Papers

Today, progress in open-weight language models enables systems capable of writing, executing and debugging code while still running on a single workstation. Most language-driven robots give the model a fixed action interface or a trained policy. Generalizing to a new task therefore means more engineering effort or more data collection, both time-consuming. We investigate whether a local open-weight vision-language model can control a robot and one-shot generalize to new variations of a task without new human programming or training. We let a local open-weight VLM, Qwen3.8-27B, drive a UR3e robotic arm from a coding-agent harness. It writes and runs its own code above a service that implements kinematics, safety limits and classic computer vision techniques. We investigate if this system is capable of generalizing to unseen tasks. Specifically, we test it on nine tasks built from children's toys designed to probe generalization capability across various object characteristics: color, size, shape, and task variation of those. With five trials for each task, we observe generalization in 30 out of 45 trials with durations ranging from 3.4 to 67.5 minutes depending on task complexity. We further test if there is a speedup when an agent is asked to redo the task after successful completion. This resulted in a 50% reduction in duration, indicating that there is self-improvement over time. Finally, we expose the limitations of a local coding agent. We believe that solving those limitations combined with further investigation of self-improvement over time points at a direct path toward real-world deployment of a local coding agent.

We propose an adaptive predictive sampling and communication framework for real-time remote monitoring over packet-erasure channels. Rather than relying on a prescribed dynamical model or continuous sensing, our model-free method uses Taylor-expansion-based prediction to adaptively estimate local signal dynamics and proactively schedule the next sampling times. An analytical compensation factor accounts for packet losses to satisfy a prescribed reconstruction-error level. We develop adaptive sample-wise and episodic policies and evaluate their performance against event-driven and uniform sampling and communication baselines.

Radiomics provides quantitative descriptions of tumour appearance that may complement disease-specific foundation models in small labelled cohorts. We investigate this complementarity for computed tomography-based classification of clear cell renal cell carcinoma. Our framework uses radiomics to modulate RenalCLIP features through feature-wise linear modulation (FiLM), while retaining a direct radiomics contribution. Internal testing and external validation compare it with conventional fusion strategies and reference classifiers. The FiLM model achieves an area under the receiver operating characteristic curve (AUC) of 0.804 internally and 0.854 externally, with the highest mean AUC among the evaluated RenalCLIP fusion strategies in both cohorts. Pathway ablations examine the contributions of conditional modulation and the direct radiomics residual, while feature permutation highlights the role of tumour texture. These findings support radiomics as a useful complement to RenalCLIP in a small labelled cohort and identify FiLM as an effective approach to integrating their representations for robust renal tumour classification.

This study presents an interdisciplinary process for benchmarking service robots in public everyday environments, addressing the gap between laboratory metrics and real-world operation at technology readiness levels 6-7. Three robots were evaluated in three use cases: outdoor park cleaning, pedestrian underpass cleaning, and interactive assistance in a public library. Over three years (2023-2025), seven benchmarking events (a consensus workshop and six on-site evaluations, two per use case) assessed the robots in increasingly realistic settings, from controlled conditions to public operation. An interdisciplinary panel of experts in robotics, human-robot interaction, safety, and economic viability consolidated use-case-specific metrics into a shared evaluation concept refined across three phases. Rather than ranking the robots, the evaluation examined how task fulfillment, interaction quality, safety, and economic viability interact in the transition from laboratory prototype to operational system. Direct quantitative comparability across the heterogeneous use cases remained limited, characteristic of benchmarking at this maturity level. The process yielded cross-case insights: increasing environmental realism introduces challenges that uniform metrics capture only in part; the interaction-quality guideline works best as a modular instrument adapted to each use case; safety was assessed by occupational-safety and product-certification experts who adapted industrial test procedures for public settings; and economic viability proved a cross-cutting dimension. We conclude that benchmarking at higher technology readiness levels is well served by a shared procedure for selecting and documenting metrics across these four categories, with safety as mandatory, rather than by a fixed set of metrics: generalizability lies in the procedure rather than in identical metrics.

Calibration of language models – the alignment between expressed or implicit confidence and empirical correctness – is a well-studied subfield within NLP. Methods to measure it already exist. The problem is adoption: outside this subfield, NLP research regularly introduces new models, datasets, and benchmarks without checking whether the model's confidence scores are meaningful. We argue that this adoption gap is a major obstacle to trustworthy LLM evaluation. Miscalibration causes problems in two distinct areas: at deployment, where overconfident mistakes cause real harm, and inside the research pipeline, where methods like LLM-as-a-judge, synthetic data generation, and active learning rely on calibrated confidence without verifying it. Standard calibration metrics only require two inputs per example: a confidence score and a correctness judgment. Most benchmarks in use today already provide both, meaning calibration can be reported immediately. For open-ended generation, however, defining these two inputs is still an open challenge. We argue that each NLP subfield should pair its main performance metric with a calibration score and call for treating calibration as an essential property of every model rather than a niche topic.

While Chain-of-Thought (CoT) reasoning has improved the capability of language models, directly applying it to Spoken Language Models (SLMs) may introduce long silent intervals under the serial "think-then-speak" paradigm, disrupting real-time spoken interaction. To address this issue, we propose an asynchronous think-aloud framework for reasoning-based SLMs within the Thinker-Talker architecture. The framework maintains a primary reasoning stream for logical deduction and a lightweight think-aloud stream that generates short, task-grounded progress utterances conditioned on the user input and the evolving reasoning state. A dynamic balance strategy coordinates the two streams at runtime, triggering additional think-aloud speech to avoid silent gaps and canceling pending utterances when the final response becomes ready. Experiments on spoken reasoning and question-answering benchmarks show that our approach substantially reduces user-audible silence during reasoning while maintaining answer accuracy comparable to that of a serial "think-then-speak" baseline, demonstrating the potential of asynchronous think-aloud for responsive interaction in SLMs.

Recursive models can continue updating their latent states beyond their nominal inference budget, so an incorrect output at that budget does not show whether computation is unfinished or has entered a persistently unsuccessful regime. We study the dynamics of completion in attention- and MLP-based Tiny Recursive Models (TRMs) on 1,000 hard Sudoku puzzles. Extending recurrence from the nominal 16 steps to 512 steps increases cumulative exact-solve accuracy from 59.2% to 87.5% for the attention model and from 74.4% to 91.9% for the MLP model, solving more than two-thirds of the puzzles unsolved in the nominal budget. Across both architectures, latent-state motion drops sharply after the first exact solution. Completed states are typically locally contractive along the trajectory direction, even though the same local Jacobian retains strongly expanding directions. We characterize this phenomenon as trajectory-conditioned anisotropic stability. Perturbation experiments confirm this directional stability across both models. The multi-step fate of the maximally expanding direction differs: it is absorbed within 16 steps in the attention model but persists longer in the MLP model. The anisotropic-stability pattern also holds for a second attention checkpoint. Together, these results distinguish nominal-budget failure from completed computation and identify a common dynamical signature of completion across two recurrent architectures.

Automatic lip-synchronous dubbing requires a speech synthesis model to generate alternating voice and silence patterns in the target language that match the timing of the source clip precisely to ensure an optimal viewing experience. Prior works address this problem by conditioning the speech synthesis process on lip movements extracted from the video signal. In this work, we condition the speech generation on a binary voice-activity signal, which has a lightweight representation and can be produced in multiple ways. We show that the model follows the voice-activity signal with high accuracy while maintaining natural prosody and semantically appropriate pause placement within sentences, as demonstrated through extensive objective and subjective evaluations. By randomly masking this condition during training, we make the feature entirely optional during inference, allowing editors to enforce or relax lip-sync constraints when desired.

Training-free visual-token pruning often uses token importance, redundancy, or related selection criteria as proxies for safe removal. We show that these signals alone do not fully characterize removability, which is conditioned on both representation depth and the surrounding deletion set. Controlled interventions demonstrate that removing the same tokens at different depths produces substantially different downstream perturbations, while changing only the deletion context at a fixed depth alters candidate marginals and pruning-boundary decisions. These findings show that token importance alone cannot determine when a token is safely removable or how its removability changes under joint deletion. Motivated by this perspective, we propose CoRePrune, a training-free two-stage framework. Progressive Perturbation-Aware Visual Pruning refreshes deletion effects as visual representations evolve, while Set-Conditioned Refinement reevaluates candidate rescue benefits under the current deletion set after visual–text interaction. Across five multimodal large language model backbones covering standard images, high-resolution inputs, and video, CoRePrune preserves performance under aggressive token budgets. On Qwen3.5, with a final budget of 128 visual tokens, it retains 90.3% of dense-model performance while reducing aggregate prefill time by 51.0%.

Social norms cannot be identified from behavior alone: the same cooperative equilibrium may reflect shared expectations, strategic incentives, or simple imitation. Yet in multi-agent large language model systems, prior work largely treats behavioral convergence as evidence of norm emergence. In this work, we introduce an evaluation framework that measures agents' reported empirical and normative expectations in addition to behavioral convergence. Through controlled ablations, we test the effect of expectation elicitation and isolate two collective mechanisms central to theories of norm formation—social learning through interaction and social selection through network-based group formation. We further test the stability of these resulting dynamics under adversarial disruption across four LLM families. We find that eliciting expectations increases cooperative contributions, while social learning stabilizes behavior, and social selection reliably identifies cooperators but provides limited behavioral reinforcement. Following disruption, normative expectations and behavioral coordination recover differently. Together, these results show that similar cooperative outcomes can arise from different underlying social processes. By making expectations observable, our framework allows us to attribute each mechanism's contribution separately, offering designers of multi-agent systems a principled basis for selecting the social processes that sustain cooperation.

Retrieving task-relevant code dependencies is critical for repository-level code generation. Existing approaches obtain dependency context through similarity-based retrieval, repository graphs, or LLM-driven exploration. A central challenge is to identify the dispersed dependencies needed to implement a functional requirement, rather than merely retrieve broadly related code. This paper presents FeatLens, a feature-guided dependency retrieval approach for repository-level code generation. FeatLens first builds an offline index linking natural-language feature descriptions to function-level code entities. Given a task requirement and target function location, it selects relevant features and constructs dependency seeds. It then expands the seed graph and applies semantic and structural heuristics to select dependencies for inclusion in the generation context. Experiments on DevEval and EvoCodeBench show that FeatLens achieves the highest dependency recall among the evaluated baselines at each fixed retrieval budget, reaching DR@15 values of 0.527 and 0.529, respectively. On DevEval, the retrieved context supports the highest non-oracle Pass@1 with both DeepSeek-V3.2 and GPT-5-mini. These results are obtained without LLM calls in the online dependency retrieval stage.

In this work, we present a linear Robin-type domain decomposition scheme for solving the mixed formulation of Richards' equation (mLRDD-scheme), governing flow in variably saturated porous media. Assuming a highly heterogeneous porous medium consisting of multiple blocks/layers of distinct materials, we apply non-overlapping domain decomposition to isolate individual materials, yielding near-homogeneous conditions within each subdomain. Richards' equation is discretized in time by backward Euler and linearized using the L-scheme. A Robin-type interface condition, consistent with the mixed formulation, is then derived to couple the subdomains. For spatial discretization, mixed finite elements are employed, ensuring local mass conservation and providing the flux variables consistent with the Robin condition. The convergence of the proposed scheme is rigorously proved. Heterogeneous, multidomain numerical examples in 2D/3D are presented to demonstrate the efficiency and robustness of the scheme, along with numerical validation of the theoretical convergence results.

Serverless platforms commonly rely on bundled, memory-centric configurations, where CPU capacity follows the specified memory size. Resource decoupling reduces this waste, but can create external fragmentation by producing diverse CPU-memory shapes that leave residual capacity stranded across nodes. Memory disaggregation and tiering can turn these resource holes into usable capacity by enabling elastic memory locality, where instances use different mixes of local and remote memory. In this paper, we present Memoryless, a fragmentation-aware resource manager that exposes memory locality as a serverless control-plane primitive. Memoryless jointly selects and places function variants that differ in their compute allocation and memory-locality ratio. This allows the scheduler to match instance shapes to fragmented node capacity while preserving SLOs. We implement Memoryless on top of Knative and evaluate it with trace-driven workloads. Compared to state-of-the-art serverless placement frameworks, Memoryless reduces node usage by up to 40% in steady state and 46% at peak, while keeping SLO violations within 3%. It also reduces CPU stranding by 44%, showing that elastic memory locality can convert fragmented node capacity into usable resources.

Scattered light is common in biomedical images, yet its removal remains challenging. The difficulty arises from three aspects: first, aligned scattered-light-free biomedical ground truth is often unavailable; second, scattering is coupled with weak illumination and sensor-induced noise; and third, many learning-based restoration models are computationally expensive for embedded devices in Internet of Medical Things (IoMT) scenarios. To address these issues, this paper proposes PP-Net, a hybrid physical-prior neural network for biomedical scattered light removal. The proposed method consists of three components: DFN-Net suppresses sensor-induced noise, ASAP estimates the scattering map and recovers a physics-based prior map, and GF-Net refines the prior map by fusing it with the denoised observation. To reduce the dependence on paired biomedical ground truth, a progressive synthetic training and cross-domain transfer strategy is developed. Experiments show that the physical-prior branch improves the peak signal-to-noise ratio (PSNR) by up to 1.26 dB on paired synthetic benchmarks. Under joint noise-and-scattering degradation, PP-Net improves PSNR by more than 10.8 dB and the structural similarity index measure (SSIM) by more than 0.62 compared with representative baseline methods. On real W2S biomedical images, the proposed method reduces the average Natural Image Quality Evaluator (NIQE) score by 43.3%. Edge deployment with RKNN conversion and INT8 quantization achieves an average inference latency of approximately 200 ms per $512\times512$ image over 360 test images. These results demonstrate that PP-Net provides an effective and deployable solution for microscopic imaging, endoscopic inspection, and edge-assisted biomedical analysis in IoMT scenarios.

Ensuring safety and scalability in Collective Perception Service (CPS) remains a key challenge for Cooperative Intelligent Transport Systems (C-ITS). Conventional CPS enhances perception by broadcasting Collective Perception Messages (CPMs). However, its reliance on transmitting a potentially large volume of context-irrelevant information at high frequency leads to network congestion, processing delays, and poor scalability. We propose a Context-Aware Adaptive Filter that dynamically adjusts CPM content and transmission frequency based on contextual relevance and situational criticality. By prioritizing safety-critical objects and interactions, the proposed approach prevents information overload while preserving timely updates for decision-making. An end-to-end SUMO–Artery simulation evaluates safety, decision-making efficiency, and communication cost under different computational capacity tiers and transmission rates. Results show that the proposed adaptive filtering mechanism achieves safety performance comparable to conventional CPMs transmitted at the maximum allowed frequency (10~Hz), while reducing communication volume by over 93% and preventing queue saturation. This demonstrates that context-aware adaptivity enables CPS to remain both scalable and safety-compliant across heterogeneous computing platforms.

A key factor in deciding whether to trust an automatic prediction is its confidence score, which should be calibrated to match the actual probability of the prediction being correct. Most confidence calibration metrics target binary or multi-class tasks, while multi-label calibration remains largely underexplored. Multi-label classification tasks, such as assigning medical codes to clinical notes or determining news topics, are usually dominated by a large number of negatives, i.e., labels that do not apply. We show that existing binning schemes to compute label-wise expected calibration error either underestimate the error, simply reflect label frequency, or suffer from many bins with very few instances. To achieve trustworthy label-wise calibration errors, we propose a new binning scheme that gives equal weight to positive and negative label assignments. Our empirical study demonstrates that in contrast to existing binning schemes, our new scheme results in meaningful estimates of calibration error in hierarchical and in extreme multi-label classification. We also show that calibrating confidence scores of large language models for multi-label predictions is an open challenge. Our detailed analysis lays the foundation for further research by providing a solid evaluation metric for measuring calibration in multi-label classification.

Vision-language-action (VLA) models often struggle in the precision-critical phases of multi-stage manipulation tasks. To mitigate this issue, VLA models can be used in conjunction with reinforcement learning (RL) specialists that are specifically trained to handle the precision-critical phases. However, the coordination between the base VLA model and the RL specialists, which dictates when a specialist should take over from the base VLA and vice-versa, remains an open research question. In this paper, we address this gap by introducing RouteRLT, a modular framework that coordinates a generalist VLA, used as the default controller, with designated precision-critical RL specialists. At a high level, our framework trains a phase-aware coordination mechanism that handles handoffs between the generalist and the specialists. We evaluate RouteRLT on the LIBERO and LIBERO-Plus benchmarks, as well as on a physical connector pickup and insertion task. Overall, we find that RouteRLT improves success on LIBERO, and retains net gains on LIBERO-Plus. On the physical task, RouteRLT completes 65.7% of trials, compared with 8.6% for the baseline. Altogether, these results demonstrate that learned coordination builds on generalist VLA capabilities to improve task completion in precision-critical manipulation.

Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. Radiomics provides structured tumour descriptors, whereas foundation representations offer transferable image features. However, it remains unclear whether radiomics still adds value beyond pretrained representations, and how 2D and 3D MedVAE encoders compare in this setting. We compared handcrafted radiomics, 2D MedVAE, 3D MedVAE, and their fusion for binary clear-cell RCC versus non-clear-cell RCC classification on KiTS23 under a unified preprocessing pipeline. Concatenation, cross-attention, and gated fusion were evaluated as representative integration strategies, and radiomics feature importance was analysed to support decision-centric interpretability. Fusion consistently improved discrimination over image-only MedVAE branches. The best overall performance was achieved by 3D gated fusion, with an AUC of 82.7%, outperforming the best 2D fusion model (79.6%), the radiomics baseline (74.4%), and the single-modality MedVAE branches. Ablation analysis further showed clear gains of the full fusion model over both image-only and radiomics-only variants, indicating complementary contributions from radiomics and image representations. These findings suggest that radiomics remains relevant for RCC CT classification in the presence of foundation representations, and that its integration with MedVAE is more effective in the 3D setting. More broadly, the study supports a complementary role for radiomics and foundation representations in clinically meaningful imaging decision support.

Pseudorandom number generators (PRNGs) constitute indispensable computational tools across multiple scientific domains, including Monte Carlo simulations, stochastic computing, and artificial intelligence (AI). The reproducibility of such applications critically depends on the ability of PRNG implementations to generate identical sequences across software environments when initialized from the same internal state. These algorithms enable the simulation of stochastic processes while providing deterministic and repeatable behaviour, thereby facilitating reproducible experiments. Modern PRNG implementations may be initialized through either a seed or, more accurately, an initial state that exceeds the capacity of a conventional integer seed. However, reliance on a simple seed alone frequently proves insufficient to ensure consistent program execution traces across different implementations. A natural assumption is that transferring the complete internal state of a generator should guarantee identical outputs regardless of the software library used. This study examines the validity of this assumption by investigating whether complete initial states can ensure cross-library fidelity and portability of PRNG streams. We focus on two widely deployed generators, Mersenne Twister and Philox, and evaluate their implementations across four major Python ecosystems-Random, NumPy, PyTorch, and TensorFlow. We compare the sequences produced by these implementations against those generated by the original reference algorithms under identical initialization conditions. Our results demonstrate that reproducibility cannot be assumed from PRNG state transfer alone, even when implementations claim to follow the same underlying algorithm. While fidelity was successfully achieved for several implementations, significant discrepancies were observed in others. Most notably, the Philox implementation in PyTorch exhibits fundamental incompatibilities with the reference algorithm, preventing exact reproduction of generator outputs across environments. These findings challenge the common expectation that access to a full internal state of a PRNG is sufficient to ensure reproducibility across software stacks. They further highlight that implementation-specific design choices can introduce hidden barriers to experimental replication, particularly in AI workflows that rely on multiple frameworks. This work shows that implementation fidelity of a PRNG is a necessary condition for scientific reproducibility and makes two primary contributions. First, it identifies practical guidelines for achieving reliable PRNG usage and reproducibility within the Python scientific and AI ecosystem. Second, it evaluates the extent to which cross-library portability and fidelity can be recovered through user-level techniques, without requiring modifications to library source code.

Anomaly detection systems are often trained using normal data alone, while model selection and evaluation typically require labeled anomalies. We study whether anomaly detection performance can be predicted without access to anomalous data. For kNN-based detectors, we derive a lower bound on the area under the ROC curve (AUC) that relates detection performance to the separation between inlier and outlier scores and to their respective variances. Under a local scaling model, we use this bound to characterize how density variation, intrinsic-dimensional heterogeneity, and cross-domain mismatch contribute to score variability. We then investigate anomaly-free model selection and show that inlier score variance alone does not reliably predict performance across different representations. To address this limitation, we introduce simple pseudo-anomaly probes that provide a reference for estimating relative score separation. Experiments on the DCASE 2022-2025 benchmarks, spanning four embedding models and 208 candidate systems, show that pseudo-anomaly-based estimators substantially improve anomaly-free model selection. In particular, diverse pseudo-anomalies enable anomaly-free model selection to outperform conventional development-set selection under domain shift. These results show that embedding-space geometry contains predictive information about anomaly detection performance while also highlighting the representation-dependent nature of inlier-only performance estimates.

Gaussian random fields are a versatile tool used in the fields of stochastic PDEs, uncertainty quantification, and geostatistical simulation. One way to obtain them is to use a truncated Karhunen-Loève expansion (KLE). Computing the expansion requires the leading eigenpairs of an $N \times N$ covariance matrix, where $N$ is the total number of grid cells. These are usually computed with a Krylov eigensolver, which relies on the covariance operator only within matrix-vector products. Stored densely, the matrix takes $\mathcal{O}(N^{2})$ memory and each product $\mathcal{O}(N^{2})$ time. For a stationary kernel on an equispaced grid, the covariance matrix becomes (block-) Toeplitz and the product evaluates in $\mathcal{O}(N\log N)$ time using FFT-based circulant embedding, without the need to assemble the dense matrix. In a matched single-threaded comparison, the median speedup of the eigensolve grows from $18 \times$ at $N = 4096$ to $183 \times$ at $N = 2^{15}$. This makes it possible to compute discretized fields that would otherwise be infeasible to compute in the standard formulation. We show that the same construction carries over to non-separable kernels as well as $d$ dimensions, using block-Toeplitz matrices. We extend it to piecewise-constant fields on arbitrary domains given as subsets of a tensor grid. Computational savings grow with problem size, and storage drops from $\mathcal{O}(N^{2})$ to $\mathcal{O}(2^{d}N)$.

We introduce CoDeR, a new paradigm for world modeling. Unlike existing video world models that implicitly represent world dynamics through visual observations, our system explicitly constructs an executable world with code and employs video generation models for visual realization. Specifically, we coordinate five complementary roles to translate high-level concepts into structured world rules, executable dynamics, and perceptual observations. This design enables long-term memory, open-ended interactions, autonomous world evolution, and multi-agent scenarios, where multiple entities can act, interact, and evolve persistently beyond the current observation. Extensive experiments demonstrate that our framework substantially extends the capabilities of existing world models, enabling long-term memory, open-ended interactions, autonomous evolution, and persistent multi-agent dynamics, while achieving state-of-the-art performance across multiple evaluation settings. Code and model weights will be made publicly available. Project Page: \href{https://becauseimbatman0.github.io/CoDeR}{CoDeR}.

AI agents are beginning to automate research and development across the AI stack, from improving training efficiency to optimizing inference. A natural next step is to improve the research efficiency of the agents themselves. When an AI research agent's own code is the object of optimization, each accepted rewrite becomes the agent that the next round edits. We refer to this loop as recursive self-improvement. Its significance lies in a long-standing trend, in which increased cumulative spending on R&D yields diminishing returns. Sustained self-improvement offers a way to counter this trend. We present AIDE^2, a system that implements this loop for a frontier AI research agent. It proposes changes to its own code, benchmarks modified versions of itself on a suite of AI R&D tasks, and keeps the changes that perform best on hidden evaluations. In an autonomous 8-day run, AIDE^2 discovered seven successive improvements, ranging from a new search policy to memory mechanisms that compress and manage the agent's growing context. These gains generalize to four held-out benchmarks spanning machine learning engineering, heuristic algorithm engineering, and physics-based weather forecasting, the last of which is out of distribution from the selection tasks. On all four, the strongest discovered agent matches or exceeds a human-engineered production research agent that ranks among the strongest on FML-Bench. On a separate held-out task family, the discovered agents also exhibit reduced reward hacking, a property the loop never explicitly optimized for: the rate falls from 55% to 32% during the run, 7 percentage points below the human-engineered agent. Together, these results show that an AI research agent can improve its own research efficiency through recursive self-improvement, and that these gains transfer to tasks and domains the loop never encountered.

Secure multiparty computation (MPC) enables mutually distrustful parties to compute on private digital inputs. We initiate the study of spatiotemporal MPC, extending this paradigm to functionalities whose inputs additionally depend on physical facts such as the parties' locations, times, or trajectories. Such protocols must simultaneously hide spatiotemporal information and ensure its physical consistency: a malicious party should not be able to make the functionality operate on a spatiotemporal input inconsistent with its actual physical state. The main conceptual challenge is to formulate extraction of spatiotemporal information within the simulation-based security framework. We introduce arguments of spatiotemporal knowledge, following the principle "I prove, therefore I am:" rather than defining physical presence directly through a mathematical relation, we define it operationally through the ability to complete a sound spatiotemporal verification protocol. Accordingly, an extractor recovers a spatiotemporal point from a successful prover and certifies its physical validity by using the extracted prover to succeed in an auxiliary spatiotemporal verification protocol. Building on this notion, we define universally composable (UC) security for spatiotemporal MPC, capturing privacy, physical consistency, and composability. We provide constructions achieving this new MPC notion. We first construct UC-secure commit-and-prove of spatiotemporal knowledge: in the CRS model under LWE against quantum provers without pre-shared entanglement, and in the QROM against quantum provers with unbounded pre-shared entanglement. Using these protocols, we obtain UC-secure spatiotemporal MPC from semi-honest post-quantum MPC. We also extend our framework to support quantum functionalities with classical spatiotemporal input.

This manuscript formalizes the most popular model validation tools used in general insurance actuarial modeling. These include graphical tools like calibration plots, actual-vs-expected plots, lift charts, Murphy diagrams, as well as classical statistical tools such as Bregman losses, deviance losses, elementary losses, Murphy's decomposition and Gini scores. Particular emphasis is placed on whether calibration and discrimination are studied under a policy-weighted or an exposure-weighted population measure. This distinction is crucial in ensuring that premium schemes are calibrated on the correct scale.

Let \(X=(X_1,\ldots,X_n)\) be uniform on the Boolean cube, and let \(Y\) be obtained by passing its coordinates independently through a binary symmetric channel with crossover probability \(p\). For a \(k\)-bit quantizer \(Q(X)\), reporting \(k\) input coordinates retains \(k(1-h_2(p))\) bits of information, making coordinate projections a natural quantization benchmark. For \(k=1\), this is the Courtade–Kumar conjecture: every Boolean function \(f\) satisfies \(I(f(X);Y)\leq 1-h_2(p)\), with equality for coordinate functions. We prove the conjecture in every dimension and for every crossover probability, without a balance assumption. The proof tracks the information gap relative to a coordinate as the channel correlation varies. After a monotone rearrangement, an entropy-flow identity relates the derivative of this gap to the edge boundary of the associated Boolean decision set. A sharp local entropy comparison, Fourier analysis, and logarithmic Sobolev estimates for pivotal sets imply that any positive gap must grow as the noise decreases, contradicting its nonpositive value at the noiseless endpoint. For \(k\geq8\), a coding-theoretic phenomenon emerges. We construct a shortened-Hamming-code quantizer that beats the coordinate benchmark for \(k=8\), and a direct-sum argument extends the failure to every \(k\geq8\). Thus structured coding can retain more information than coordinate selection. Exhaustive searches within several structured code families and Monte Carlo searches over random codebooks for \(2\leq k\leq7\) find that structured codebooks outperform random ones but remain below the coordinate benchmark. This motivates our conjecture that coordinate projections are optimal for \(2\leq k\leq7\).

Recent advances in Artificial Intelligence (AI)-powered Computer-Aided Diagnosis (CAD) systems have substantially improved breast cancer screening, diagnosis, and prognosis. Comparatively, postradiotherapy outcome prediction using paired longitudinal mammograms has received considerably less attention. This is largely due to the limited availability of well-annotated longitudinal datasets. Longitudinal mammograms, coupled with paired pre- and post-treatment information, provide a unique opportunity to characterize treatment-induced breast tissue changes following radiotherapy. The resulting learned representations can serve as a valuable asset for advancing personalized radiotherapy planning and post-treatment management. In this context, we propose Mammo-LIFE, a patient-level multimodal framework for post-radiotherapy outcome prediction that combines longitudinal mammographic features with patient-level clinical variables. The imaging branch processes paired pre- and post-treatment mammograms acquired from the four standard views using a mammography-specific encoder adapted via Low-Rank Adaptation (LoRA). Within each view, preand post-treatment representations are explicitly compared through a longitudinal comparison module to capture treatment-related changes. The resulting view-level embeddings are then aggregated using learned view-attention pooling to form a unified patient-level mammographic representation. Selected clinical variables are subsequently combined with the image-derived prediction probability through a late-fusion strategy. To evaluate the effectiveness of combining paired longitudinal mammograms with clinical information, experiments were conducted on an in-house clinical cohort using patient-level stratified five-fold cross-validation.

Drifting provides a direct route to one-step generative models, but applying it directly to stochastic transition modeling requires multiple samples of the next state conditioned on the same current state. Standard trajectory data, however, typically provide only one realized next state for each observed current state and therefore do not provide an empirical approximation of the corresponding conditional distribution over possible next states. We introduce block-triangular joint drifting, which instead applies a projected drift field to the empirically accessible joint distribution of consecutive states. Importantly, the block-triangular architecture preserves the current-state marginal while making its second component a direct sampler of the conditional distribution of possible next states. The resulting surrogate generates stochastic trajectories with one model evaluation per time step, without auxiliary generative steps between time steps. Numerical experiments demonstrate accurate marginal and trajectory-dependent statistics and favorable accuracy-cost tradeoffs compared with deterministic, diffusion-, flow-, and distillation-based generative surrogate models.

Dataset distillation (DD) compresses a large training set into a compact synthetic set while preserving downstream training utility. Although DD has been widely studied for images and recently extended to time-series forecasting, its application to human motion prediction remains largely unexplored. Human motion is high-dimensional and structurally coupled, and gradient matching (GM) in the original motion space optimizes many correlated variables without a prior on pose plausibility or temporal dynamics, which frequently yields implausible and unstable synthetic motions. To address this limitation, we propose a latent DD framework that regularizes distillation with a learned motion prior. Motions are first compressed by a residual-quantized variational autoencoder (RVQ-VAE), and distillation then updates only a learnable latent bank through the frozen quantizer and decoder. The pretrained decoder restricts synthetic motions to its output space, while residual quantization progressively refines the latent approximation across multiple codebooks and alleviates the representational bottleneck of single-stage vector quantization. Experiments on Human3.6M, CMU, and 3DPW with two prediction backbones show that the proposed framework outperforms direct GM in 27 of 30 evaluated settings and random subsets in every setting, and produces visibly more plausible synthetic motions in qualitative comparisons.

Adaptive regulation can itself perturb the state it is intended to stabilize. In replicated simulations of an adaptive agent, we compare external disturbance, persistent internally generated disturbance, and control-generated disturbance under regulation-first and disturbance-first ordering. Persistent internal disturbance produces the largest exposure and regulatory burden within the tested parameter grid. When positive controller updates generate an immediate disturbance cost, increasing that cost produces a nonmonotonic response: effective disturbance initially rises, variability across stochastic runs increases over an intermediate range, and corrective activity becomes strongly suppressed at higher costs. The results show how disturbance source and timing shape exposure and controller burden in this model. They motivate testing adaptive agents with distinct disturbance sources and assessing regulatory activity alongside exposure.