Watching AI evolve.
Understanding what comes next.
New papers, new methods and questions worth exploring.
Channel RSS ↗Treat a paper as a claim to examine: identify the task, test data, baseline and failure cases. A preprint is not the same as peer-reviewed evidence, and a benchmark improvement may not transfer to your setting.
arXiv:2610.19058v1 Announce Type: new Abstract: Compartment models of infectious diseases are often linear in coefficients that are physical parameters or products or ratios of them. We exploit this with closed-form least squares and equip the estimates with distribution-free uncertainty.
arXiv:2610.18945v1 Announce Type: new Abstract: Amortized Bayesian inference uses simulations to perform Bayesian estimation when likelihoods are expensive or analytically unavailable. However, learning the full joint posterior is challenging in high-dimensional models with complex dependencies.
A new study on agent training explores integrating self-improvement processes into native operating environments.
arXiv:2610.18935v1 Announce Type: new Abstract: We study PAC learning of binary classifiers when labels arrive after random delays and are censored beyond an observation window $W$. How many samples does this observation model require? We propose a distribution-dependent answer, the Delay Complexity Dimension (DCD). The DCD combines the VC dimension with the exact label-information rate of the observation channel.
arXiv:2610.19003v1 Announce Type: new Abstract: Abstractive summarization remains challenging across languages, where linguistic quality and factual consistency may diverge, particularly in low-resource settings. We present a standardized zero-shot benchmark of eight closed-source and open-weight LLMs on size-matched English and Bengali XL-Sum test sets.
arXiv:2606.11245v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, raising expectations for Artificial General Intelligence (AGI). This position paper argues that integrating explicit memory is the cornerstone for advancing LLMs toward AGI.
arXiv:2610.18879v1 Announce Type: new Abstract: Protein function annotation operates over an expanding label space, making class-incremental learning (CIL) a natural framework for incorporating newly discovered functions without full retraining. Yet existing CIL methods have been developed largely in vision and have not been systematically evaluated over frozen protein representations.
arXiv:2610.19220v1 Announce Type: cross Abstract: The Continuous Thought Machine (CTM) is a recurrent network that attends to inputs and makes predictions based on the synchronization between its neurons. On tasks spanning many domains, it displays emergent thought processes that have not been explained. We report a number of findings about how the CTM classifies images, focusing on ImageNet.
arXiv:2610.14149v1 Announce Type: new Abstract: VETNET represents an ecosystem of live benchmark datasets and evaluation frameworks designed to accelerate AI-driven innovation in animal science and veterinary medicine through standardized, high-quality datasets and multi-institutional collaboration across academic and non-academic sectors.
arXiv:2610.18939v1 Announce Type: new Abstract: This paper studies Wong--Zakai convergence and Fourier neural operator learning for stochastic Volterra integral equations (SVIEs) describing random systems with memory. A Wong--Zakai theorem establishes convergence of pathwise solutions driven by piecewise linear approximations of Brownian motion to the corresponding SVIE solution.
arXiv:2610.18880v1 Announce Type: new Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A difficult case arises when both genes in a test pair were seen individually during training, but their combination was not.