arXiv:2605.05148v1 Announce Type: cross Abstract: One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet practical image codec is yet to be proposed. In this work, we aim to close […]
Geometry-Aware State Space Model: A New Paradigm for Whole-Slide Image Representation
arXiv:2605.05164v1 Announce Type: cross Abstract: Accurate analysis of histopathological images is critical for disease diagnosis and treatment planning. Whole-slide images (WSIs), which digitize tissue specimens at gigapixel resolution, are fundamental to this process but require aggregating thousands of patches for slide-level predictions. Multiple Instance Learning (MIL) tackles this challenge with a two-stage paradigm, decoupling tile-level […]
Almost-Orthogonality in Lp Spaces: A Case Study with Grok
arXiv:2605.05192v1 Announce Type: cross Abstract: Carbery proposed the following sharpened form of triangle inequality for many functions: for any $pge 2$ and any finite sequence $(f_j)_jsubset L^p$ we have [ Big|sum_j f_jBig|_p le left(sup_j sum_k alpha_jk^,cright)^1/p’ Big(sum_j |f_j|_p^pBig)^1/p, ] where $c=2$, $1/p+1/p’=1$, and $alpha_jk=sqrtfracf_jf_k\$. In the first part of this paper we construct a counterexample […]
n:m Phase-Locking of Coupled Oscillators with Nonlinearities in Coupling Strength and Heterogeneity
arXiv:2409.14566v4 Announce Type: replace Abstract: We introduce a scalar reduction method for forced or coupled systems with nonlinearities in both heterogeneity and coupling strength. Heterogeneity is formulated as a relatively weak but nonlinear alteration of the vector field(s). The method can be used to determine the existence and stability of $n:m$ phase-locked states in a […]
Manifold of Failure: Behavioral Attraction Basins in Language Models
arXiv:2602.22291v3 Announce Type: replace-cross Abstract: While prior work has focused on projecting adversarial examples back onto the manifold of natural data to restore safety, we argue that a comprehensive understanding of AI safety requires characterizing the unsafe regions themselves. This paper introduces a framework for systematically mapping the Manifold of Failure in Large Language Models […]
Layerwise LQR for Geometry-Aware Optimization of Deep Networks
arXiv:2605.04230v1 Announce Type: cross Abstract: Geometry-aware optimizers such as Newton and natural gradient can improve conditioning in deep learning, but scalable variants such as K-FAC, Shampoo, and related preconditioners usually impose structural approximations early, often discarding cross-layer interactions induced by the network computation. We introduce Layerwise LQR (LLQR), a framework for learning structured inverse preconditioners […]
A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers
arXiv:2605.04074v1 Announce Type: cross Abstract: AI data centers experience rapid fluctuations in power demand due to the heterogeneity of computational tasks that they have to support. For example, the power profile of inference and training of large language models (LLMs) is quite distinct and big divergences can result in the instability of the underlying electricity […]
Toward Human-AI Complementarity Across Diverse Tasks
arXiv:2605.04070v1 Announce Type: cross Abstract: Human-AI complementarity, the idea that combining human and AI judgments can outperform either alone, offers a promising pathway toward robust oversight of advanced AI systems. However, whether human-AI complementarity can be achieved on realistic tasks remains an open question. We investigate this through two approaches: hybridization and two AI assistance […]
Learning Reconstructive Embeddings in Reproducing Kernel Hilbert Spaces via the Representer Theorem
arXiv:2601.05811v1 Announce Type: cross Abstract: Motivated by the growing interest in representation learning approaches that uncover the latent structure of high-dimensional data, this work proposes new algorithms for reconstruction-based manifold learning within Reproducing-Kernel Hilbert Spaces (RKHS). Each observation is first reconstructed as a linear combination of the other samples in the RKHS, by optimizing a […]
Transformation Categorization Based on Group Decomposition Theory Using Parameter Division
arXiv:2605.04056v1 Announce Type: cross Abstract: Representation learning seeks meaningful sensory representations without supervision and can model aspects of human development. Although many neural networks empirically learn useful features, a principled account of what makes a representation “good” remains elusive. We study unsupervised categorization of transformations between pairs of inputs under algebraic constraints. Classical disentanglement favors […]
Analogy between Boltzmann machines and Feynman path integrals
arXiv:2301.06217v1 Announce Type: cross Abstract: We provide a detailed exposition of the connections between Boltzmann machines commonly utilized in machine learning problems and the ideas already well known in quantum statistical mechanics through Feynman’s description of the same. We find that this equivalence allows the interpretation that the hidden layers in Boltzmann machines and other […]
Modeling Subjective Urban Perception with Human Gaze
arXiv:2605.00764v1 Announce Type: cross Abstract: Urban perception describes how people subjectively evaluate urban environments, shaping how cities are experienced and understood. Existing computational approaches primarily model urban perception directly from street view images, but largely ignore the human perceptual process through which such judgments are formed. In this paper, we introduce Place Pulse-Gaze, an urban […]