arXiv preprints from January 1, 2026 through July 21, 2026 — 17:39:33 EST
Long-term persona agents must remain identifiable while adapting to new events, relationships, evidence, and social conditions. We identify self-locking as a runtime failure mode in continuing persona-life loops: locally plausible events keep appearing while the generated life collapses toward familiar environments, weak...
In this paper, we establish an analogue of the Kővari-Sós-Turán Theorem for $\operatorname{GF}(q)$-representable matroids. For $2\leq s\leq t$, we show that if $M$ is a rank-$n$ simple $\operatorname{GF}(q)$-representable matroid having no $M(K_{s,t})$-restriction, then \[ |E(M)|=O_{q,s,t}\bigl(q^{(1-1/s)n}\bigr). \] In particular,...
An LLM-as-judge score can move even when the candidate responses stay fixed, simply because the evaluator has changed. We treat this evaluator-replacement ambiguity as a measurement-validity problem. Across four judgment datasets, we compare two upgrade paths available in practice: scaling Qwen3 dense judges from 1.7B to 32B...
This paper introduces Actor as Its Own Critic, a unified reinforcement learning framework, Cycle Group Relative Policy Optimization (CycleGRPO), that jointly optimizes region understanding and localization for Multimodal Large Language Models (MLLMs). Unlike existing separate pipelines, we leverage the inherent duality between the two...
Few-shot spheroid segmentation must adapt to new cell lines, microscopes, and illumination conditions from only a small set of annotated images. While foundation few-shot segmenters can be accurate, their large opaque backbones make it difficult to understand which visual cues drive success or failure. We study this question with...
The minimum spanning tree (MST) problem is one of the most basic optimization problems on metric spaces and graphs. We study the problem of computing a $(1+ε)$-approximation to the MST of an $n$-point metric space $(X, \mathbf{d})$ of doubling dimension $\mathrm{ddim}$. In doubling metrics, previous deterministic algorithms incur a...
Inversion sets of permutations in the affine symmetric group $\widetilde{S}_n$ were studied extensively by Björner and Brenti. One of their methods for encoding an inversion set is through an affine inversion graph, which is a certain weighted graph on vertex set $[n]=\{1,2,\ldots,n\}$. Subsequent work by Papi characterized which...
A formula of the modal mu-calculus enjoys finite convergence on a structure if there is some finite unfolding of the formula that defines the same set. A structure enjoys finite convergence if all formulas of the mu-calculus enjoy finite convergence on said structure. It is known that there are words that are not ultimately periodic,...
We continue the study of $D(z)$-quadruples in the ring $\mathbb{Z}[\sqrt{-2}]$. Motivated by the earlier classification due to the authors and by the subsequent partial results for the remaining families, we consider the exceptional congruence classes arising in the forms $24a+5+(12b+6)\sqrt{-2}$, $24a+2+(12b+6)\sqrt{-2}$, and...
Central to machine learning and signal processing is the ability to perform universal function approximation and learn complex input-output relationships from limited numbers of observations. Multivariate polynomial models offer a natural way to express such relationships through multiplicative feature interactions, but their...
The Hubble tension has reached a nominal significance above $7σ$, while new high-precision measurements of the cosmic microwave background (CMB) and baryon acoustic oscillations (BAO) sharpen the test of proposed solutions. Using a common framework, we compare fourteen representative alternatives to the standard $Λ$ Cold Dark Matter...
The integration of power converters is profoundly changing the power system dynamics and poses significant challenges for stability analysis. The dynamic interactions between the power grid and the heterogeneous converters are highly complex and difficult to analyze due to the curse of dimensionality. Moreover, system stability varies...
Quantum Neural Networks (QNNs) have emerged as a promising paradigm for quantum machine learning in the Noisy Intermediate-Scale Quantum (NISQ) era, leveraging quantum phenomena such as superposition and entanglement to process information in exponentially large Hilbert spaces. However, QNNs inherit critical security vulnerabilities...
Product data scientists often ask LLM-based agents to help with recurring execution tasks such as cleaning data, writing SQL, choosing statistical tests, and formatting results. Reusable skill files are meant to avoid prompting from scratch by packaging guidance for a task family. Expert-written skills can encode high-quality...
Reconstructing the location and shape of an unknown impenetrable scatterer from far-field measurements is a fundamental inverse problem in elastic scattering. In this paper, we propose monotonicity-based shape characterization theorems and develop corresponding algorithms for rigid and traction-free impenetrable scatterers. By...
Collisions of ultra-relativistic bubbles during cosmological phase transitions can produce particles much heavier than the transition scale. Previous analyses modelled this process as the off-shell decay of the scalar background. We show that its results parametrically overestimate hard particle production and depend on the gauge...
Video models are evolving into vision foundation models, yet they still lack human-like multi-step reasoning. Streaming autoregressive diffusion models are efficient but limited in reasoning, while bidirectional diffusion enables global revision with high inference costs due to dense frame-level denoising. Both paradigms struggle to...
In-context learning is commonly interpreted as a form of conditional inference, in which the prompt specifies a context and the model's output is treated as an estimate of the corresponding conditional distribution. If this interpretation holds, then LLM estimates should satisfy basic probabilistic identities. In particular, the law...
Deep thermalisation characterises the emergence of universal quantum state ensembles on subsystems due to projective measurements on their complement. We study the notion of locality, or lack thereof, in this phenomenon by considering a subsystem partitioned into two disjoint subregions which remain causally disconnected at all times...
Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state-of-the-art policies, without growing inference latency. At this...
We propose an unconventional metallic phase emerging on doping the $1/3$ Fractional Chern insulator, which can serve as a parent state to anyon superconductivity with arbitrary chiral central charge. It is a twisted $\mathbb{Z}_3$ orthogonal metal: a state with vanishing electron quasiparticle weight but a single well-defined Fermi...
MeanFlow generators achieve fast few-step sampling by predicting average velocities over time intervals, making them attractive for efficient generation. Reinforcement learning (RL) has become a powerful way to align diffusion and flow models with human preferences and task-specific objectives. In particular, DiffusionNFT offers an...
Editing the figures in a research paper is a routine and time-consuming part of everyday research practice: authors relabel components, rearrange panels, and restyle visuals as they revise their manuscripts. Automating this editing workflow under a natural-language instruction, however, is challenging, because a scientific figure is a...
Online novel view synthesis from multi-view streaming videos faces a fundamental trade-off: maintaining a persistent, long-horizon memory to reconstruct temporarily occluded regions while operating under strict real-time constraints. While Test-Time Training (TTT) offers a powerful memory mechanism, standard models mandate...
The snake-in-the-box problem, introduced by Kautz in 1958, asks for the longest induced (chordless) path, called a snake, in the hypercube graph $Q_n$. The maximum length $a(n)$ is known in each dimension $n \leq 8$. We give snakes that are longer than the previous best-known in every dimension from $9$ to $13$, improving the lower...