Papers

Efficient resource provisioning for large-scale workflows on cloud infrastructures is a critical performance engineering challenge. These workflows are often structured as directed acyclic graphs (DAGs), where under-provisioning can cause critical bottlenecks and over-provisioning leads to unnecessary costs. Accurate, task-level prediction of resource intensity (e.g., CPU load and memory usage) is essential for mitigating these issues. While task-level features are commonly used for prediction, the performance impact of the workflow's overall topological structure is often overlooked or assumed. The central question of our work is: To what extent does what part of the DAG topology influence task-level resource intensity, and what is the most effective way to model this influence? This paper presents a comprehensive benchmark to systematically quantify the impact of graph topology on task intensity prediction. We evaluate and compare a spectrum of modeling approaches. Our findings demonstrate that topology is a critical feature for accurate prediction. Models incorporating important topological information, even through simple handcrafted features, significantly outperform baseline models. We show that graph-native models provide the highest accuracy, achieving low mean absolute errors for both CPU and memory predictions, and can still be combined with simple topological features that they do not learn for better performance.

This paper investigates semantic secrecy in wireless status-update systems using Version Age of Information (VAoI). We model the fundamental tradeoff between informative updates and confidentiality (semantic asymmetry between the legitimate destination and the eavesdropper) using a three-node wiretap channel. To evaluate secrecy performance, we introduce the concept of a semantic secrecy region (SSR) and analyze it from a geometrical perspective. By developing a two-dimensional Markov chain, we derive closed-form expressions for the destination's average VAoI and the probability of semantic asymmetry at the eavesdropper. These results enable the joint optimization of transmission probability and power control. For Rayleigh fading channels, we characterize the optimal SSR boundary and power allocation. Numerical results validate our analysis, showing that optimized power allocation significantly enlarges the secrecy region compared with fixed-power benchmarks.

This study systematically evaluates self-evaluation-based uncertainty quantification across different language models of varying sizes on question-answering tasks spanning general to specialized knowledge domains. Using various self-evaluation methods where models judge their own predictions, we examine how model scale and domain specificity affect the quality of self-assessed confidence signals. Our results reveal that while accuracy predictably declines with smaller models and more specialized domains, the reliability of self-evaluated confidence remains largely stable across both dimensions. This independence means the most capable model is not necessarily the best at self-assessing prediction reliability. These findings suggest that smaller models can achieve reasonable self-assessed confidence despite lower accuracy, making them viable for resource-constrained deployments.

Teams of autonomous agents, including large language model (LLM) agents, must coordinate over scarce and unreliable wireless links. We propose goal-oriented semantic communication (GOSC), a closed-loop co-design that jointly decides what each agent sends, when it sends it, and how reliably it is transmitted, based on each message's value to the team task. An edge broadcast of the team's common knowledge closes the loop by updating these values. We prove that a message is sent only if its value exceeds the cost of delivering it and that more valuable messages receive more robust transmission rates, and we show that the scheduler solves each scheduling step exactly whenever the radio budget is not saturated, which held in 95% of scheduling decisions. In search-and-rescue missions validated on unseen scenarios, GOSC meets the same mission targets as carefully tuned periodic semantic schemes with 1.2–8.5 times fewer uplink channel uses. In most settings, this advantage persists with realistic packet overheads, reaching 16.6 times fewer uplink channel uses and 13.8 times lower cost when downlink costs are included; in the rescue task, it also persists when all agents share one uplink. Rough value estimates suffice, whereas values that ignore message content can fail. With three different LLMs, GOSC uses 3.2–3.5 times fewer channel uses, while completion-time gains depend on the model.

Autonomous agents increasingly rely on memory to generalize beyond their training environments. However, agents are bounded by what they have seen and believed, and leveraging such memories in unseen environments can introduce biases into their internal beliefs. We formalize this phenomenon as false memory, which can arise from spurious correlations, environment shifts, and knowledge conflicts. Despite its importance, false memory is difficult to evaluate because it stems from agent internal beliefs and is easily confounded with ordinary generalization failures. Therefore, we propose FAME, a training-free framework that evaluates false memory through the evolution of agent beliefs under counterfactual reasoning. Specifically, counterfactual scenarios reveal how beliefs change as the latent concept of memory shifts under hypothetical interventions; thus, measuring the resulting concept drift provides a signal for distinguishing faithful versus false memory. Such concepts can be estimated from agent hidden states before answer generation, avoiding the need for reward design or answer sampling. Empirical experiments reveal that simply monitoring answers often fails to detect false memory, while FAME achieves AUROCs of 76.2% - 96.7% across false-memory settings, and outperforms the best baseline by 3.4% - 23.3% across realistic benchmarks, spanning math reasoning (GSM-Symbolic), code generation (GitChameleon), and complex reasoning (BigBench-Hard). We further release corresponding counterfactual templates and facilitate future research on false memory.

A mesh-free numerical framework based on Kolmogorov–Arnold Physics-Informed Neural Networks (KAN-PINNs) is developed for the approximation of fourth-order elliptic boundary value problems, with specific application to the biharmonic equation governing thin plate deflection. Unlike conventional Multi-Layer Perceptrons relying on fixed nodal activations, learnable univariate functions parameterized via radial basis functions are deployed on network edges, while high-order differentiability is preserved through hyperbolic tangent activation mappings. The severe numerical stiffness inherent to fourth-order differential operators and fully clamped boundary conditions is addressed through a direct normalized residual formulation coupled with a hybrid, multi-stage AdamW-to-L-BFGS optimization pipeline. An automated 24/7 hill-climbing search protocol is implemented to systematically calibrate boundary penalty weights and optimization schedules. When evaluated on a smooth manufactured benchmark on the unit square, an error reduction factor exceeding $150\times$ is attained over successive iterations, culminating in a final relative $L_2$ error of $1.593 \times 10^{-5}$ ($0.00159\%$) and a training loss of $3.065 \times 10^{-6}$ utilizing only $7,801$ trainable parameters. These results demonstrate that high-order PDE problems can be accurately resolved using compact, mesh-free KAN-PINNs architecture without requiring auxiliary variable transformations or discrete mesh generation.

Pedestrian detection plays a crucial role in computer vision with applications in autonomous driving, surveillance, and public safety. However, real-world dense scenes bring severe challenges, including heavy occlusion, drastic scale variations, and strict real-time requirements. Existing lightweight detectors struggle to balance accuracy and efficiency while often neglecting quality-aware feature modeling and consistency between classification and localization, leading to unstable performance under crowded conditions. To address these issues, we propose DensePed-Lite, a unified framework built on a single principle: under occlusion the network should adapt its behavior to the quality of what it observes rather than assume complete information. This principle is realized at three points where occlusion does the most damage: unreliable confidence scoring (UQE), fragmented spatial coverage (MPSC), and incoherent multi-scale fusion (CTDM). The three mechanisms reinforce one another instead of acting in isolation, all without significantly increasing complexity. Experiments on CityPersons and CrowdHuman validate that DensePed-Lite achieves a superior accuracy-efficiency trade-off compared with recent state-of-the-art lightweight methods, making it suitable for real-time deployment in dense pedestrian scenarios.

In this work, we introduce a new clustering method, namely T-ARC (Topology-Aware Randomized Clustering), that corrects the geometric bias of K-means by embedding topological information directly into the optimization objective. Building on the assumption that the data admits an underlying hidden structure modeled via a latent graph, the idea is to uncover this information through the interplay between the standard K-means data-fidelity term and a graph-cut penalty, which discourages cluster assignments inconsistent with the connectivity structure of the data. To render this coupling tractable, the latent graph is modeled as a random realization from a Stochastic Block Model (SBM), whose scalar parameter is optimized within a Distributionally Robust Optimization (DRO) framework, yielding a closed-form proximal update. Both SBM and DRO are informed by a persistence-based similarity matrix derived from zero-dimensional persistent homology ($H_0$), which translates the multiscale connectivity structure of the data into a pairwise topological prior. The overall optimization proceeds via Block Coordinate Descent; convergence is established through a global Lyapunov functional: the deterministic blocks satisfy monotonic descent, while the stochastic graph update satisfies descent in expectation, so that the expected energy converges. Experiments on synthetic datasets with non-convex geometries and on random subsets of Fashion-MNIST show that T-ARC recovers latent topological structures where K-means fails, achieving the highest accuracy on curved and interleaved clusters while remaining competitive, and markedly more stable than K-means, on real data.

In federated averaging, local objectives can admit multiple optimal heads, making the aggregate depend on which heads clients return. We study this ambiguity in federated multivariate regression with private backbones and a shared linear head, using an unconstrained feature model (UFM) that treats training-sample features as free variables. We introduce a natural selection rule: each client returns the optimal head closest to the broadcast head. We show that global minimization with a vanishing proximal penalty on the head realizes this rule. When the clients' optimal Gram matrices and the initial shared Gram matrix are positive definite, the shared Gram matrix follows a closed recursion and converges to the unique Bures-Wasserstein barycenter of the clients' optimal Gram matrices. Even with this alignment, the limit generally differs from the centralized optimal Gram matrix. We decompose this gap into three positive-semidefinite terms arising from differences in client target means, covariance heterogeneity, and averaging the aligned heads. A correction based on a one-time exchange of target means and covariances recovers the centralized optimal Gram matrix in one round under exact local optimization and the same selection rule. We verify these results numerically in the UFM and test its predictions on five tabular and five image regression datasets using deep networks with feature regularization and long local training. In these experiments, ordinary training approaches the predicted barycenter, while a weak proximal penalty improves endpoint agreement and yields trajectories that closely follow the predicted Gram dynamics. The correction moves the final Gram matrices close to the centralized UFM prediction.

Rechtsrock is a subgenre of rock music that spreads right-wing ideology, often instrumentalized to recruit adolescents into the radical scene. Monitoring institutions counteract this by manually examining and, in some cases, banning extremist content; however, there are border cases that evade regulation. We present a study aimed at determining whether such a case, the band Frei$.$Wild, should be classified as politically right-leaning or as part of the general German rock genre. We sampled a German rock dataset and created a corpus for right-wing rock to use as reference in this analysis and found that we can confirm the intuitions from previous investigations that Frei$.$Wild successfully maintains an ambiguity with regard to their political affiliation. However, the tendency is towards the right-wing spectrum. Lexical analyses reveal nationalistic narratives and two high-performing classifiers (up to 97% ROC-AUC score) label more than half of their songs as right-wing extremist. Our analysis provides insight into how computational methods can improve the process of identifying right-wing extremist tendencies in music, especially in borderline cases like Frei$.$Wild. The code and data are made available for future research.

Quantum speed-ups have been obtained for many fundamental graph problems, including most variants of matching. A notable exception, however, is the maximum-weight perfect matching (MWPM) problem in general graphs with integer edge weights, which is arguably the most challenging variant of matching. We present a quantum algorithm for MWPM in general graphs that runs in \( \widetilde{O}(n m^{2/3}\log W) \) time, where $W$ is an upper bound on the magnitude of the edge weights. This is an improvement over the best known classical combinatorial bound of \( \widetilde{O}(m\sqrt n \log W) \) in the dense regime, where $m\ge n^{3/2}$. To the best of our knowledge, this is the first quantum algorithm to obtain an asymptotic improvement over the best classical combinatorial algorithm for the MWPM problem in general graphs. The running time of our method accounts for QRAM initialization and access overheads up to polylogarithmic factors, as well as all classical updates to the data structures. At a high level, our algorithm is based on a classical framework due to Duan, Pettie, and Su, but our algorithm requires replacing certain classical tasks with quantum methods, alternative analysis of classical procedures, and the use of alternative data structures that can be implemented effectively in the QRAM model.

This work proposes a mutual feedback architecture, MEQ, that refines the two inputs, of possibly different modalities, into a pair of coupled embeddings such that each embedding reflects the information of the other. The core idea is to incorporate continuous interchange of information between the two inputs. This idea leads to a mutual feedback architecture consisting of two components whose outputs are fed back into the other. The final output of this model is defined as the fixed point of this interaction. We provide theoretical analysis that offers interpretation of this model as well as design choices to prevent failure cases. We show the benefits of MEQ through classification and visual grounding tasks spanning various datasets. Quantitatively, our model outperforms or shows competitive performance on concatenation-based multimodal classification problems. Qualitatively, the proposed interactive mechanism allows the model to progressively refine the visual grounding when paired with complementary modality, thus demonstrating the power of mutual feedback under such settings.

Speech emotion recognition (SER) is the task of assigning emotion labels to utterances. Early systems relied on acoustic features, whereas recent approaches combine multiple modalities, most commonly speech and text. Still, performance remains poor on many datasets. Large language models (LLMs) have therefore attracted interest for SER, as they can process diverse inputs jointly with instructions. However, direct audio input raises questions of explainability. To address similar questions in image classification, concept bottleneck models were introduced. This work adapts concept bottlenecks to SER to examine how individual predictions depend on transcripts, acoustic descriptions and speaker attributes. Experiments test three LLMs on CREMA-D, IEMOCAP and MELD, with concepts extracted by separate tools. On scripted corpora, LLMs are strongly biased towards the transcript in the zero-shot setting, which lowers Macro-F1 from 27.8 to 5.8 on CREMA-D. Fine-tuning removes this bias, and the transcript raises Macro-F1 from 41.8 to 45.1. Removing speech rate changes 48% of Neutral predictions to Disgust on CREMA-D; removing intensity level on MELD changes predictions despite little change in Macro-F1. These findings show that aggregate performance changes alone do not capture the effects of concept removal on individual predictions.

Progressive autoregressive image codecs provide an appealing paradigm for generative compression by quantizing continuous latents into discrete tokens, transmitting coarse-to-fine prefix tokens and generating the remaining suffix tokens at the decoder. However, their reconstruction quality is fundamentally limited by two residuals introduced along this pipeline: the quantization residual, arising from information loss during discrete tokenization, and the generation residual, resulting from imperfect autoregressive generation of the suffix tokens. To address these limitations, we introduce ResARC, a residual-aware autoregressive codec that explicitly compensates for both residuals at the decoder. Specifically, we generate the quantization residual with a diffusion transformer conditioned on the autoregressive decoding context, while requiring no additional side information. In parallel, we compute the generation residual at the encoder and employ a learned Generation Residual Codec to efficiently compress and transmit it for decoder-side correction. The recovered residuals are then integrated with the reconstructed latent representation and decoded through an adapted VAE decoder. Extensive experiments demonstrate that ResARC achieves competitive perceptual similarity while substantially improving distributional fidelity over leading generative codecs across the ultra-low bitrate regime. Code and models will be released soon.

LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures. However, malicious instructions inserted into an otherwise benign skill can cause a benign user request to trigger dangerous Tool Calls, including data exfiltration, file deletion, or unauthorized code execution. This paper presents ActionGuard, which inspects skill-influenced Tool Calls immediately before execution. ActionGuard separates the target agent's action-generation context from the safeguard's authorization context. The target agent may use the original skill for planning, but the Reviewer does not receive the potentially poisoned raw skill text. Instead, it determines whether each action is justified by the trusted user request using a balanced skill profile, current and recent Tool Calls, and local script contents. ActionGuard intercepts each Tool Call at OpenClaw's before-tool-call stage and enforces the Reviewer's ALLOW or DENY decision under a fail-closed policy. We evaluate ActionGuard on 139 contextual and 180 obvious injections in a SKILL-INJECT-based setting against Dynamic Guardian and SkillGuard, using three open-source and two commercial Reviewer models. Each condition is repeated three times and evaluated using Attack Success Rate (ASR) and Task Success Rate (TSR). Overall, ActionGuard reduced ASR by 35.54 to 46.11 percent relative to existing safeguards and by 70.44 percent relative to No Safeguard, while maintaining high benign-task completion. These results show that execution-boundary authorization grounded in trusted user intent and runtime evidence can restrict unauthorized Tool Calls induced by skill injection.

Distributionally robust optimization (DRO) studies parameter estimation under uncertainty in the underlying probability distribution and has emerged as a principled framework for analyzing robustness and generalization. In particular, Wasserstein DRO, with distributional uncertainty induced by the Wasserstein distance, generalizes several popular regularizers. This paper studies Wasserstein DRO linear regression, unifying square-root Lasso and adversarial linear regression as important special cases. We prove that many properties of these two special cases carry over to this general method. In particular, we show (i) deterministic and non-asymptotic in-sample error bounds $O(n^{-1/2})$ in general and $O(n^{-1})$ under design matrix and sparsity conditions; (ii) insensitivity to the noise level, also known as the pivotal property; and (iii) solution equivalences for small and large ambiguity sets. The key proof step is to recast the method into a quadratic form, mimicking adversarial linear regression. We also show that the method can be solved efficiently, and we validate our findings through numerical simulations.

Interpreting properties of LLM-generated data is important for understanding its utility and limitations across learning tasks. In this work, we characterize synthetic data through sample-level learnability, studying variation among LLM families and scales, alongside human-written data as a reference. We first generate synthetic datasets spanning single- and multi-label classification, labeling, and tree prediction tasks. We then derive empirical data distributions from encoder training dynamics for both machine and organic data, and estimate the robustness of these distributions across encoders. Finally, we evaluate how data selection strategies based on these learnability signals affect both data sources differently.

Existing full-duplex speech benchmarks cover only subsets of real-time interaction behaviors, often under limited contextual conditions. We introduce DuplexAct-Bench, a bilingual benchmark that systematically covers six complementary behaviors, from interruption and yielding to proactive initiation, active silence, and backchanneling, across Pre-session, In-session, and No-explicit conditions. Across 1,290 English and Chinese streaming trials, we evaluate 12 full-duplex speech systems on both Timing and Content. Results reveal substantial variation across behaviors, conditions, and systems, as well as frequent mismatches between semantic quality and behavioral timing. These findings show that current systems remain far from robustly managing when, whether, and how to participate as real-time interaction unfolds. Project page: https://alitaxky.icu/DuplexAct-Bench/

Time series foundation models (TSFMs) commonly adapt to new data by attaching a single trainable head to a frozen backbone, a one-size-fits-all setup that underfits heterogeneous regimes. Replacing the head with a mixture of experts is the standard upgrade, but on instance-normalized backbones (the dominant TSFM design class) it fails: routing entropy collapses to zero and one expert absorbs every input, a failure we call normalization-induced routing collapse. Standard MoE rescue mechanisms do not repair it, because the cause is in the router's input, not its optimization. Pre-encoder normalization strips the statistics a router would need to tell regimes apart. A mutual-information decomposition makes this precise and yields a signal-ratio that, computed before training, predicts dataset vulnerability (Spearman $\rho = -0.88$). Eight causal controls, including a vision-modality replication, isolate instance normalization as the cause. The prescription is a minimal causal intervention: Raw-Routed Mixture of Adapters (RR-MoA), which routes on the raw, pre-normalization input. Under a strictly frozen backbone, RR-MoA wins 54/54 comparisons against the strongest fixed adapter and significantly outperforms LoRA, TRACE, AdaMix, and full fine-tuning. The effect generalizes across six backbones and an imputation task. Frozen RR-MoA also beats full fine-tuning by 12-79% (the Frozen Paradox); two architecturally distinct variants confirm the principle generalizes beyond this specific router.

Generative artificial intelligence can contribute to the representations, alternatives and evaluations through which executive judgements are formed. Existing research already explains important aspects of hybrid cognition, reliance, managerial agency and accountability. This article develops a narrower process challenge: locally competent human and AI contributions can still culminate in an inadequately warranted organisational commitment when established operational assumptions, uncertainties or dependencies are lost or transformed before authorisation. It proposes qualification attrition as the process through which such epistemically consequential content is weakened across successive transformations, and a formation–authorisation gap as the resulting discrepancy between the grounds required for warranted commitment and those that remain accessible, intelligible and challengeable to the authorising role. Executive judgement governance is defined through four dimensions: boundary setting, interpretive challenge, reliance calibration, and authorisation with answerability. Four propositions connect transformation, qualification attrition and governance arrangements to epistemic risk, accountability risk and judgement quality. The contribution is an integrative process theory of how distributed judgement formation can fail as a composition even where individual contributions, local reliance decisions and formal accountability arrangements appear competent.

Online reinforcement learning has been extended to flow matching for diffusion model (DM) image generation. However, this paradigm faces three limitations: (1) Window selection. Existing methods manually set the stochastic differential equation (SDE) sampling window, i.e., the denoising steps where exploration noise is injected. We instead determine it from each model's denoising trajectory. (2) Reward saturation. Current methods rely on scoring models trained on human annotations; we find that such scores are extremely high and nearly indistinguishable on the latest SOTA open-source DMs, making advantage estimation largely ineffective. (3) Sample inefficiency. A single scalar reward collapses different failure modes into almost identical scores, leaving minimal gradient guidance for targeted improvement. To address these issues, we propose CAST (Causal Advantage-Structured Training), an RL fine-tuning method for pretrained DMs, which (1) identifies the denoising step at which each model fixes the objects and their spatial arrangement in the image and uses that timing to set the SDE window, (2) decomposes each prompt via Causal Scene Graphs (CSG) into verifiable-atoms, i.e., minimal semantic units such as an object, count, attribute, or spatial relation that can each be checked independently, and rewards each atom separately, and (3) projects the signed atom-level advantages into pixel space through teacher-forced attention and uses them to spatially weight the SDE policy objective. We fine-tune two of the strongest open-source DMs, FLUX.2-dev and Qwen-Image-2512, with CAST, and evaluate them on GenEval 2, a compositional benchmark, and on Qwen-Image-Bench for overall quality. Within almost the same training budget, CAST's improvement over the base model on the most challenging GenEval 2 prompts is up to 3.07x that of Flow-GRPO, while overall generation quality also improves.

We compare the instance-wise, finite-sample risks of monotone spectral filters for linear regression, a broad class of estimators including principal component regression (PCR), gradient descent (GD), and ridge regression. We show that PCR dominates all monotone spectral filters: compared to any such filter, the risk of optimally tuned PCR is no bigger by a constant factor for all problems. Furthermore, the dominance is strong if the filter is separated from step functions (e.g., GD and ridge): there exist problem instances for which the risk of PCR is smaller by a polynomial factor in sample size dependence. Our comparison results show that PCR is optimal and thus admissible among monotone filters, significantly extending Wu et al. (2026)'s result that GD strongly dominates ridge. From a technical perspective, we establish new upper and lower bounds for general spectral filters, which are instance-wise sharp when specialized to ridge or GD, recovering or improving the best-known bounds.

In integrated sensing and communication (ISAC) systems involving multiple operators, unmanned aerial vehicle (UAV) tracking can benefit from sensing at multiple base stations, while raw sensing records, channel information, and transmit decisions remain local to each operator. The resulting problem is to obtain a reliable UAV prediction from different track estimates and use it to guide transmission without centralizing their data or control variables. To resolve this, we propose a two-timescale framework comprising slow-timescale motion-uncertainty calibration and online track fusion with predictive beamforming. Local radar innovations calibrate the uncertainty assigned by each tracker to unmodeled UAV motion, with only the resulting parameters shared across operators. During online tracking, covariance intersection (CI) combines local estimates without requiring knowledge of correlations between their estimation errors. The fused prediction then guides each operator's transmission design subject to communication QoS, power, and tracking constraints. We further establish exact rank one recovery for the communication covariances and finite interval bounds on local tracking uncertainty. Simulations show improved consistency of tracking uncertainty under substantial motion model mismatch. CI avoids overconfidence under correlated errors, while using the current fused prediction reduces RMSE by about 31% relative to transmission designed for communication alone, with less than 2% additional power. Ablation further shows that the power difference between current and outdated predictions is driven mainly by predictive covariance rather than predictive mean.

Large language models (LLMs) encode substantial latent geographic knowledge, yet they reason poorly over space and are unreliable when queried from coordinates alone. Useful behaviour emerges only when structured spatial context is supplied in the prompt. This raises a question geographic evaluation has left unexamined: once the right context is supplied, does the model reason from it, or override it with its own parametric recall? We take up this question with an open pipeline for network-based spatial context retriev-al. In it, the surroundings of a selected point are defined by the pedestrian street network, the area actually reachable on foot. Using only open data and open-weight models, the pipeline retrieves features from OpenStreetMap and the GHS-POP population grid, computes indicators over the network catchment in code, and injects them as a compact spatial brief. On this basis we build a faithfulness benchmark. It labels every claim a model makes by its source (grounded in the brief, or drawn from training knowledge) and its correctness, and it probes each case with a planted false premise that the brief refutes. We evaluate sixteen open-weight model configurations across three families (Qwen, Gemma and Llama, with Gemma in two generations), four size classes and, where available, both thinking and non-thinking modes, on three con-trasting cities, resampling every case over ten seeds. The results show that resistance to the planted premise varies more strongly by model family and generation than by scale, while brief-reading competence forms a partly separate dimension. These behaviours are not captured by conventional world-correctness scores or single-shot evaluation. We release the implementation, spatial briefs, model outputs, and claim-level labels as a reproducible workflow at github.com/perezjoan/NSCR-LLM.

Reinforcement learning with a verifiable reward (RLVR) offers a scalable approach to training language-model agents, yet sparse outcome rewards can leave early training with little signal for policy improvement. We identify an On-Policy Acceleration Phenomenon: in our main comparisons, RLVR initialized with on-policy distillation reaches high performance earlier in training and achieves both higher average performance during subsequent RLVR and higher final performance than the alternative baselines. Motivated by this observation, we study On-Policy Warmup (OPW), a teacher-guided stage in which the student trains with teacher supervision on its own interaction trajectories before transitioning to RLVR. Unlike imitation on fixed teacher-generated trajectories, OPW targets states induced by the student's own decisions, including imperfect actions and recovery situations. We provide a theoretical explanation by connecting on-policy reverse-KL distillation to trajectory-level distribution matching. Under a competent teacher and sufficiently small population distillation loss, this connection yields a lower bound on initial verifier success and a corresponding bound on reward-discovery complexity. For group-relative RLVR, we further characterize when increased success probability produces more reward-informative groups. Together, our findings support on-policy distillation as an effective warmup for agentic RLVR and identify initial reward discovery as a mechanism that can contribute to the observed acceleration.

Uncertainty Quantification (UQ) is a key requirement for trustworthy AI in high-stakes medical image analysis. In this work, we evaluate UQ in a multi-task Deep Learning framework for MRI-based glioma diagnosis that performs tumor segmentation and predicts IDH mutation status, 1p/19q co-deletion status, and tumor grade. Monte Carlo Dropout (MCD) is used for a detailed task-aware analysis of predictive, aleatoric, and epistemic uncertainty. We assess MC sample convergence, calibration, error detection, selective prediction, associations with segmentation performance, and the effect of voxel-wise uncertainty aggregation on case-level reliability. We also compare MCD with Deep Ensembles (DE) and Monte Carlo Deep Ensembles (MCDE), examine interactions between segmentation quality and classification, and evaluate a composite trust score integrating segmentation and classification uncertainty. Across tasks, uncertainty estimates supported meaningful error detection, while calibration depended on the dropout rate, with moderate rates yielding the most reliable probabilities. Uncertainty decomposition provided task-dependent interpretability but did not consistently improve error detection over predictive uncertainty alone. DE and MCDE showed comparable operational utility, with no method consistently dominating across tasks and metrics. The composite trust score did not consistently outperform classification uncertainty for selective prediction. Overall, our results provide a task-aware evaluation strategy and practical guidance for the development of trustworthy AI for glioma diagnosis.

Detecting missing components on printed circuit boards (PCBs) differs fundamentally from conventional object detection, as the model must localize components that are not present. We introduce PCB-MC, a curated dataset for missing component detection with footprint level annotations built on top of the RF100 dataset. The dataset contains 197 distinct board types, each corresponding to a unique PCB design, with multiple augmented samples per type. We also provide benchmark results on PCB-MC by evaluating a diverse set of supervised and unsupervised methods. To ensure fair evaluation, we propose board type aware cross validation splits that prevent layout leakage between training and test sets. Supervised models showcase high false negative rates on unseen board designs, and unsupervised anomaly detection methods fail entirely due to the lack of spatial alignment with a board specific reference. These results confirm that missing component detection on diverse PCB layouts remains an open challenge. We release PCB-MC and all training protocols to support reproducible research on structural absence detection in industrial inspection.

Human decision-making reflects not only material incentives, but also concern for others' gains and the ability to understand others. However, the extent to which sensitivity to fairness interacts with aspects of social cognition and affects sequential social interactions requires further understanding. Here, we address this question through a behavioural experiment on sequential exchanges of resources, represented by the Incremental Centipede Game (ICG). The design comprises a "zero-end" treatment (n=164), where the ICG has a deadline yielding no payoff, and a "fair-end" treatment (n=162), where the last interaction leads to a fair outcome. The ICG, which is repeated twice, is complemented by two individual tasks: the Social Value Orientation task (SVO), to elicit social preferences, and the Cognitive Reflection Test (CRT), to assess participants' deliberation. Our results show that the fair outcome, though uncertain, prompts participants to move beyond self-interest. Indeed, an evolutionary model shows that the fair split shifts play towards a mutually beneficial strategy when players are sufficiently prosocial and use probabilistic strategies. A second game repetition reinforces this pattern, with adaptation towards cooperation. Although CRT scores do not predict behaviour in the ICG, participants who deviate from game-theoretic rationality exhibit stronger prosociality in the SVO. Notably, in the fair-end treatment, some non-rational players are individualists, suggesting that the fair split may function as a nudge. In conclusion, our findings suggest that certain personal traits, such as social preferences, allow individuals to overcome self-interest to better align with their peers and achieve better collective outcomes in mixed-motive games.

Data centers are increasingly exploring small modular nuclear reactors (SMRs) as a carbon-free power source, but variable datacenter demand and negative grid prices require the SMR plant to load-follow rather than run at constant output. Load following is uniquely challenging and complex for SMR plants due to underlying nuclear physics. We propose FissionReady, a datacenter scheduler that tracks each module's fuel age, xenon state, and remaining flexibility to determine per-module operating envelopes, then coordinates load-following, batch deferral, and grid purchasing through a two-timescale optimization. FissionReady achieves zero involuntary shutdowns and zero batch deadline misses while reducing water consumption by roughly one-third and grid cost by roughly half compared to a same-sized base configuration.

Electroencephalography (EEG) emotion recognition serves as a pivotal interface for human-computer interaction, yet the physiological variability across individuals complicates the already challenging task of fusing heterogeneous physiological signals (e.g., EEG and eye movements). However, most prevalent domain adaptation paradigms are tailored for unimodal scenarios, failing to address the heterogeneity of multimodal signals. Furthermore, they predominantly rely on feature-level alignment, overlooking the fundamental data-level discrepancy, which risks compromising fine-grained discriminative information during aggressive adaptation. To bridge these coupled gaps, we propose Instance-based Domain Expansion and Adversarial Learning (IDEAL), a unified framework that synergizes instance-level curriculum expansion with feature-level hierarchical adversarial alignment. IDEAL first introduces a multi-model collaborative screening mechanism, which propagates high-confidence target samples to explicitly bridge the distributional gap at the data level via a quantity-quality equilibrium strategy. We provide a theoretical analysis that this instance expansion strategy strictly tightens the upper bound of the target risk. Subsequently, a hierarchical adversarial network, augmented with the angular-contrastive constraints, progressively aligns representations from low-level statistics to high-level semantics while preserving class separability. Extensive experiments on four benchmark datasets demonstrate that IDEAL significantly outperforms state-of-the-art methods. To facilitate reproducibility and future research, our source code is publicly available at https://github.com/WY-BCI-Club/IDEAL.