Papers

Neural Architecture Search (NAS) automates network design, but evaluating a single candidate requires training it to convergence, making exhaustive search intractable. Zero-cost proxies estimate architecture quality at initialization in seconds, yet a single proxy is noisy, and combining several does not straightforwardly help: proxies are strongly correlated, so naive aggregation compounds their shared errors instead of averaging them out. Existing methods exploit either proxy signals or architectural topology - never both within a single active-learning framework. We introduce ZAPS (Zero-cost Active Proxy Search), a four-stage pipeline that closes this gap. ZAPS (i) selects a compact, non-redundant proxy subset offline via ProxyFit, a greedy anti-redundancy criterion; (ii) seeds the search with a hybrid K-means strategy that balances exploitation and exploration; (iii) re-selects proxies at every iteration by a bootstrapped vote as the labeled set grows; and (iv) ranks candidates with an XGBoost ensemble trained jointly on proxy ranks and one-hot topological encodings, queried through an Upper Confidence Bound (UCB) acquisition function. On NAS-Bench-201 under a budget of B=200 evaluations, ZAPS recovers 52.3% of the true top-100 architectures on CIFAR-10 and 65.8% on CIFAR-100, ahead of every baseline we consider - Random Search, Local Search, REA, BANANAS and TPE - and, on CIFAR-10, with less than half the run-to-run standard deviation of the strongest of them. The advantage is largest where evaluations are scarce: on NAS-Bench-201 it narrows as the budget grows, whereas on the harder NAS-Bench-101, which no method comes close to saturating, it widens instead. All methods are scored by a single criterion: how much of the true top-100 lies among the architectures they actually evaluated.

This paper presents the development and initial testing of DreamSat-Bench, a modular rendezvous and proximity operation testbed designed to benchmark AI-based relative navigation techniques. By integrating a software- and hardware-in-the-loop robotic pipeline, the platform enables a seamless transition from digital simulation to physical reality. DreamSat-Bench unifies state-of-the-art robotic learning tools such as MuJoCo, Isaac Lab, and LeRobot into a single benchmarking platform, utilizing robotic arms to trace 3D trajectories. The platform allows for extensive customization of orbital environments and lighting to evaluate the simulation-to-reality gap. We demonstrate the testbed's utility by evaluating an end-to-end vision-based navigation pipeline that pairs DreamSat, a generative AI framework for single-view 3D reconstruction, with FoundationPose for zero-shot 6-DoF tracking of unseen spacecraft. Initial testing explores mission-representative orbital segments, including fixed-point station-keeping and fly-around characterization. Through a series of parametric studies, we quantify the impacts of reconstruction latency, mesh resolution, orbital range, and illumination geometry on pose estimation accuracy. Finally, a preliminary hardware-in-the-loop campaign qualitatively validates the physical deployment of the pipeline, identifying target symmetry and accumulated tracking drift as critical factors for robust navigation. DreamSat-Bench provides a rigorous framework for maturing autonomous navigation with unprepared space assets in the absence of prior geometric models.

We study the complexity of simple semi-conditional grammars (SSCGs) in terms of the number of their terminals and non-terminals. We show that SSCGs with three non-terminals can generate all RE languages; two non-terminals suffice for linear languages; and one suffices for unary regular languages. We also determine both upper bounds and fundamental limitations of SSCGs: while certain one-non-terminal SSCGs can generate non-context-free languages, every language generated by a one-non-terminal SSCG is in non-deterministic linear space. We also prove that there exists a regular language of alphabet size at least 3 which cannot be generated by any one-non-terminal SSCG. Finally, we prove that membership testing for SSCGs of two non-terminals is already NP-hard.

Fault detection in autonomous VTOL aircraft is critical because even minor component degradations can rapidly destabilize multirotor vehicles operating in complex, safety-critical environments, motivating robust fault detection and estimation strategies capable of identifying early signs of rotor damage; however, real-flight fault detection remains challenging due to sensor noise, environmental disturbances, and the nonlinear aerodynamics of multirotor platforms. This study proposes a comprehensive machine-learning framework for rotor fault detection, isolation, and severity prediction using real flight data. A convolutional neural network (CNN) architecture is developed to learn spatio-temporal patterns from multivariate flight dynamics, enabling direct inference of both the faulted rotor and its damage level. The framework is first validated using simulated data generated by a data-generative model, and experimental validation is then performed on a hexacopter by introducing controlled blade-tip breakage. The trained model achieves rotor-wise fault classification accuracies above 99% and severity estimation accuracy of 96% within a 1% tolerance in experimental data, demonstrating strong generalization and supporting real-time health monitoring for autonomous VTOL systems.

The rapid diffusion of hate speech and misinformation on social networks challenges democratic societies, since direct suppression efforts may deepen polarization, fuel public distrusts, and strengthen extremist narratives. LLM-driven counter-narratives (CNs) offer a promising way to reduce those risks, yet their effectiveness depends on rhetorical and stylistic choices that remain poorly understood. We present a multi-stage agent-based framework for generating, refining, and evaluating CNs, applied to pro-Russian hate and misinformation narratives on the war with Ukraine and adaptable to other domains. A pilot experiment with human evaluators identifies effective technique style pairings, such as repetition with emotional framing enhancing persuasiveness. Building on these insights, we introduce a multi-agent refinement process that iteratively improves CNs for persuasiveness, emotional engagement, and shareability. After human validation confirmed improvement, an automated safety analysis shows that our refined CNs match or improve on expert-written counterspeech. A simulated experiment then shows that they reduce the perceived strength of pro-Russian narratives and consistently outperform a vanilla LLM baseline, highlighting a pathway toward scalable, narrative-specific interventions against hate speech and misinformation. Code and data accompanying this work are publicly available at https://github.com/carmelkron/inlg2026-counter-narratives.

Asked to describe what one of six speakers in a recording talks about, audio language models describe the right one on 6 to 16% of trials, below the 16.7% a guess would give. Adding a fixed bias to the attention logits of a hundred heads, under a tenth of the model's and with no training, redirects the description to whichever speaker we choose, on 90.7% to 99.0% of trials. Those heads are largely not specific to audio. Rank the text-only language model an audio model was built from, or a released model of the same family, on a written version of the task, take its top hundred heads, and carry them over unchanged: they redirect the audio model on 80.8% to 95.0% of trials, with nothing about audio entering the selection. The audio and text head sets share 66 to 74 of 100 where chance would give about 20, and the shared part alone reproduces almost all of the steering. What that does not show is that sharing is what makes the heads work: an equal-sized draw from the same discovered hundred does nearly as well, and none of our three models separates the two explanations. A second finding concerns how such heads are found. Ranking heads by how much attention they place on the segment asked about, as an established score does, or by how much of their attention moves with the question, as a per-head normalised variant does, gives top hundreds that share 69, 37 and 4 heads across our three models. In Ultravox, where they share 4, the established score's heads leave output the judge cannot place on any segment on 69.7% of trials, against 40.0% with no intervention and 1.0% for the normalised variant. That is one arm of six; on the other five the established score steers above a random draw.

Human-to-robot skill transfer from sensing gloves has so far relied on shared hardware: the same tactile glove worn by the demonstrator and the robot, or a learned alignment between two tactile sensors. We present GIFT (Glove-Inferred Force Transfer), a pipeline in which the interface between human and robot is a physical unit rather than a shared sensor: fingertip force is measured in newtons on the human side and estimated in newtons on the robot side. A wearable glove records finger flexion, calibrated fingertip force, and wrist orientation, while a head-mounted camera records the demonstration; no robot is present. At deployment, the robot estimates force from actuator-current residuals relative to a free-space baseline, through a calibrated mapping to newtons, so any position-controlled hand that reports motor current can serve as the deployment platform. The policy uses a glove-space state and predicts finger-position targets; the robot enters only through two calibrated adapters, a retargeting decoder and a force estimator. We evaluate GIFT on a cup grasp-and-hold task with two action-chunking policies trained on the same demonstrations, with fingertip-force inputs retained in one and zeroed in the other. In a 50-rollout evaluation with sample size and metrics fixed before scoring, both policies succeeded in all 25 rollouts. The median of the per-rollout hold-phase grip-force estimates was 53% lower with force inputs: 1.20 N versus 2.55 N (one-sided Mann-Whitney U, p<0.0001). In an observation ablation, a vision-only policy achieved 0/15 grasps, policies given hand-command state acquired the grasp, and the force inputs determined how hard the policy held. A force channel measured on the human hand thus transfers to a robot hand with no tactile hardware, through a retargeting map from five glove channels to seven robot actuators, with no sensor shared between the two.

Complex-valued signals like MRI and audio spectrograms are typically modelled as flat two-channel Euclidean data. The inherited Euclidean metric $dA^2 + A^2 d\theta^2$ vanishes at the origin, leaving phase unpenalised exactly where the signal is weakest. We replace it with the decoupled product metric $dA^2 + d\theta^2$ on the cylindrical closure $[0, \infty) \times S^1$, which stays non-degenerate at $A = 0$. We measure what this substitution costs and buys. Exact analytical bridges across synthetic fields, fastMRI knee data, and LibriSpeech spectrograms show Cartesian paths induce a heavy-tailed angular velocity distribution (Pareto index $\approx 1$). Under independent coupling, 43%-49% of signal energy falls on paths turning faster than $\pi$ rad per unit time. Cylindrical paths never reach this speed. We formulate Cylindrical Flow Matching (CyFM) to strictly bound the angular regression target, coupling noise and data via exact minibatch Optimal Transport jointly over whole fields. This coupling reduces few-step generation error by 3%-60%. CyFM achieves lower generative error than the best Cartesian baseline at every step up to $k = 8$ on synthetic fields and speech spectrograms, with all seeds separated. On knee MRI, the single-step advantage is 1.8x. At convergence ($k = 100$), the two geometries show no significant difference. Finally, a prior-only control exposes the cost of flat parametrisation: on synthetic fields, a single Cartesian Euler step performs worse than the unintegrated noise prior (0.376 vs. 0.150).

Distributed multiple testing asks $N$ sites, each holding p-values for its own hypotheses, to control the false discovery rate (FDR) of the discoveries made across the whole network while communicating only a small number of bits. Greedy interval aggregation (Pournaderi and Xiang, IEEE TSIPN, 2023) meets the communication budget but controls FDR only asymptotically, and its FDR can exceed the target at finite sample sizes; the same interval counts both select the rejection regions and calibrate the stopping rule, which biases the selected interval densities upward. We propose budgeted BONuS-GA: each site mixes synthetic uniform p-values into its data, the center ranks candidate p-value intervals across sites using the pooled counts, and each site's false discoveries are estimated from its own synthetic counts under a per-site share of the level. The procedure needs no knowledge of the null proportions, uses every p-value for both selection and inference, and controls $FDR\le\alpha$ at every sample size for any fixed assignment of hypotheses to sites, assuming only that the null p-values are independent uniforms, independent of the non-null p-values. It keeps the original $O(\sqrt m\log m)$ communication, $m$ being the total number of p-values, when $N=O(\sqrt m)$. We also give a sample-splitting alternative, cross-fit greedy aggregation, with finite-sample control under a random-site model, and we quantify the selection bias behind the original procedure's failure. In a monitoring-network simulation the budgeted procedure retains most of the power of its heuristic counterpart at moderate-to-large site sizes.

Context parameterization enables large language models (LLMs) to internalize contexts into reusable model parameters, avoiding repeated processing across subsequent queries. However, existing methods typically assume static contexts and lack explicit mechanisms for distinguishing validity states under continual updates. To study this real-world scenario, we formalized the Memory Updating with Sequential Evolution (MUSE) task and constructed MUSE-bench to evaluate update incorporation and unaffected-information preservation. The resulting challenge requires preserving the global state while adjusting the contribution of memory evidence. Motivated by this, we proposed PLUME, a training-free method that constructs a global update representation, activates memory evidence to form a local parameter view, and adaptively integrates their predictions during decoding. Comprehensive evaluation on MUSE-bench demonstrated PLUME's effectiveness in sequential evolution settings, yielding relative improvements of 29.9% in average ROUGE-L Recall and 54.9% in LLM-as-a-Judge. Our codes are available at: https://github.com/xiaobingshi-LLM/PLUME.

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition whose early diagnosis remains challenging because conventional clinical assessments are often subjective, time-consuming, and require expert evaluation. Gait provides a promising non-invasive behavioral biomarker for auto- mated ASD screening; however, existing studies have primarily relied on single-dataset evaluations, convolutional architectures, and descriptive summaries of cross-validation performance without formally assessing fold-to-fold stability. This study addresses these gaps with an attention-enhanced Transformer framework for ASD classification, evaluated on two structurally different 3D gait feature representations: precomputed statistical gait descriptors and raw biomechanical ground-reaction- force measurements. Under five-fold cross-validation, the proposed framework achieved 99.00% accuracy, 99.02% precision, 99.00% recall, 99.00% F1-score, and 99.00% specificity on the public Kinect-based benchmark, exceeding the performance of the compared state-of-the-art methods. On the independent private force-plate dataset, it achieved mean values of 95.00% accuracy, 93.81% precision, 96.67% recall, 95.13% F1-score, and 93.33% specificity.

Large language models (LLMs) are increasingly deployed with external tools that extend what they can do beyond their own knowledge. Tools help on tasks that need external information, but their availability may also change how a model handles questions that do not need them. Prior work has mostly asked whether models select and use tools appropriately; whether an unnecessary tool changes the correctness of answers has received less attention. We ask whether making a related but unnecessary tool available affects a model's ability to answer from its own knowledge, and whether a preceding tool interaction changes this behaviour. We construct 500 query pairs across 10 knowledge domains. Each pair consists of a tool query, which needs the domain's tool, and a closed-domain query, which does not. Six LLMs are evaluated with the tool unavailable, available, and available after a prior tool call. Across 3,000 baseline trials the pooled answer rate is 98.2%. When an unnecessary tool is available it falls to 63.5%, with large differences between models. The decrease occurs even when the tool is rarely called, so it cannot be explained by unnecessary tool invocation alone. A one-sentence scope-aware system instruction recovers most of the lost answers.

Integrating contact information into visuomotor policies remains an open problem. Touch is essential to robust manipulation, yet most modern policies, including pretrained vision-language-action (VLA) models, operate from vision and proprioception alone. Existing approaches to closing this gap require specialized tactile hardware, add separate tactile encoders, or commit to non-image policy backbones, all incompatible with the modern paradigm of image-conditioned policies built on pretrained 2D visual representations. Our key insight is that the bottleneck is not the contact information itself, but how it is delivered: when contact signals are exposed in the same spatial frame as the scene the policy already attends to, they become directly usable by any image-conditioned policy without architectural changes. We operationalize this insight in Visible Touch, paired with a custom low-cost magnetic contact sensor that is open-sourced and fabricated from off-the-shelf parts via a parametric CAD-to-mold pipeline. Across the LIBERO benchmark, Visible Touch improves BC-Transformer success by 15.7 percentage points on average in the 2-view setting, with similar gains in the 1-view setting; controlled comparisons show that the contact-integration strategy strongly affects how effectively tactile information is used. The pattern holds when fine-tuning pretrained VLAs: miniVLA on LIBERO gains 25 percentage points on average, and $\pi_{0.5}$ on four real-world contact-rich tasks gains 30 percentage points with our custom sensor.

Steering language models using a set of contrastive representations has been a canonical and computationally efficient method for controlling model behavior. Despite this success in controlling certain model behaviors, the effectiveness of activation steering varies markedly across concepts; the generalization properties of steering vectors are often considered a function of the dataset used to construct them. We make this dataset-dependence claim more rigorous and show that simple separation metrics strongly correlate with the downstream steerability of language models across diverse settings, even after controlling for layers and dataset effects. Beyond prediction, we provide evidence from a synthetic superposition experiment that separation metrics are strongly correlated with alignment between the empirical and true feature direction. Our results suggest that simple separability statistics can serve as practical diagnostics for when steering vectors are likely to work.

This work presents an algorithm, together with its correctness proof, to determine the minimum perimeter polygon (MPP) for digital objects given as regular complexes in the triangular plane tiling. Such objects are edge-adjacency-connected sets of triangle tiles that have no end tiles, and the point set union of all their tiles forms a simple polygon. Nevertheless, the boundary paths of the objects are not assumed to be simple. Then the MPP is a weakly simple polygon that coincides with the relative convex hull (i.e., geodesic hull) of a set $A$ with respect to a simple polygon $B$, where $A\subset B$, but $A$ is not necessarily a polygon, in fact it is generally not connected. Our MPP algorithm relies on constructing and iteratively constraining cones of visibility through forthcoming boundary tiles, it uses the structure of the canonical boundary path, the MPP frontier is the shortest polygonal curve following this path. We also propose a boundary tracing algorithm to obtain such paths from the objects.

Vision-language-action (VLA) deployment can reduce inference latency while changing closed-loop task behavior. We evaluate HuggingFaceVLA/smolvla_libero on an RTX 2060 (6 GB) in LIBERO Spatial and Object (MuJoCo 3.3.2, LeRobot 0.6.1, seed 42), comparing PyTorch+AMP with ONNX Runtime CUDA Execution Provider (CUDA EP). The main evaluation uses 100 episodes/suite; a paired rollout uses 300 episodes/suite. PyTorch+AMP reaches 70.0%/88.0% Spatial/Object success at 1181 ms p99. Requested-FP16 and requested-INT8 ONNX reduce tether-inspect p99 to 601 ms and 532 ms, while Spatial success falls to 41.0% and 40.0% and Object remains at 89.0%. A graph audit shows those artifacts are byte-identical FP32 graphs, so the requested-INT8 row is not operator-level INT8 quantization. A static language-width ablation (16/24/32 tokens) yields Spatial success of 41.0%, 75.0%, and 71.0%; widths 24 and 32 recover much of the Spatial drop while Object success and uniform-bench latency stay approximately stable. Width-24 ONNX Spatial success is comparable to the PyTorch+AMP baseline at roughly half the latency (Wilson intervals overlap; two-proportion chi-squared p=0.53). Context width is an important contributor in this stack; it does not account for every PyTorch-vs-ONNX difference. Deployment evaluation should jointly report latency, artifact inspection, interface constraints, and closed-loop success. Code: https://github.com/rafiqul713/smolvla-libero-onnx.

Kinship verification is a task involving determining whether two individuals share a first-order kin relation. To tackle this task, we propose CONVTRAP-TN, a new architecture for audio-based kinship verification, and conduct an ablation study on the proposed model. To the best of our knowledge, we are the first to apply the successful transformer architecture to the task of audio-based kinship verification. Furthermore, we also collect a custom speech dataset, ARKIN, which accurately reflects everyday recording conditions. We do this because only a few speech datasets with kinship labels currently exist, all of which either source extremely noisy in-the-wild data from the internet, or instruct speakers to record in specific environments. These settings fail to reflect real-world scenarios where users record on personal devices under unrestrained conditions. Additionally, we perform a series of preliminary baseline experiments on the collected dataset, including speaker verification and recognition, speech recognition, age estimation, and kinship verification, as well as cross-dataset kinship verification experiments to show that existing methods are not robust across datasets.

A transformer language model is trained to respond to any prompt, but each deployment asks only a narrow range of questions: a support assistant sees delivery complaints, a coding tool sees Python. Every deployment nonetheless pays the same computation per token. This paper measures how much of that cost is avoidable when the range of prompts is known in advance. The mechanism examined is early exit: a small, trained component - called a readout - is attached to an intermediate layer and proposes a token, and a confidence test decides whether to emit it or to run the remaining layers. The models are frozen, and the only supervision used is the model's own output on ordinary traffic. Three findings are reported. First, achievable savings depend strongly on the kind of traffic: at half depth on a 1.5-billion-parameter model, 96 percent of tokens could be emitted early for arithmetic word problems and 8 percent for Chinese-language explanations, at matched token-level fidelity to the full model (a measure whose limits the third finding exposes). Second, of three ways a deployment might use knowledge of its traffic, only customizing the threshold for exiting early is worthwhile: calibrating it per deployment raised exit rates by up to 59 percentage points across three models, and by more than 10 points on most corpora tested. Third, token-level fidelity - the standard evaluation measure in the early-exit literature - fails in domains where tokens can be checked against ground truth: on arithmetic word problems, three models each answered sixty questions correctly when run in full, and between 10 and 28 correctly under early exit, in the configuration that scored highest on fidelity. The intended setting is small models on personal devices, where generation is limited by memory bandwidth rather than computation.

Large language models (LLMs) can struggle with time-series question answering (TS-QA), especially when numerical signals are serialized as text and require explicit computation. Tool-augmented approaches improve performance, but existing systems often intertwine language reasoning, computation, and perception, making it difficult to determine which components drive the gains. We present T-SMART, a neurosymbolic framework that separates these roles: a frozen LLM interprets questions and selects operations, deterministic tools perform numerical computation, and structured perception is invoked only when needed. Controlled paired ablations show that deterministic computation provides the dominant benefit, improving accuracy by 31.7 percentage points over direct LLM reasoning on serialized time series, while language understanding and perception offer smaller complementary gains. These results indicate that tool-augmented TS-QA benefits primarily from reliable numerical execution rather than additional language-model reasoning and provide a controlled framework for analyzing component contributions in neurosymbolic time-series systems.

We study a class of distributionally robust optimization (DRO) problems for the statistical risk problem, formulated as minimax problems over the product of a Euclidean space and a Riemannian manifold. Because the resulting minimax landscape is nonconvex nonconcave in general, no globally convergent first order method is known to be available. We instead introduce the notion of a basin saddle point, a Nash equilibrium defined locally on the Cartesian product of a $\delta$ basin around a connected component of the local minima critical set and a geodesic ball on the measure manifold. We develop an abstract convergence framework for a Riemannian gradient ascent multistep descent iteration to a basin saddle point under a local Łojasiewicz type growth condition, with exponent $\beta \in (1,2]$, in the $\delta$ basin around connected components of the local minima critical sets. Under Lipschitz regularity of critical sets we establish linear convergence for $\beta = 2$ and polynomial convergence for $\beta \in (1,2)$ to a basin saddle point, with explicit dependence on the sectional curvature of the manifold. We then instantiate this framework for the statistical risk DRO problem over Gaussian measures, where the ambiguity set is naturally modeled as the product of Euclidean space and the Bures Wasserstein manifold of covariance matrices, which we relax to a penalized DRO formulation. We derive nonasymptotic Hessian estimates for the resulting Lagrangian, establish existence and local uniqueness of its maximizer, and prove that an alternating Riemannian gradient scheme converges to a basin saddle point of the penalized DRO problem, recovering the linear and polynomial rates of the abstract theory with all constants explicit in terms of data dimension, loss moments, and the reference covariance.

As Alzheimer's disease (AD) has increasingly become a major global public health issue, speech-based AD detection has attracted widespread attention. However, most existing methods are trained and evaluated on a single dataset, often leading to severe cross-domain performance degradation due to reliance on dataset-specific artifacts rather than disease-related speech cues. In real-world applications, reliable Alzheimer's disease detection requires models that are robust to variations in recording environments, speakers and data collection conditions. To address this challenge, this paper adopts unsupervised domain adaptation to learn robust, domain-invariant feature representations in the absence of target-domain diagnosis labels. On this basis, a novel unsupervised domain adaptation method, Iterative Adversarial Self-Training (IAST), is proposed. Results demonstrate that IAST significantly improves the generalization ability and robustness under various cross-domain settings.

As LLM agents become integrated into increasingly complex workflows, they must continually acquire new capabilities while retaining competence on previously learned tasks. Lifelong agents address this through experience replay, injecting past interactions into the prompt to leverage prior experience during inference. However, replay is not free: every replayed trajectory competes with retrieval, reasoning, tool use, and verification for the same limited prompt and compute budget, making effective resource allocation essential. Existing approaches allocate these resources using fixed replay policies, regardless of whether replay is beneficial for the current task. We identify this as inference-time memory allocation, a distinct problem class for lifelong agents, and introduce LIMBO: the first online framework to our knowledge that treats memory as a controllable inference-time resource and jointly optimizes memory strategy and inference budget for each incoming task. Unlike prior approaches that fix the replay policy or require model weights, teacher supervision, or offline retraining, LIMBO learns this allocation online in a single pass, explicitly balancing task performance and inference cost without modifying the underlying agent. Across three LLM backbones on LifelongAgentBench, LIMBO achieves better cost-accuracy tradeoffs than state-of-the-art memory-augmented baselines and nearly matches all strongest such baselines at up to ~83% lower inference cost (~53% on average). LIMBO adapts its policy across models and environments without retraining, demonstrating that effective allocation can be learned online rather than manually specified.

Many analytics tasks require secure computation over encrypted data. In particular, fine-grained data such as pixel-level images require higher precision, as every pixel can directly affect outcomes in tasks like tumor segmentation and anomaly detection. While Multi-Party Computation (MPC) is interactive, Differential Privacy (DP) protects only aggregate values, and Partially Homomorphic Encryption (PHE) lacks multiplicative support, none of them can efficiently handle fine-grained data analytics. Fully Homomorphic Encryption (FHE) uniquely enables arbitrary operations on encrypted pixels but remains computationally expensive, posing significant challenges for both software and hardware accelerators. We present PixCrypt, a caching-based acceleration mechanism for fine-grained fully homomorphic encryption. PixCrypt replaces expensive fresh ciphertext generation with cache retrieval and coefficient-level operations across CKKS, BFV, and BGV, while randomized reconstruction ensures that ciphertexts do not repeat. Its linear noise growth reduces the need for bootstrapping and lowers NTT load, improving hardware accelerator efficiency. This design yields up to 35x faster fine-grained encryption and maintains IND-CPA (Indistinguishability under Chosen Plaintext Attack) security. Experiments on five real-world pixel-level image processing tasks show that PixCrypt significantly improves the practicality of FHE for privacy-preserving analytics.

Precise manipulation in dynamic environments, whether induced by a mobile robot base or a target with unknown motion, remains a major challenge in robotics. Manipulation in dynamic environments introduces substantial uncertainty, which fundamentally conflicts with the tight precision requirement of precise tasks such as peg-in-the-hole. We propose a Vision-Force Admittance Learning (VFAL) framework that fuses asynchronous visual feedback with a high-frequency force-based model, using visual pose estimations as a regularization term. VFAL adapts insertion strategies online to dynamic motion while maintaining millimeter-level precision. To obtain robust, low-frequency pose information, we employ state-of-the-art vision foundation models for visual pose estimation. Additionally, we incorporate failure recovery mechanisms to enhance overall robustness. We validate our approach in real-world experiments, demonstrating high success rates and strong adaptability to various pegs and dynamic environments.

Repeated AC power-flow calculations are common tasks in transmission system operations, in particular for contingency analysis and remedial-action assessment. For large networks, their cumulative runtime can become a computational bottleneck in operational processes. This paper develops a sparse reformulation of the generalized bus-admittance power-flow method known as PFPD. Loads and generators are represented by fixed shunt admittance terms on the diagonal of the admittance matrix, while corrective nodal currents are iteratively computed to match the constant-power and regulated-voltage constraints. In contrast to the original formulation, the slack bus is treated as a fixed-voltage boundary and removed from the admittance block decomposition. The resulting iteration reuses sparse LU factorizations of the initial generalized non-slack matrix and its PQ block, without explicitly forming dense inverse matrices. The same formulation admits two initialization modes: an unsolved base case using the same flat-start shunt heuristic as in the primary PFPD method, and repeated post-action calculations initialized from a solved operating point. Localized topology and parameter changes are expressed as low-rank admittance updates and the resulting admittance matrices are inverted by means of the Woodbury identity. An optional local-network formulation can provide an warm start before full-network refinement. N-1 experiments on the 1354-bus and 9241-bus PEGASE systems and the 6717-bus synthetic Texas system yield average per-contingency speedups between 14.4 and 18.0 relative to pandapower. On transformer tap-position actions, the method is 2.8–2.9 times faster than pandapower and 7.2–29.9 times faster than PowSyBl OpenLoadFlow.

Ultra-High-Definition (UHD) video presents significant challenges for efficient storage and real-time decoding. Learning-based methods, such as Neural Video Compression (NVC) and Implicit Neural Representations (INR), achieve competitive rate-distortion performance but suffer from high decoding latency and excessive memory usage. Meanwhile, Gaussian Splatting has recently attracted attention in the computer graphics community due to its ultra-fast rendering and high-fidelity visual quality. Despite these advantages, its application in video compression remains largely unexplored. To bridge this gap, we propose a real-time video compression framework that represents and compresses a Group of Pictures (GOP) using a coarse-to-fine multi-scale 2D Gaussian Splatting (2DGS) structure coupled with a lightweight deformation network. Experiments demonstrate that our method delivers rate-distortion performance in LPIPS that surpasses H.265 and other state-of-the-art learning-based video compression methods. Our work demonstrates the potential of Gaussian Splatting as a practical solution for efficient high-resolution video compression.

We derive exact local responses for attention interventions, allowing candidate edits to be scored from a cached baseline and one backward pass. The starting point is the RoPE derivative $\partial_p z(p) = A z(p)$: its integral gives the finite positional displacement, which we carry through the softmax without linearising either rotation or normalisation. The resulting predictions achieve 95.36–96.52% sign accuracy across 92,160 executed positional edits on 768 held-out prompt sets, reducing answer-margin MAE by 73.6–82.5% against the positional Jacobian and by 36.2–50.9% against zero. For simultaneous key and value edits, the same divided-difference calculus isolates the interaction term $C_{KV} = \sum_j (p'_j - p_j)\,\varepsilon_j$, which is omitted by adding separate attributions. Retaining it reduces downstream margin MAE by more than a factor of nine in every setting of a 5,120-intervention sweep across two Qwen sizes, two tasks, and multiple layers; reductions against a quadratic interaction correction are 75.9–98.5%. Exactness concerns the edited attention write; downstream predictions contract that response with a baseline gradient and are evaluated by native execution. The calculus also yields a KL certificate for local approximation error, an exact query-conditioned gradient-step representation whose curvature identifies attention-preserving query directions, and minimum-norm query control. Sparse evaluation supports candidate ranking and cache decisions under explicit local distortion criteria.

Blocking flow-type maximum matching algorithms are based on finding maximal sets of shortest augmenting paths. They run in $O(m\sqrt{n})$ time, on both bipartite [HK73, Din70, Kar73a, Kar73a] and nonbipartite graphs [GT91, Gab17, Vaz24], but this time bound can be improved if the input is constrained. In this paper we consider $d$-regular bipartite and nonbipartite graphs. Previous algorithms show that a perfect matching in $d$-regular bipartite graphs can be computed in near-linear time deterministically [COS01] or sublinear time with high probability [GKK13]. On $d$-regular non-bipartite graphs, a $(1-1/(d+1))$-approximation can be computed in sublinear time $O(n \log n)$ with high probability [DH25], and hence a maximum matching can be computed in $O(n^2)$ time, w.h.p., which is slightly faster than the best deterministic algorithm for regular graphs [Yus13], running in O(n^2 log n) time. We prove that any blocking flow-type maximum matching algorithm based on finding shortest augmenting paths runs in $O(n^2)$ time on d-regular graphs, both bipartite and nonbipartite. On nonbipartite graphs this is an asymptotic improvement over $O(n^2 \log n)$ [Yus13] and an improvement over $O(m\sqrt{n})$ [GT91, Gab17, Vaz24] when $d = \omega(\sqrt{n})$. It also improves [DH25] by making its $O(n^2)$ bound deterministic. However, the main take-away message is that no new algorithms are needed: the "classic" matching algorithms automatically outperform [Yus13, DH25]. We also consider extensions of our results to graphs that are only "nearly regular," meaning that their degrees all lie within a specified range, $[d, \Delta]$.

Metric differential privacy (mDP) is well suited to structured secret domains, but directly constructing utility-aware mechanisms over large or fine-grained domains is often computationally prohibitive. We study extension-based mDP design, where a mechanism is first specified on a finite set of seed records and then extended to a larger target domain. To our knowledge, this is the first work to systematically formulate extension as a general design paradigm for mDP rather than a method-specific construction. We present a graph-based extension framework, identify three requirements for correctness, local mDP constraints, overlap consistency, and successor-level mDP preservation, and show that, under these conditions, the induced global mechanism is well defined and satisfies $\epsilon$-mDP on the target domain. We further instantiate the framework with a tree-based extension algorithm for multi-resolution grids, where multi-dimensional extension is realized through one-dimensional interpolation and dimension-wise composition. Experiments on road-map datasets demonstrate that our approach achieves a strong utility-scalability trade-off while preserving exact mDP guarantees.

Medical image analysis is often hindered by biased datasets, which can lead to biased models and limited clinical applicability. A promising strategy for mitigating such biases is to augment training data with synthetic images. Counterfactual (CF) generation is one such strategy, though the term is used in two different senses: in some works, CFs are produced through causality-based interventions derived from structural causal models, whereas in others, they are produced by non-causal image edits or conventional conditional generative models, such as altering anatomy or adding pathologies. In this work, we study this distinction and evaluate its practical consequences for medical image augmentation. We compare three conditioning strategies: $\textit{Deterministic}$, which changes selected variables while holding the remaining variables fixed; $\textit{Undirected}$, which updates variables according to learned statistical associations without assigning causal directions; and $\textit{Causal}$, which propagates interventions along a directed causal graph. We analyse how these choices affect the resulting images, and explore when causally grounded methods improve dataset augmentation or bring limited benefit. In particular, we assess downstream performance and fairness, where fairness refers to reduced sensitivity to dataset biases across sensitive subgroups. Our experiments demonstrate that using a causal approach to synthetic training data generation can lead to tangible benefits, with these insights offering valuable guidance to machine learning practitioners for the effective design of data generation protocols.