downstream applications.
arXiv:2510.14049v1 Announce Type: new Abstract: Causal Representation Learning (CRL) aims to uncover the data-generating process and identify the underlying causal variables and relations, whose evaluation remains inherently challenging due to the requirement of known ground-truth causal variables and causal structure.…
