arXiv:2608.01434v1 Announce Type: cross Abstract: Normally the statistical mechanics of learning treats constraints on weight distributions as restrictions that shrink the space of possible solutions. Therefore,…
arXiv:2608.04288v1 Announce Type: cross Abstract: Calibration requires a predictor to be unbiased after conditioning on its own predictions. Multicalibration asks for this guarantee simultaneously across a…
arXiv:2608.04254v1 Announce Type: cross Abstract: Longitudinal prediction of Alzheimer's disease biomarkers increasingly informs clinical decisions, and a forecast is only useful if it also reports how…
arXiv:2511.11413v2 Announce Type: replace-cross Abstract: Consider the problem of finding the best matching in a weighted graph where we only have access to predictions of the…
arXiv:2502.09151v3 Announce Type: replace-cross Abstract: Diffusion models are one of the key architectures of generative AI. Their main drawback, however, is the computational costs. This study…
arXiv:2608.04667v1 Announce Type: new Abstract: Selective inference (SI) provides statistically valid $p$-values for hypotheses selected by applying an algorithm to the data, correcting for the bias…
arXiv:2605.24212v2 Announce Type: replace-cross Abstract: Deploying clinical prediction models across healthcare systems often fails when key training covariates are unavailable at deployment and labeled outcomes are…
arXiv:2511.09002v3 Announce Type: replace Abstract: Self-consuming generative models have received significant attention over the last few years. In this paper, we study a self-consuming generative model…
arXiv:2405.18220v4 Announce Type: replace Abstract: Tensor-based discrete density estimation requires flexible modeling and proper divergence criteria to enable effective learning; however, traditional approaches using $alpha$-divergence face…
arXiv:2608.04507v1 Announce Type: cross Abstract: Can cooperation among large language model (LLM) agents be evolutionarily stable against free-rider invasion? We study an indirect reciprocity donation game…
arXiv:2608.04451v1 Announce Type: cross Abstract: We give a negative solution to MAIS-O60. We first construct an example in which an initially active ReLU neuron becomes completely…
arXiv:2608.04582v1 Announce Type: cross Abstract: We present a unified theoretical framework connecting classical universal approximation theory, Fourier-feature approximation, and diffractive optical processors. We show that phase-encoded…
arXiv:2604.08324v4 Announce Type: replace Abstract: Symbolic regression (SR) aims to discover mathematical expressions from data, a task traditionally tackled using Genetic Programming (GP) through combinatorial search…
arXiv:2608.04075v1 Announce Type: new Abstract: Accurate traffic forecasting is essential for proactive resource management in edge computing, where service demand evolves dynamically across both space and…
arXiv:2603.23878v3 Announce Type: replace Abstract: The parameterized CROWN analysis, a.k.a., alpha-CROWN has emerged as a practically successful abstract interpretation method for neural network verification. However, existing…
arXiv:2608.04074v1 Announce Type: new Abstract: Long-context LLM decoding reads the key-value (KV) cache at every step. Loading it takes longer than computing attention over it, so…
arXiv:2510.09764v2 Announce Type: replace Abstract: Modeling multi-modal time-series data is critical for capturing system-level dynamics, particularly in biosignals where modalities such as ECG, PPG, EDA, and…
arXiv:2608.04060v1 Announce Type: new Abstract: Joint-embedding predictive architectures learn abstract states by predicting target embeddings from context embeddings, but their transition models are typically opaque neural…
arXiv:2608.05115v1 Announce Type: cross Abstract: Can computer vision help make classrooms safer? In this pilot study, we investigate privacy-aware and computationally efficient classroom incident recognition from…
arXiv:2608.04057v1 Announce Type: new Abstract: Top-$k$ selection determines which components of a sparse model remain active. Hard selection blocks gradients, while continuous relaxations often couple mask…
arXiv:2608.04893v1 Announce Type: cross Abstract: Multi-agent LLM systems relay key--value caches instead of text and credit their gains to exchanged ``latent thoughts''. That credit is a…
arXiv:2608.04051v1 Announce Type: new Abstract: Real-world time series are often governed by recurring patterns, but their dominant periods may vary across datasets, forecasting settings, and individual…
arXiv:2605.28566v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, yet their standard generation process -- auto-regressive token prediction -- is inherently…
arXiv:2608.04048v1 Announce Type: new Abstract: Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput. However, conventional quantization…