Trending
Enterprises are moving toward autonomous cyber defense: agentic AI that builds situational awareness of an organization's security state and reasons from it to assessments, decisions, and actions. This rests on a holistic view of the…
Reasoning and planning over Dynamic Knowledge Graphs (DKGs) present significant challenges, especially in open-world environments with incomplete information. Existing action formalisms often face decidability issues and the Ramification…
Automated classification of pulmonary disease from chest radiographs is a widely studied application of machine learning in medical imaging. This paper presents a pilot study evaluating classical texture- and gradient-based feature…
Analytical solutions encompassing the so-called Hubble tension problem are revisited through the framework of Weyl--Wigner quantum mechanics and discussed in the context of generalized phase-space scenarios of quantum cosmology. After…
For graphs \(G\) and \(H\), let \(N(G,H)\) be the number of unlabeled, not necessarily induced copies of \(H\) in \(G\), and let \(f(n,H)\) be the maximum of \(N(G,H)\) over all \(n\)-vertex planar graphs \(G\). Ghosh, Gy\H{o}ri, Martin,…
Long-horizon benchmarks often show that agents fail more as tasks become longer. This observation is useful for deployment, but it does not by itself explain why failure occurs. More stages create more opportunities for ordinary errors to…
We study the estimates for the number of exceptions to the representation of integers as the sum of at most two prime numbers. Most of this article is a survey that gives an overview of existing results. We begin with the legendary…
A capability appears in a language model when the last parts of its circuit align in one stochastic attempt, and getting all but one right is worth nothing. We show this no-partial-credit joint alignment is the rate-limiting step of…
Robust Optimization Over Time (ROOT) is a recent branch of evolutionary dynamic optimization that seeks solutions capable of remaining effective across multiple consecutive environments. Unlike the traditional track-the-moving-optimum (TMO)…
Exponentials of (real/complex) vector fields are classically defined via the vector field integration. Take a k-algebra k[x] \subset R\subset k[[x]], where k\supseteq \Q is a local domain. Suppose a derivation \xi is x-adically nilpotent.…
Open-vocabulary Earth observation (EO) aims to localize geospatial concepts specified in natural language rather than a fixed label set. Existing benchmarks, however, usually cover narrow category vocabularies or limited query forms. To…
In a hedonic game, agents need to be partitioned into coalitions, and have a preference order over partitions. A partition is called strongly popular if it beats any other partition in a majority vote among the agents. We focus on the…
A study of the production of the Higgs boson in association with either a top-quark pair ($t\bar{t}H$) or a single top quark ($tH$) in the $\tau$-lepton-pair decay channel is presented. The analysis relies on final states featuring fully…
Post-training quantization to 4-bit weights is widely reported to be nearly lossless. We test this claim for multi-turn, tool-calling agents, where it now matters most. On $\tau^2$-bench, across two open-weight model families in dense and…
EEG-based disease diagnosis requires one prediction per subject, yet common pipelines segment recordings into short instances, inherit the subject label for every instance, and train instance-level classifiers. This assumes that all…
Post-training of large language models is expensive, and existing efficiency improvements mainly focus on selecting informative samples or designing training schedules. However, data organization itself is usually treated as a static…
We introduce the class $\mathscr{P}_{\mathcal{H}_n^0}(\alpha)$ $(0\leq \alpha<1)$ of normalized pluriharmonic mappings in the setting of several complex variables. This class extends the harmonic family…
Code models are increasingly trained with execution feedback, but most training signals still stop at correctness. This leaves an important gap for systems code: two programs can pass the same tests while differing greatly in runtime. We…
Formalizing compiler-aware numerical correctness requires distinguishing what an observed floating-point difference means, what compiler behavior the evidence supports, and what numerical consequence follows. Existing testing workflows…
Multi-head latent attention (MLA) is increasingly important for long-context LLM inference because compact latent states replace the growing key-value (KV) cache and reduce decoding memory traffic. Yet most capable open checkpoints use…