arXiv:2510.05175v1 Announce Type: new Abstract: We present Fast Causal Attention (FCA), an algorithm that computes exact Causal Attention using 10% fewer operations. FCA accelerates a special class of matrix multiplications where either one operand or the output matrix is upper-…
arXiv:2504.14898v4 Announce Type: replace-cross Abstract: We address the problem of planning under uncertainty, where an agent must choose actions that not only achieve desired outcomes but also reduce uncertainty. Traditional methods often treat exploration and exploitation as separate objectives, lacking…
arXiv:2510.05176v1 Announce Type: new Abstract: KV cache in autoregressive LLMs eliminates redundant recomputation but has emerged as the dominant memory and bandwidth bottleneck during inference, notably with long contexts and test-time scaling. KV quantization is a key lever for reducing…
arXiv:2510.05178v1 Announce Type: new Abstract: Symbolic regression promises readable equations but struggles to encode unit-aware thresholds and conditional logic. We propose logistic-gated operators (LGO) — differentiable gates with learnable location and steepness — embedded as typed primitives and mapped back…
arXiv:2510.05829v1 Announce Type: cross Abstract: In this work, we present FoleyGRAM, a novel approach to video-to-audio generation that emphasizes semantic conditioning through the use of aligned multimodal encoders. Building on prior advancements in video-to-audio generation, FoleyGRAM leverages the Gramian Representation…
arXiv:2510.05180v1 Announce Type: new Abstract: In critical IoT environments, such as smart homes and industrial systems, effective Intrusion Detection Systems (IDS) are essential for ensuring security. However, developing robust IDS solutions remains a significant challenge. Traditional machine learning-based IDS models…
arXiv:2510.06105v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly shaping how information is created and disseminated, from companies using them to craft persuasive advertisements, to election campaigns optimizing messaging to gain votes, to social media influencers boosting engagement.…
arXiv:2510.05205v1 Announce Type: new Abstract: A common challenge in the natural sciences is to disentangle distinct, unknown sources from observations. Examples of this source separation task include deblending galaxies in a crowded field, distinguishing the activity of individual neurons from…
arXiv:2406.01899v3 Announce Type: replace Abstract: Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This ‘better with more’ phenomenon enables the effectiveness of large-scale pre-training on vast…
arXiv:2510.05218v1 Announce Type: new Abstract: Ensembles of neural network weight matrices are studied through the training process for the MNIST classification problem, testing the efficacy of matrix models for representing their distributions, under assumptions of Gaussianity and permutation-symmetry. The general…
