Papers

This dissertation presents a scalable architecture for transforming unstructured, domain-specific text into structured knowledge for retrieval and reasoning. It integrates semi-automatic corpus curation, semantic structuring, retrieval, and inference into an interpretable pipeline. The research introduces Binary Bleed, an adapted binary search method that reduces low-rank search complexity for Non-negative Matrix Factorization (NMF), and Hierarchical NMF with automatic latent feature selection (HNMFk), a depth-adaptive topic modeling method that produces interpretable taxonomies guided by subject matter experts. These representations populate a typed Knowledge Graph and a semantically aligned Vector Store containing extracted latent features, synchronized through an event-driven substrate. Tensor-Structured Retrieval-Augmented Generation (T-SRAG) dynamically routes queries across retrieval paths. Contrastive alignment maps document and query embeddings to hierarchical topic structures to improve semantic fidelity and reduce hallucinations. Beyond retrieval, tensor-based link prediction identifies and completes missing links in the Knowledge Graph, supporting inference grounded in citation structure. Applications across cybersecurity, law, materials science, and healthcare demonstrate improvements in retrieval precision, early trend detection, hypothesis generation, and hallucination mitigation. The dissertation provides a deployable, modular foundation for trustworthy, domain-specific AI systems that retrieve and reason over structured knowledge.

We construct a symmetric conference matrix of order $86$, the smallest order for which existence was open. Equivalently, there exist a conference graph with parameters $(85,42,20,21)$, a regular two-graph on $86$ points, and a real equiangular tight frame of $86$ vectors in $\mathbb{R}^{43}$. The matrix is a $12\times12$ array of $7\times7$ circulants with two border rows, and it admits a group of automorphisms of order $21$. Its $86$ descendants give exactly ten nonisomorphic strongly regular graphs.

Multiplicative gamma noise is one of the dominant noise factors in Synthetic Aperture Radar (SAR) and medical ultrasound images. They are dependent on pixel level noises due to which they are highly varying across the image and harder to handle as compared to additive noise. The denoising methods to address this noise currently include classical partial differential equation (PDE) methods which are good for interpretation but lack the restoration ability as compared to the state-of-the-art models while deep convolutional networks like DnCNN achieve high performance but at the cost of transparency due to which practitioners are skeptical to use them in high-risk critical fields like medicine. This paper presents Hybrid++, a novel trainable nonlinear reaction-diffusion architecture that addresses both the concerns - staying interpretable while offering performance close to huge black-box models. It combines a fully learnable PDE initialization with a 3-stage reaction-diffusion network having 64-channel multiscale filter banks, 4-layer Squeeze-and-Excitation attention-based influence functions and a 64-dimensional noise level embedding. It uses a two-phase training strategy, stage-wise optimization followed by joint end-to-end refinement which enables co-adaptation of all learnable parameters. On the FoE benchmark, Hybrid++ substantially improves over classical PDE, BM3D and the original TNRD baselines. In the severe-noise setting L=1, it comes within 0.23 dB PSNR of a separately trained DnCNN while using only about 8% of its parameters. We therefore position Hybrid++ not as a universal state-of-the-art image restoration backbone, but as a compact, physically structured reaction-diffusion model for multiplicative gamma noise.

We prove that every finitely generated group with rapid decay and trivial amenable radical is C*-simple.

Quantum numerical algorithms often encode a positive solution $q$ in the amplitudes of a quantum state, while the required scientific output is a normalized linear functional of $q$. Basis measurements produce probabilities determined by squared solution values, while the functional uses the solution values themselves. We study the complexity of this output-interface problem for $F_\phi(q)=\int\phi q\,\mathrm d\nu/\int q\,\mathrm d\nu$ and identify a target-dependent susceptibility $\chi_\phi$ that governs the amount of copies of the solution state needed. For a fixed positive reference state and a neighborhood around it, the optimal number of unknown-state copies is $\Theta\!\left(\chi_0\varepsilon^{-2}\log(1/\beta)\right)$, where $\varepsilon$ is the absolute error tolerance and $\beta$ is the allowed failure probability. We show that two fixed single-copy measurements attain the same rate. We then analyze how this baseline changes when the interface retains classical information, uses adaptive allocation, supplies coherent access, or restricts the allowed solution family. Therefore $\chi_\phi$ quantifies a central cost of using a solution encoded in an $L^2$-normalized quantum state to estimate an $L^1$-normalized linear observable.

Consider placing the numbers $1, \ldots, n$ consecutively around an $n$-cycle. We ask for a given $n$, which numbers $k$ can be written as a sum of consecutive numbers on the $n$-cycle. If all numbers between $1$ and $T_n$, the $n$th triangular number, can be written as a sum this way we say the $n$-cycle is complete. Our main result shows that for $n\geq 8$, $n$-cycles are incomplete.

Let $\mathcal P_1$ denote the class of 1-planar graphs and let $tC_5$ be the disjoint union of $t$ copies of $C_5$. For every fixed $t\ge3$ and all sufficiently large $n$, we determine the unique $n$-vertex $tC_5$-free graph in $\mathcal P_1$ with maximum adjacency spectral radius, answering Problem 1 of Li, Wang and Zhao. The proof first gives a structural description of every extremizer. After two dominating vertices are removed, the remainder consists of copies of the seven-vertex graph $B=K_1\vee2K_3$ together with at most one bounded connected core. This follows from a two-family covering theorem for 1-planar $K_2$-joins and the sharp packing–defect inequality \[ 12v(Q)-7e(Q)\ge1-10\nu_5(Q). \] The same inequality yields an exact edge-extremal result for remainders with bounded pentagon packing. A normalized resolvent then cancels the repeated $B$-components, and finite moment comparisons force all packing and all nonzero defect into one core and identify that core uniquely in each residue class modulo $7$. The case $t=3$ is the pentagon-free boundary case and is completed by one exact finite component lemma.

Full-duplex voice agents need to modulate emotion and delivery during real-time conversations, when de-escalating a complaint, carrying urgency in dispatch, softening a clinical result. Emotion and delivery control is well studied for TTS and turn based models through prompt-conditioned synthesis, reference-conditioned synthesis and activation steering; PersonaPlex controls identity in a duplex model but not affect. We study emotion steering in Moshi, a fully open sourced full-duplex speech language model, across four emotions, using mean-difference activation steering, which costs only a few vector additions per frame and no retraining. We show that emotion is linearly decodable from Moshi's residual stream, but activation steering is only partially achievable, and unevenly so; as happy, angry and surprise steer towards a shared direction while sad is distinctly steerable. We also show that the shared component across the three emotions cannot simply be projected away from all the emotions equally.

Let $n\ge2$ be a fixed integer, and let $K,x,y$ be positive integers satisfying $2\le K\le y<x$. Consider a polynomial \[ f(u)=\alpha u^n+\alpha_{n-1}u^{n-1}+\cdots+\alpha_1u+\alpha_0 \] with real coefficients. We study the quantity \[ V_n(K,x,y) = \sum_{k=1}^{K} \left| \sum_{x-y<p\le x}e(kf(p)) \right|, \qquad e(t)=e^{2\pi it}, \] where the inner sum is over primes. For $\alpha=\frac{a}{q}+\frac{\theta}{q^2}$, $a\in\mathbb Z$, $q\in\mathbb N$, $(a,q)=1$, $|\theta|\le1$, we establish the bound \[ \begin{aligned} V_n(K,x,y) &\ll Ky\Biggl[ \frac{1}{\sqrt{K\log(2y)}}+ \min\left\{ \Delta^{\frac{1}{2^n}} \bigl(\log(2y)\bigr)^{\frac{n^2-1}{2^n}}, \Delta^{\frac{1}{3\cdot 2^{n-2}}} \bigl(\log(2y)\bigr)^{\frac{n^3-1}{3\cdot 2^{n-1}}} \right\} \Biggr], \end{aligned} \] where \[ \Delta= \frac{1}{q}+\frac{1}{y}+\frac{q}{Ky^n}. \] The bound is uniform in the position of the interval, and the logarithmic factors depend on its length. The proof uses the nonnegative Fejér kernel, successive differencing, and the second and third moments of the generalized divisor function. The Brun-Titchmarsh inequality accounts for the number of primes in the interval and provides an additional logarithmic saving in the term arising from averaging. We obtain sufficient conditions for a saving of any fixed power of the logarithm of the interval length, as well as an analogous mean estimate for sums over all integers.

We show that Hitchin-Wolf's harmonic map parametrization of Teichmüller space, the Schwarzian holonomy map, and Uhlenbeck's almost-Fuchsian holonomy map all arise as restrictions of a single locally biholomorphic map into the $\mathrm{PSL}(2,\mathbb{C})$ character variety. The map admits a right inverse defined on an open subset of quasi-Fuchsian space, encoding harmonic maps together with the Bers embedding. The construction goes through complex harmonic maps to the space of oriented geodesics of $\mathbb{H}^3$. Along the way, we further develop the theory of complex harmonic maps, with a focus on the natural $\mathbb{C}^*$-action and the relation to complex projective structures. This leads to an independent application: we obtain a new geometric interpretation of certain real twistor lines in the rank-two Deligne-Hitchin moduli space and we recover a theorem of Gothen-Silva.

A declared task can sometimes certify a reduced source before a downstream encoder, codebook, rate, distortion target, or optimizer is chosen. This paper studies when one such reduction preserves the complete downstream problem family, a property termed Task-Sufficient Contraction. The reduced source is fixed by the task before the later operating point is selected. An exact contraction allows the later problem to be solved on that source with the same result as if the full source had been retained. For a machine with a fixed set of possible actions and a fixed loss, the paper identifies a consumer-specific source by merging states only when every available action has the same regret in both. For finite action sets, replacing the richer source by this reduced source preserves the complete one-step rate-regret curve, even though the reduction is fixed before the distortion target is chosen. A second result gives an exact characterization for quadratic loss on affine feasible-action sets: the canonical reduced source is the projection onto the directions in which feasible actions can differ. Under a fixed energy budget, this becomes centered load, while retaining only the optimal water-filled action is too coarse. Earlier Information Bottleneck, semantic rate-distortion, and goal-oriented quantization results are then used to distinguish exact, architecture-conditioned, approximate, failed, and corrected contractions. The framework suggests a way for heterogeneous machines to exchange what a receiving task needs without first aligning their full internal representations.

Finding low-energy configurations of interacting particles and approximating probability distributions lead to the minimization of potential-interaction energies in Wasserstein space. These energies can be nonconvex, making it important to exploit second-order information while controlling the reliability of local approximations. We study trust-region optimization of smooth potential-interaction energies on the Wasserstein space of probability measures with finite second moment. The method uses a quadratic model along pushforward curves, an $L^2(\rho)$ step radius, and a Steihaug-Toint subsolver with an explicit self-adjoint second-variation operator. A ratio test determines acceptance and guides the radius update. Under a lower energy bound and globally bounded Hessians of the potential and interaction kernel, we prove that the objective is nonincreasing, the Wasserstein-gradient norms converge to zero, and an $\varepsilon$-stationary iterate is reached within $O(\varepsilon^{-2})$ total outer trials, including rejected trials. If the potential is quadratically coercive, every weak accumulation point is stationary. The analysis applies to arbitrary initial measures with finite second moment. For empirical measures, the iteration is a finite-dimensional trust-region method in the $L^2(\rho_N)$ inner product, with complexity constants independent of particle number and dimension when the initial objective gaps are uniformly bounded. Numerical experiments include a smooth soft-particle energy, maximum-mean-discrepancy minimization for non-Gaussian targets, component ablations, and scaling studies in particle number and dimension.

FinVector-Market-4B adapts Qwen/Qwen3.5-4B with rank-16 LoRA on a 22,000-example corpus for structured financial tasks. We evaluate the base and adapted models on the same 600-example benchmark under implicit and explicit JSON-schema contracts. Supplying the schema alone raises base-model JSON validity from 0% to 91.3%. Under matched explicit prompting, the frozen scores improve from 14.7% to 40.0% for FinQA answer exact match, from 48.0% to 82.7% for calculator-expression correctness, from 20.1% to 89.5% for scenario branch-label agreement, and from 52.4% to 87.2% for implication-direction agreement. A post-hoc policy-scoring audit shows that the reported macro-F1 decline reflects a changing label set; using the same three target classes gives 77.4% for the base and 83.1% for the adapter. Filing overlap and calculator-target inconsistencies qualify the benchmark's generalization claims. The results show that compact financial domain adaptation can produce substantial task-specific gains beyond output-format learning under matched prompting, with gains bounded by the evaluated task distribution and prompt contract.

Modern software-intensive systems increasingly incorporate GenAI components, including LLM and agentic subsystems, which introduce novel and compounding sources of uncertainty across system layers. The self-adaptive systems community has made significant strides in understanding and managing uncertainty. The intrinsic characteristics of GenAI, including probabilistic outputs, hallucinations, context window limitations, and memory staleness, demand a re-examination of existing frameworks and mitigation strategies for dealing with uncertainty, and especially, the interactions among uncertainty occurrences and manifestations. This position paper posits an initial conceptual framework that establishes preliminary guidelines for characterizing and mitigating uncertainty interactions in GenAI-based software-intensive systems. We argue that mitigation must be considered across the full software lifecycle, encompassing requirements analysis, design-time decisions, and run-time adaptations, which implies the unfeasibility of decoupling it from monitoring and analysis at execution. We introduce the notion of a mitigation function that maps uncertainty interaction categories, involved uncertainty types, system design characteristics, criticality, and mitigating architectural tactics to impacted quality attributes and corresponding tradeoffs. As a proof of concept, we apply the framework to three illustrative use cases: LLM serving, AI-driven software operations, and agentic cloud management.

This paper studies tetrahedral meshes as the body representation for differentiable simulation and computational design. Fixed-connectivity meshes degrade under large morphs, while remeshing from scratch discards node correspondence. We present JamTet, a physics-based sphere-packing framework for volumetric meshing and morphing. We contribute (i) a GPU-parallel mesher combining octree-hierarchical packing with constrained Delaunay tetrahedralization, producing more uniform element volumes than TetGen and fTetWild; (ii) Lagrangian mesh morphing that preserves interior-node identities by re-equilibrating the same spheres within changing shapes and rebuilding the boundary and connectivity, remaining inversion-free where fixed-connectivity and TetSphere meshes invert; and (iii) a differentiable GPU simulator in JAX, with mass-spring edges and a volumetric Neo-Hookean term, integrated with mesh morphing in a design pipeline. In soft-robot morphology design experiments, interior-node gradients improve swimming fitness by 0.73-1.07 over a matched surface-only variant, while voxelized versions of the same designs yield 32-63% lower fitness. These results establish sphere packing as a practical volumetric mesh representation for gradient-based shape optimization. Code and media: under review.

Pretraining strategies significantly impact the quality of language models, yet existing comparisons of Masked Language Modeling (MLM), Whole Word Masking (WWM), and MacBERT-style replacement have focused primarily on base-scale models (>=110M parameters). This paper presents a controlled comparison of these three strategies on a tiny-scale Chinese BERT model (4 layers, 256 hidden dimensions, 8.7M parameters). Under identical architecture, corpus (1.29M sentences from Chinese Wikipedia), and hyperparameters, we train three models from scratch and evaluate them across five intrinsic dimensions: perplexity, MLM hit rate, semantic discrimination, grammatical judgment, and contextual sensitivity. At tiny scale, MLM achieves the best overall intrinsic performance (winning 3 of 5 dimensions), while WWM excels in both perplexity (1.27 vs. 2.10, a 39.5% improvement) and MLM hit rate (22% vs. 16%). Notably, MacBERT under a severely limited synonym dictionary (222 entries, 3.3% coverage) exhibits severe perplexity degradation (47.23, 22x higher than MLM), yielding a ranking (MLM > WWM >> MacBERT) that differs markedly from the established base-scale conclusion (MacBERT > WWM > MLM). We further identify a critical evaluation pitfall: MacBERT achieves the lowest training loss (2.17) yet the highest perplexity (47.23), revealing that training loss alone is unreliable under mixed replacement strategies. All models and corpus are publicly available at https://huggingface.co/eebyp.

This article develops a failure-mode framework for analyzing how advanced artificial intelligence could contribute to human extinction, irreversible civilizational collapse, or permanent human disempowerment. The central thesis is that catastrophic AI risk does not require consciousness, hostility, or an explicit intention to harm humanity. Instead, risk may arise through several distinct but interacting pathways, including autonomous misalignment, harmful human use, organizational failure, and competitive deployment. The severity of these pathways depends on factors such as capability, autonomy, external access, persistence, institutional safeguards, and the preservation of recovery capacity. The analysis is deliberately non-operational: it identifies causal conditions, empirically tractable intermediate quantities, and defensive research questions rather than procedures for causing harm.

Radioactive nuclei with extreme proton-to-neutron ratios provide unique probes of nuclear structure, fundamental symmetries, astrophysical processes, and applications such as medicine. However, their short half-lives and low production rates mean that experiments must work with few desired ions, often amid contaminant backgrounds exceeding the signal by six orders of magnitude. Efficiently isolating, transporting, and delivering these ions through multi-stage apparatus is therefore a central challenge. We introduce a differentiable probabilistic surrogate for ion-beam transport in regimes dominated by particle loss. The model jointly captures the survival probability of ions along the beamline and the evolving phase-space distribution of the surviving particles by combining discrete-time survival analysis with conditional normalizing flows. Applied to a high-dimensional electrostatic beamline, the resulting likelihood enables gradient-based optimization of operating voltages and inference of beam properties from sparse detector observations. Once trained, the surrogate provides millisecond-scale differentiable predictions, transforming particle-tracking simulations with hard losses into an inference-ready model for experimental design, beamline optimization, and future digital twins of experiments with rare nuclei.

Hardware faults can flip bits in the stored weights of a quantized neural network, potentially compromising its predictions. While such faults typically affect multiple parameters simultaneously, existing verifiers are limited to single-parameter perturbations due to the combinatorial explosion of possible flip locations in large networks. We present mBFV (m-BitFlip Verifier), an efficient verification framework that proves robustness against simultaneous bit flips across multiple parameters without explicitly enumerating these combinations. mBFV achieves this via a novel multi-parameter bound propagation technique that directly aggregates the m worst-case contributions. To further tighten these bounds, mBFV employs a branch-and-bound mechanism over perturbation locations, partitioning the potential flips to smaller groups of neurons. Evaluated on 625 instances, mBFV successfully verifies 293, significantly outperforming a prior single-parameter verifier (38 verified instances) and an exact mixed-integer linear programming baseline (0 verified instances). Notably, while these baselines are restricted to single-parameter flips on small networks (up to 13k parameters), mBFV scales to verify networks with up to 1.15M parameters against up to four simultaneous parameter flips.

Agent Skills package procedural guidance and resources for reuse, but a relevant Skill does not necessarily improve task performance. Existing studies characterize Skill content and evaluate downstream performance, yet provide limited explanations of how utility depends on content, execution configuration, and multi-Skill organization. We conduct an empirical study on 87 SkillsBench tasks, defining downstream utility as the pass-rate difference from No-Skill on the same tasks under the same model–harness configuration. We compare the same Skills across nine configurations, then examine alternative published Skills and organizations of fixed Skill sets under three selected configurations. We retrieve marketplace candidates from a curated corpus of 37,596 Skills. LLM-assisted analysis of content, execution traces, and final artifacts, followed by author review, relates provided support to actual use and task outcomes. The same Skills help some configurations and hurt others on 36.78% of tasks, with trajectories showing that recommended procedures can become an execution burden. Relevance rankings overlook more useful candidates. Within the evaluated candidate sets, reranking by support for required operations raises first-choice pass rates by 4.35–5.80 percentage points across the three configurations. We derive 17 authoring practices linking executable procedures to recovery, preservation of task requirements, and checks on final artifacts. Stage Plan and Dependency DAG outperform use order alone, with DAG's additional benefits concentrated in tasks supplied with five or six Skills. These findings guide developers to assess usable operation support, allow procedure adaptation while preserving task requirements, and make artifact dependencies explicit when organizing Skills.

Metallic nanowire aerogels combine the functional properties of metals with the high porosity of aerogels. Here, Ag and Cu nanowire aerogels with densities of 20-500 mg cm-3 were synthesized by freeze casting and investigated using lock-in thermography during sequential mechanical compaction. Thermal transport depended strongly on nanowire diameter, with 30 nm Ag nanowires exhibiting substantially lower thermal diffusivity than 60 nm wires, likely due to enhanced surface scattering as the wire diameter approaches the electron mean free path in Ag. Surprisingly, increasing the aerogel density through mechanical compaction reduced the calculated thermal diffusivity by nearly 300x, opposite the conventional expectation that denser materials transport heat more efficiently. Further analysis showed that this decrease is dominated by the thickness term in the thermal diffusivity formalism, while the fitted transport coefficient changes comparatively little. The characteristic thermal diffusion timescale decreased only modestly during compaction, indicating that densification primarily collapses pore volume without fundamentally restructuring the conductive nanowire network. This behavior resembles topology-preserving densification, where large geometric compression produces comparatively small changes in the effective percolative transport pathway. These results show that nanowire aerogels cannot always be treated as homogeneous bulk media, because their macroscopic geometry and conductive network evolve differently during compaction.

A classical phenomenon distinguishing infinite-dimensional holomorphy from its finite-dimensional counterpart is that monomial expansions of holomorphic functions need not converge absolutely. In this paper, we systematically investigate monomial convergence on complex Banach sequence spaces. We establish general structural results and give a negative answer to Lempert's problem. We then determine the domains of absolute monomial convergence for holomorphic functions on the classical Banach sequence spaces and obtain a complete classification for continuous homogeneous polynomials. As a further application, we establish a sharp comparison between two notions of convergence radius for homogeneous Taylor expansions on $\ell^1$. The methods developed here are of independent interest and may be applied in other places.

We study community recovery in the sparse symmetric stochastic block model with $q$ communities, average degree $d$ and signal strength $\lambda$ through statistical decision theory and Fisher information, and obtain three characterizations of the Kesten-Stigum threshold $d\lambda^2=1$ and of the information-computation gap below it. First, on each community-size profile the minimax risk of any class of rules closed under averaging and vertex relabeling equals its Bayes risk under the uniform prior; the posterior mean is the unique Bayes rule and is admissible, and the Bayes risk of degree-$D$ polynomial rules is the trivial risk times $1-\mathrm{Corr}_D^2$. Combined with known low-degree and information-theoretic results, this gives the gap as a worst-case statement: for $q\ge 5$ there is a window below the threshold in which no low-degree rule beats the trivial risk asymptotically, while an exponential-time rule does on a set of labelings of probability $1-o(1)$. Second, the Fisher information about $\lambda$ carried by cycle counts is a series with terms of order $k(d\lambda^2)^k$, convergent exactly when $d\lambda^2<1$; below the threshold the relative error of every unbiased cycle-based estimator of $\lambda^k$ stays above an explicit constant, and every cycle-count test has success probability bounded below one. Third, the derivative of belief propagation at its uninformative fixed point multiplies a random perturbation by $|\lambda|\sqrt{d}$ per iteration, and one EM step taken there leaves $\lambda$ unchanged. A signal-to-noise computation recovers the condition $d\lambda^{1/\chi}>1$ of Chin et al. for $q=n^\chi$ communities and identifies personalized PageRank as a walk count with suboptimal weights. Experiments on networks with up to $3\times 10^5$ vertices confirm the threshold for $q=2$, the hard window for $q=5$, and the many-community scaling.

Language model agents are increasingly deployed to automate everyday digital chores from managing emails and social media to handling banking and bills allowing users to step away from supervision. However, this capability also exposes sensitive information to phishing. Safe execution requires distinguishing malicious requests from genuine ones without simply refusing to act. Despite its practical importance, this problem remains underexplored and it is unclear whether current agents or existing defenses can achieve it. To study this problem, we first propose CredLeak-Bench, a comprehensive benchmark designed to evaluate how effectively and securely agents automate human workflows when confronted with phishing and identity verification. The benchmark covers both user-directed authentication and autonomous inbox monitoring, where agents are not explicitly instructed to log in. It systematically varies deceptive cues and pairs phishing scenarios with legitimate counterparts, enabling joint evaluation of information leakage and utility on genuine tasks. Within a sandboxed environment, leakage is measured through actual submissions of information rather than agents' self-reported behavior. Our evaluation reveals that all tested models are vulnerable to leakage. Agents also disclose sensitive information during autonomous inbox monitoring, demonstrating that phishing can induce disclosure without a user request to authenticate. Furthermore, most evaluated mitigations that reduce leakage also impair performance on genuine tasks, exposing a security utility trade off in existing defenses. These findings show why reducing leakage alone is insufficient: effective defenses must prevent unauthorized disclosure while preserving legitimate task completion. CredLeak-Bench provides a controlled framework for measuring both objectives and evaluating progress toward secure, useful agents.

Unlike conventional teleoperation, wearable interfaces allow operators to collect dexterous demonstrations through their own hand motions while directly interacting with task objects. This direct interaction reduces dependence on the target robot during collection, but it also makes the collection hardware part of the physical process that generates each demonstration. Interface geometry can influence both how a task is performed and what tactile observations are recorded for learning. We study two versions of a DexUMI-family exoskeleton that share the same robot command definition, mapping procedure, and tactile module type but differ in hand-side geometry. The revised interface reduces reported physical demand, improves selected device ratings, enables tactile access in a precision grasp that is mechanically blocked by the baseline, and produces task-dependent changes in recorded contact. Lid twisting primarily exhibits a change in contact location, whereas egg carton opening primarily exhibits a change in contact occurrence. We then train matched policies using either a binary aggregate input or a spatial-plus-force input. On lid twisting and egg carton opening, policies trained on revised-interface demonstrations achieve higher success than those trained on baseline demonstrations, with a significant pooled interface effect. Across these and two additional tasks, USB insertion and soldering tool pick and place, the spatial-plus-force input likewise outperforms binary aggregation. These results show that wearable collection hardware is part of the data-generation process for robot learning. Such interfaces should therefore be evaluated not only through operator experience, but also through the tactile interactions they make recordable and the policy performance their demonstrations support.

Regulated credit scoring requires scores monotone non-decreasing in every exposure input. Deployed pipelines – hand-crafted monotone aggregates feeding sign-constrained gradient boosting – already meet this by composition; the open question is what learned temporal aggregation is worth inside one. We answer on five production-scale credit datasets at matched admissibility (one priced baseline convention excepted), with a monotone recurrent architecture whose per-input guarantee we extend, with proofs, to vector-valued inputs and to exogenously macro-conditioned decay gates, severities, thresholds, and peak memory. Two findings result. First, a strictness ladder: the value of learned monotone features rises with governance-frame strictness – zero on unconstrained engineered panels, maximal in summaries-only frames – replicated across two datasets and an official temporal-stability metric, though unconditioned features degrade on externally adjudicated later weeks. Second, a conditioning-delivery asymmetry under regime shift. On a train-on-boom, test-on-crisis mortgage design, two public macroeconomic series hurt as input columns, yet conditioning the recurrence on them delivers the paper's only learned-block crisis-cohort uplifts. The confirmed effect: +0.006 to +0.013 AUC on an internally pre-registered Freddie Mac replication, at all five held-out seeds. The discovery estimate: +0.015 to +0.021 on Fannie Mae (three of five seeds post hoc), worth 10-27 basis points of defaulted balance at an 80% approval cutoff, and grows with early-prepaid loans excluded. A state-level test identifies the mechanism: between-cohort calibration transfer. A pandemic-band episode bounds scope: under forbearance-distorted labels the gain generalizes at a quarter to a third of crisis size on Fannie Mae, on Freddie Mac only against the capacity control.

Smart light-emitting diode (LED) bulbs are networked devices that produce information-carrying output. This study asks whether that light can carry digital data through changes small enough to be difficult for a person in the room to notice. To explore this covert communication channel, we tested an unmodified smart bulb (Philips WiZ A19) using a camera as the receiver. Binary data were encoded programmatically in nearly matched color and brightness changes. Because the differences were deliberately small across 16 million color steps, the receiver periodically measured known reference states and used them to compensate for changes in the camera and background room illumination. The color method successfully transmitted the short message 'hi' using a color difference (E) of 0.5, a standard measure of perceptual color distance. The receiver recovered 99% of the transmitted bits, and the complete message passed an integrity check. The brightness method remained decodable at the smallest nonzero integer difference tested, alternating between dimming settings 56 and 54, with 96.2% mean bit accuracy across two runs. When both binary symbols were assigned to the same brightness in a control experiment, accuracy fell to approximately chance. These results show that the visible output of an ordinary smart bulb can serve as a low-rate data channel without hardware modification. Camera color drift can overwhelm small signals unless the receiver is recalibrated during transmission, sudden changes in ambient light can disrupt decoding, and longer messages require stronger error correction. The color experiment operated at a difference below a conventional threshold for human color discrimination. The corresponding perceptual limit for the brightness method has not yet been established experimentally.

The rapid growth and heterogeneity of Internet of Things (IoT) environments have exposed fundamental limitations in traditional rule-based and signature-based intrusion detection systems. This paper presents a quantitative deployment-aware analysis of machine learning (ML)-based intrusion detection approaches across edge, fog/gateway, and cloud architectures. Unlike prior surveys that primarily emphasize detection accuracy, this work defines representative quantitative deployment capability envelopes extracted from experimental and system-level studies and introduces a structured Deployment Feasibility Score (DFS) model. The proposed framework maps ML techniques to architectural layers based on computational demand, memory footprint, and latency sensitivity using a weighted ordinal scoring mechanism. The analysis demonstrates that lightweight statistical and linear models are most suitable for edge deployment, ensemble and clustering-based methods align with fog/gateway environments, while deep and optimization-driven models are best suited for cloud infrastructures. By formalizing deployment feasibility through quantitative grounding and structured evaluation, this work provides practical guidance for selecting intrusion detection solutions under real-world architectural constraints, supporting more informed and deployment-conscious IoT security design.

Video world models can produce visually convincing yet physically inconsistent sequences, raising concerns about their reliability for prediction and planning in embodied AI systems. Existing evaluations often rely on model-based judgments or reference videos, while direct physical tests largely focus on mechanics. We introduce World Models' Last Exam in Physics, a measurement-based benchmark for evaluating physical consistency in video world models. The benchmark comprises 40 controlled tasks spanning mechanics, optics, fluids, thermal and phase-change phenomena, electromagnetism, and surface tension. Each task pairs an initial image and a generation prompt with predefined physical criteria, enabling interpretable tests of observable physical relationships without requiring reference videos. Its evaluator combines task-observability screening with task-specific quantitative physical measurements. Experiments on eight video generation models across 1,280 videos reveal persistent physical inconsistencies and substantial variation across tasks, with the best model achieving an overall score of 57.76 out of 100. Evaluation on synthetic videos with known physical relationships provides evidence for the validity of the measurement module under controlled conditions. The evaluator also achieves higher agreement with human judgments than a direct vision-language model baseline in both within-task rankings and pairwise comparisons. By combining coverage across physical domains with scores grounded in measurable evidence and explicit measurement limitations, the benchmark provides an interpretable basis for diagnosing physical inconsistencies and tracking progress toward physically consistent video world models.

Single-image scene generation aims to produce a complete 3D scene mesh from a single image, including surfaces the camera did not observe. While pretrained 3D object generators encode a strong shape prior, they are mainly designed for isolated objects in a fixed canonical volume and focus mostly on indoor scenes, since diverse 3D data for outdoor scenes are quite limited. In this work, we present a method that redesigns such an object-centric generator, e.g., Trellis 2, to work on both indoor and outdoor scenes while retaining its prior. We accomplish this by (a) partitioning the scene into adaptive chunks that scale relative to the distance to the camera; nearby chunks have a smaller size to keep the finer detail, while distant structures, e.g., buildings, are covered by large chunks; (b) making the generator capture explicit 2D-3D correspondence by lifting image features and making the model aware of the free space, observed surface, and unobserved region; (c) synthesizing around 4,000 outdoor scenes to broaden the training data, as existing scene datasets are largely indoor. Experiments on Tanks and Temples, ScanNet++, and in-the-wild images show that our method outperforms all baselines in geometric accuracy and perceptual quality across both indoor and outdoor scenes.