arXiv:2509.19633v1 Announce Type: cross Abstract: The quadratic complexity of the attention mechanism in Transformer models has motivated the development of alternative architectures with sub-quadratic scaling, such as state-space models. Among these, Mamba has emerged as a leading architecture, achieving state-of-the-art…
arXiv:2006.14061v4 Announce Type: replace-cross Abstract: We consider the problem of optimizing a vector-valued objective function $boldsymbol{f}$ sampled from a Gaussian Process (GP) whose index set is a well-behaved, compact metric space $({cal X},d)$ of designs. We assume that $boldsymbol{f}$ is…
arXiv:2509.19710v1 Announce Type: cross Abstract: The advent of Scientific Machine Learning has heralded a transformative era in scientific discovery, driving progress across diverse domains. Central to this progress is uncovering scientific laws from experimental data through symbolic regression. However, existing…
arXiv:2502.01512v4 Announce Type: replace-cross Abstract: Circular and non-flat data distributions are prevalent across diverse domains of data science, yet their specific geometric structures often remain underutilized in machine learning frameworks. A principled approach to accounting for the underlying geometry of…
arXiv:2509.19830v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) offer a structured and interpretable framework for multivariate function approximation by composing univariate transformations through additive or multiplicative aggregation. This paper establishes theoretical convergence guarantees for KANs when the univariate components are…
arXiv:2509.19455v1 Announce Type: new Abstract: Standard first-order Langevin algorithms such as the unadjusted Langevin algorithm (ULA) are obtained by discretizing the Langevin diffusion and are widely used for sampling in machine learning because they scale to high dimensions and large…
Honor has revealed the design of its upcoming Magic 8 Pro flagship in a selection of images shared exclusively with The Verge, confirming that the phone will include a dedicated AI button. When the Magic 8 series launches in China…
“The Supreme Court is Google’s last hope to avoid an Epic reckoning in October,” I wrote last week. Google apparently agrees. Today, it’s finally elevated its Epic v. Google case, the one that might fracture its control over the entire…
Most RAG failures originate at retrieval, not generation. Text-first pipelines lose layout semantics, table structure, and figure grounding during PDF→text conversion, degrading recall and precision before an LLM ever runs. Vision-RAG—retrieving rendered pages with vision-language embeddings—directly targets this bottleneck and…
Self-supervised learning (SSL) has made significant advances in speech representation learning. Models like wav2vec 2.0 and HuBERT have achieved state-of-the-art results in tasks such as speech recognition, particularly in monolingual settings. However, multilingual SSL models tend to underperform their monolingual…
