arXiv preprints from January 1, 2026 through September 23, 2026 — 09:00:03 EST
This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Network (GAN) to enhance communication for individuals with hearing impairments. Three specialized discriminators -- global, hand, and head -- each guide a corresponding expert branch in the...
Time-domain inverse design in photonics is known to be suitable for maximizing the efficiency of optical devices over broad frequency ranges. Objectives commonly used in this context include time-integrated field quantities derived from Poynting's theorem, such as energy, flux, or dissipated power, which can be directly linked to...
In this paper, we introduce the notion of a distinguished variety in the domain $\mathbfΘ_n$. One of the main results of the paper is a determinantal representation for every distinguished variety in $\mathbfΘ_n$. We also show that the closure of every distinguished variety is polynomially convex. Furthermore, we obtain a dilation and...
Rotation-based post-training quantisation commonly applies an orthogonal transform across an entire attention head to reduce outlier-induced error. RoPE instead partitions each head into two-dimensional frequency pairs, raising the question of whether a transform respecting this decomposition can improve on full-head mixing. Prior...
We investigate thermal photon emission from magnetized quark-gluon plasma (QGP) within (1+1)-dimensional relativistic magnetohydrodynamics (MHD), systematically incorporating magnetic susceptibility $χ_m$---encompassing both constant and lattice-QCD-derived temperature-dependent $χ_m(T)$ parametrizations---and weak-field quantum...
This study develops a weighted framework for measuring the discrepancy between two nonnegative lifetime distributions through cumulative past extropy. We propose two measures, referred to as the weighted cumulative past extropy inaccuracy (WCPEI) and the weighted cumulative past extropy Kullback-Leibler divergence (WCPED). The...
Dexterous manipulation promises substantially richer robot interaction with the physical world, but learning these behaviours remains constrained by the difficulty of collecting consistent, complete-task demonstrations. Unlike parallel-jaw manipulation, dexterous tasks require the operator to coordinate arm motion with precise,...
In quantum physics the order in which different operations occur can be placed in superposition. The resulting processes have an indefinite causal order and are both of fundamental interest and can be viewed as a novel quantum resource that enables a variety of new protocols. Here we report an experimental implementation of one such...
Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system. While an ideal harness system should align with human design priors and accumulate reusable experience through empirical exploration to drive recursive...
It is shown that, if an event $A$ has the same conditional probability in each trial in an infinite sequence of Bernoulli trials, then $A$ is independent of each trial. More general results are actually established.
Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the full evidence on which scientific discovery depends. Existing systems typically reason...
In holography, four-dimensional confining gauge theories are often modelled by five-dimensional Einstein--scalar gravity by choosing a specific form of the scalar potential. In a large class of non-conformal theories, we show that a predictive structure emerges for the thermal confinement transition by generalising the gravitational...
Latent video generation relies on autoencoders to define a compact space in which generative models operate. Although video autoencoder architectures have evolved substantially, their latent spaces are still optimized primarily for pixel-level reconstruction and provide limited high-level semantic organization. A...
Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos. Kinematic errors average per-frame pose differences but miss the physical artifacts that matter most, particularly unstable support and incorrect contacts such as foot skating and mistimed...
We study online probabilistic forecasting of binary outcomes chosen by an adaptive adversary. Given an online learning algorithm for a weak hypothesis class $H$, we would like to efficiently obtain two incomparable guarantees that existing online boosting techniques provide separately. Online gradient boosting competes in Brier score...
In 1986, Gromov asked whether every complete noncompact $n$-dimensional Riemannian manifold with nonnegative Ricci curvature and scalar curvature at least one satisfies: \[ \Vol_g (B(p, R))\le C_{n}R^{n-2} \] for all $p\in M$ and $R>0$. We answer this question affirmatively using the heat-kernel Fisher metric and Nash entropy.
Video world models simulate future states conditioned on current observations and user actions. Recent systems have demonstrated impressive video consistency and action controllability over long sequences. However, fairly comparing these interactive models remains challenging. In practice, a human player typically evaluates a world...
Let $μ$ be a positive Borel measure on $\C^n$. For every $0<p<\infty$, we prove that the Toeplitz operator $T_μ^{\mathrm{ph}}$ induced by $μ$ on pluriharmonic Fock space belongs to $\Sp_p$ if and only if $z\mapstoμ(B(z,r))$ belongs to $L^p(\C^n)$ for one, or equivalently every, $r>0$; this is also equivalent to Schatten membership of...
We prove that every PPT linear map has finite entanglement-breaking index, thereby establishing the eventual entanglement-breaking property of PPT channels in full generality. Furthermore, by utilizing completely positive maps with low entanglement dimensionality, we show that a large family of PPT maps, which strictly containing the...
The per-instance Jaccard score, or intersection over union (IoU), is standard in multi-label classification and binary segmentation. With $s$ labels, its loss matrix has $2^s$ outcomes and reports. Under the convention $\mathrm{Jac}(\varnothing,\varnothing)=1$, we prove that the Jaccard score, shifted-loss, and ordinary loss matrices...
The orbital angular momentum (OAM) of light is a discrete, unbounded degree of freedom that underpins mode-multiplexed communications and high-dimensional quantum photonics. Yet, dynamic OAM control remains dependent on bulky free-space optics or cascaded architectures that separate switching from wavefront shaping, hindering...
LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish command-generation errors from failures introduced after generation. QuoteBench measures this boundary with exact final-state validation on 56 one-shot tasks from 14...
Interactive world models must support persistent memory, responsive interaction, and long-horizon generation, yet these requirements place conflicting demands on the model. Maintaining history in the denoiser context or key-value cache incurs growing cost, forcing a trade-off between session length and retained memory, while...
Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to related content is hard to characterize. To address this challenge, we introduce LITTLECURRICULUM, a curated 88B-token pretraining corpus tailored to U.S. elementary...
Knutson and Tao's hives is a combinatorial model to compute Littlewood--Richardson coefficients. Similar to hives, Speyer introduced skeps and used them to prove a Schur log-concavity conjecture by Lam--Postnikov--Pylyavskyy. We first introduce skew hive and skew skep models, which specialize to both hives and skeps, and use this to...