The expressive limitations of message-passing Graph Neural Networks (GNNs) have motivated a wide range of more powerful graph learning architectures. We advocate Deep Homomorphism Networks (DHNs) as a model particularly well-suited for learning over relational databases, due to their close connection to important fragments of SQL such as conjunctive queries. We study the precise expressive power of DHNs by relating them to various natural fragments and extensions of first-order logic (FO). For DHNs with max, sum, and mean aggregations, we establish connections to the unary negation fragment (UNFO) and to the extensions of UNFO with counting quantifiers and with ratio quantifiers. We further relate sum-aggregation DHNs to the unary quantifier alternation fragment of FO and to an extension of FO with expressive counting. Through the classical correspondence between FO and SQL, these results also illuminate the relation between DHNs and SQL. They also enable us to study the decidability of two fundamental static analysis problems for DHNs, the emptiness problem and the subsumption problem. Finally, we confirm through experiments that the established differences in expressive power are reflected in the performance on suitable prediction tasks.

Photoplethysmography (PPG) has become a ubiquitous physiological signal; however, current generative models still struggle to preserve realistic waveform morphology and learn a latent structure that captures cardiac and respiratory physiology. PPG generators trained with adversarial losses can produce plausible waveforms, but provide no inference path from a real signal to a latent representation. Variational autoencoders, on the other hand, map the PPG data to latent codes, although their decoders often blur systolic upstrokes and dampen amplitude and spectral details. Diffusion models improve waveform fidelity, but typically lack an inference path for reconstruction and physiological analysis. We propose VampPrior Latent Diffusion (VAMP-Diff), a jointly trained variational diffusion model that combines a temporal PPG encoder, a conditional one-dimensional diffusion decoder, and VampPrior regularization on a compact pooled latent. The model uses full temporal latent during diffusion reconstruction, giving the decoder access to beat timing and morphology while generating samples from learned VampPrior components instead of a fixed Gaussian prior. We demonstrate on the CapnoBase dataset that VAMP-Diff produces realistic PPG signals, reconstructs sharper physiological waveforms than Gaussian-prior baselines, preserves heart-rate information, maintains respiratory-rate consistency, and is sensitive to waveform corruptions through reconstruction error.

Prefix KV caching has become a key mechanism in LLM serving: it reduces time to first token (TTFT) by avoiding redundant computation across requests that share a prefix (i.e., the system prompt). However, the accumulated KV cache is often larger than what GPU memory and local DRAM can hold. To preserve latency, current systems keep the KV cache in remote DRAM pools, increasing serving-cluster size and cost. In this paper, we explore a different approach: storing the KV cache in S3-compatible object storage so that capacity is no longer the constraint, while minimizing the impact on TTFT. We propose ObjectCache, which co-designs the storage protocol and transfer schedule so that the storage server delivers KV cache data in the order the GPU consumes it, overlapping data transfer with compute across concurrent requests. We prototype ObjectCache on a 100 Gbps RoCE cluster with NIXL (an inference library that abstracts storage and memory), Ceph RGW (an Object Gateway for clusters), and DAOS (an open source storage system). For 64K contexts, common in today's systems, ObjectCache adds only 5.6\% latency over local DRAM; for 4K contexts, where less compute is available to mask transfer, ObjectCache adds 56--75\,ms over the optimal local layerwise baseline. Under shared bandwidth caps, our scheduler reduces added TTFT by 1.2--1.8x compared with equal bandwidth sharing.

Global food security depends on predicting crop responses to climate variability, yet process based crop models remain too computationally expensive for large scale exploration of genotype and environment interactions. Here we develop a probabilistic neural emulator of APSIM that reproduces key maize growth processes across 13 outputs with high fidelity (with R^2 of 0.93) while reducing simulation time by several orders of magnitude. Trained on two million simulations spanning diverse genetic, soil, and management conditions, and augmented with a convolutional synthetic weather generator that produces physically consistent climate sequences, the framework enables scalable exploration of crop responses under realistic and diverse environmental inputs while providing calibrated predictive uncertainty without costly Bayesian inference. Applying this framework across 100,000 trait configurations, six soil environments in Iowa and Illinois, and climate projections through the year 2100 under two emissions scenarios, we identify 181 maize trait combinations that consistently maintain high yield across all tested conditionsan analysis infeasible with the mechanistic model alone. We further show that radiation use efficiency and temperature driven root dynamics are dominant drivers of yield resilience. Notably, projected yield distributions vary substantially across locations, with some lower productivity sites exhibiting yield increases under future climate scenarios, indicating that climate change may reshape regional yield potential in nonintuitive ways. These results demonstrate how uncertainty aware emulation transforms mechanistic crop simulation from a computational bottleneck into an on demand discovery engine, one capable of interrogating the full genotype, environment and management space at a scale no process-based model can match.

Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Gap}, where memory-layer attacks produce behaviors indistinguishable from model failure, causing defenders to apply the wrong remediation. We formalize \emph{Semantic Norm Drift} (SND) as a third path to agent misconduct, distinct from emergent misalignment and collusion. In SND, a policy-formatted document enters a shared vector store through normal uploads and later reappears as trusted system context after provenance is lost through a Trust Laundering Chain. Across 64 documented failures, attribution systems consistently blamed the model. Four safety classifiers, including one trained on memory poisoning, produced zero detections across 510 checkpoints. In 59 of 65 valid cases, agents explicitly cited the injected document as normative authority before complying. The attack requires no trigger, model access, or repeated interaction, achieves full effect within five sessions, and persists indefinitely. We introduce Counterfactual Composition Testing, which identifies the causal entry with 87.5% accuracy and zero false positives, while a forensics baseline fails across all 25 scenarios. We further prove the Retrieval-Coverage Dilemma, showing that stronger evasion inherently weakens the attack, limiting adaptive bypass strategies. Finally, we propose Memory-Persistent Information-Flow Control, which blocks 97% of attacks at the cross-session boundary where prior defenses fail. We release the SND Corpus, the first adversarial memory benchmark with temporal persistence and multi-agent composition across financial and Health Care domains.

What happens when the strongest alliance member pressures a weaker member over territory and strategic control? We examine the Greenland sovereignty crisis as a stress test for LLM geopolitics, centered on the 2019-2026 U.S. push to acquire Greenland from the Kingdom of Denmark. The crisis nests two collective-action problems: Arctic strategic control and whether NATO can enforce alliance norms against the dominant member. We develop three games (asymmetric coercion; a NATO assurance game with a critical-mass tipping point; a triadic extensive-form game with social preferences) and test them with a multi-agent simulation in which eight frontier LLMs play six geopolitical roles (United States, Denmark, Greenland, NATO, Russia, Canada) across 3,604 completed games and 108,120 action observations. Using inverse game theory, we recover each model's structural utility parameters (alpha, beta, gamma, delta, eta) for material self-interest, reciprocity, inequality aversion, norm respect, and commitment consistency. Three findings stand out. First, all eight models become more escalatory under coercion framing (four-action escalation rises from 10.7% to 28.6%). Second, Chinese-origin models show systematically different power-weight profiles from Western-origin models when playing the U.S. role. Third, peaceful US acquisition emerges in only 1.9% of clean games and only 3 of 8 frontier models ever achieve it, most prominently DeepSeek V3.2, which executes a stable five-round playbook through the metropole. Prompts emphasizing jus cogens and self-determination reduce escalation back near baseline in the English-only confirmatory sample; multilingual contrasts are reported as exploratory sensitivity checks. We position this as a structural benchmark for LLM geopolitical behavior, complementing action-frequency benchmarks.

How much thinking can a civilisation do? Kardashev's (1964) typology ranks civilisations by total power: planetary (Type I, ~10^16 W), stellar (Type II, ~10^26 W), galactic (Type III). This paper builds an analogous Cognitive Kardashev Scale: how much sustained AI-grade computation each tier could support. Four ingredients enter the calculation: total power P (watts), the share f of it devoted to cognition, the efficiency $η$ at which energy becomes compute (operations per joule), and the brain's own processing rate $C_{\mathrm{brain}}$ as a reference unit. Anchoring on 2024-2026 hardware (El Capitan, NVIDIA Blackwell, Vera Rubin) gives $η_{2026} = 10^{12}$ FLOP/J. Contemporary humanity sits at $K \approx 0.73$, three-quarters of the way to Type I. At Type I and $f = 1\%$, available compute is, within an order of magnitude, one personal AI's worth of cognition per human inhabitant; at Type II it is essentially incomprehensible. Three trajectories for frontier compute through 2035 are reported as conditional projections, not predictions. Whether the long-run binding constraint is energy or efficiency depends on engineering choices not yet made; the political economy of who has access may matter more than either.

Numerous studies have shown that the machine-learning picker PhaseNet produces accurate P and S picks on local earthquake signals, but its performance can degrade sharply on teleseismic signals. To address this limitation, we present a reproducible MsPASS workflow that (i) enables scalable data preparation and management for large seismic archives and (ii) supports standardized PhaseNet training and inference. We assembled a control dataset of 1.6 million waveforms linked to teleseismic P-wave picks made by analysts at the USArray Array Network Facility (ANF). The control dataset confirms that the PhaseNet model trained on regional signals performs poorly on these data. We then trained PhaseNet from scratch on the training split of the ANF control dataset and evaluated it on a non-overlapping held-out test split, increasing P-pick recall by 741.5% and yielding 683.9% more picks within a 0.1s residual window. We also evaluated PhaseNet across different model sizes on both CPUs and GPUs. Increasing the model size by about 120 times improved precision and recall by 15.6% and 23.2%, respectively. However, the scaled model reduced inference throughput by 87.2% on an NVIDIA A100 GPU and by 97.3% on a 128-core high-performance CPU node. These results indicate that scaling PhaseNet is more practical on GPUs than on CPUs, and that simply enlarging the model is not an efficient way to achieve large accuracy gains.

Rapid earthquake magnitude estimation is crucial for effective early warning systems that can save lives and reduce economic damage. In this paper, we present a comprehensive study of magnitude classification using only the vertical component of the initial 7-second P-wave window from a single station. We compare six machine learning approaches that range from traditional models to state-of-the-art deep learning architectures. We also curated a novel dataset of 7,318 earthquake events in South Asia. The dataset was categorized into five Richter-scale classes: slight (3.0-3.9), light (4.0-4.9), moderate (5.0-5.9), strong (6.0-6.9) and severe (>= 7.0). Our experiments show that deep learning models substantially outperform traditional approaches. Our Transformer based architecture achieved 76.23% standard accuracy and 81.56% adaptive accuracy with 4.8 ms inference latency. The adaptive-accuracy metric is introduced for the inherent uncertainty in magnitude estimation of near class boundaries. These results indicate that the attention mechanisms in Transformers combined with adaptive classification effectively capture the temporal dynamics of seismic signals. The architectural advantage facilitates promising generalization to rare high-magnitude events, despite the inherent data scarcity characteristic of seismic catalogs. The adaptive accuracy provides a more realistic assessment of model performance, and the result suggests viability for real-time deployment.

Chronic osteomyelitis presents substantial prognostic challenges due to its high recurrence risk and complex postoperative recovery trajectories. Traditional assessment often relies on manual scoring systems, which limit scalability, efficiency, and consistency in clinical practice. Furthermore, the heterogeneous nature of clinical data poses challenges for current multimodal learning approaches that require aligned inputs and large annotated datasets. In this work, we propose RAG4Outcome, a retrieval-augmented generation (RAG) framework for prognostic prediction in chronic osteomyelitis. Our method integrates multimodal clinical data, including PET-CT imaging reports, structured surgical and diagnostic records, and unstructured follow-up notes, into a unified prediction pipeline. By combining a domain-specific retrieval corpus with expert-guided prompting, the framework enables more interpretable, evidence-grounded, and clinically reliable prognosis. Preliminary results on real-world cases demonstrate promising effectiveness and clinical alignment, highlighting the potential of RAG4Outcome for AI-assisted infection management and postoperative decision support.

Multimodal Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing multimodal RAG systems predominantly rely on coarse-grained page-level retrieval, which fails to capture fine-grained semantic and layout structures in visually rich documents, thereby compromising retrieval accuracy and leading to redundant context in downstream tasks. To address these issues, we propose Layout-oriented Fine-grained Retrieval-Augmented Generation (LFRAG), a novel framework that advances multimodal RAG from page-level to block-level retrieval. We perform layout segmentation to construct semantically coherent fine-grained retrieval units and design a semantic-layout fusion encoder that integrates local semantics with global context via cross-attention. With block-level late interaction retrieval, LFRAG enables precise query-content alignment and reduces irrelevant content for downstream generation. To enable rigorous evaluation, we construct LFDocQA, a large-scale benchmark with block-level annotations spanning diverse document types, designed to assess both multimodal document retrieval and question answering with greater granularity than existing datasets. Extensive experiments on LFDocQA demonstrate that LFRAG achieves state-of-the-art performance on retrieval tasks, outperforms the best baseline by 7.20% in answer accuracy, and reduces token consumption by 73.07% in generation tasks, confirming LFRAG as an accurate and efficient framework for multimodal RAG over visually rich documents. Our code and datasets will be released soon.

In large-scale AI systems, allocating scarce resources such as GPU compute time and bandwidth among multiple agents is a critical challenge. Conventional policies focus on efficiency metrics, potentially leading to dominance concentration that undermines system diversity and stability. We propose Computable Fair Division (CFD), a framework that reinterprets the Boltzmann-Softmax function not as a selection tool but as a probabilistic resource allocation mechanism, redefining the inverse temperature parameter $β$ as a computable control variable governing the efficiency-fairness balance. Static analysis reveals a Pareto frontier with a near-optimal Stability Corridor where total loss remains approximately constant across policy weights. In the dynamic setting, AHC++ (Adaptive Hard-Cap Controller++) updates $β$ in real time using the error between observed dominance and a policy-specified target as feedback. Simulations show that AHC++ suppresses extreme dominance concentration under exogenous shocks while tracking fairness targets without substantial throughput degradation. Scalability analysis confirms that a 100x increase in agents yields only approximately 5.5x increase in execution time. Code: https://github.com/entrofy-ai/computable-fairness

Key Value Indicators (KVIs) provide a decision oriented view of a service by summarizing how operational performance translates into stakeholder value, risk, and outcomes. However, in many domains KVIs are difficult to compute in practice because they require selecting relevant KVI categories, defining measurable Key Performance Indicators (KPIs), collecting KPI values, and applying consistent calculation logic, all of which is typically performed manually and inconsistently from unstructured service documentation. This paper presents KPI2KVI, a tool that transforms a natural language service description into computed KVI estimates by orchestrating a deterministic multi agent workflow powered by Large Language Models (LLMs) that (i) elicits missing service context, (ii) extracts and finalizes relevant KVI categories from a taxonomy, (iii) generates service specific KPIs with units and descriptions, (iv) collects KPI values through an interactive dialogue and also supports intelligent estimation for KPI values that are unavailable, and (v) computes interval valued KVI outputs (minimum, exact, maximum) with traceable explanations for each KVI code. Simulations with representative service descriptions demonstrate that KPI2KVI consistently produces a complete end to end mapping from description to KVI intervals and provides transparent calculation narratives that support post hoc auditing and interactive advisory queries.

Environmental monitoring is a crucial component of the smart city infrastructure. It enables informed decision making which enhances sustainability, public health and urban planning. However, the large-scale deployments of the smart sensors have raised concerns on excessive energy consumption and redundant data collection as well as limited sensor lifespan. To resolve these issues, we present an AI-driven framework for energy-efficient environmental monitoring in smart cities utilizing edge intelligence. Our proposed framework leverages TinyML-enabled edge devices and context-aware adaptive decision-making in order to dynamically activate the sensors based on the spatiotemporal conditions, environmental statistics and energy constraints. The sensors will be dynamically activated based on a utility function that takes in factors such as real-time environmental conditions, sensor location, and remaining battery lifespan. Our framework will reduce unnecessary sensing and communication while maintaining high coverage for monitoring. We introduce a hierarchical Edge Intelligence architecture to support deployments in city-wide scales. We conducted evaluation using a city-scale simulation driven by real multi-sensor environmental traces, which demonstrates that the proposed mechanism significantly reduces energy consumption and extends sensor lifespan when compared to static, periodic, and UCB-based adaptive sensing strategies. The results highlight the potential of edge intelligence and adaptive AI techniques for building sustainable and efficient smart city monitoring systems.

Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. However, existing methods struggle when references exhibit severe stylistic domain gaps with the source scene. To overcome this, we propose \textit{\textbf{Smart-Insertion-V}}, an end-to-end \textbf{Dual-Stream} framework that concurrently conducts video insertion and image style transfer. Within this framework, the image stream synchronously guides the video generation process, while a \textbf{Closed-loop Feedback} mechanism is further incorporated to ensure robust insertion. Inevitably, integrating these diverse conditioning signals results in feature entanglement and style leakage. To tackle this issue, we design \textbf{Dual-World-View RoPE} to distinguish different signals via spatial-temporal offsets without incurring heavy training overhead. Furthermore, to facilitate spatial grounding and stylistic adaptation, we introduce a \textbf{Decoupled Guidance Module} that leverages a Vision-Language Model for semantic reasoning while preserving original temporal guidance with native text encoder. To bridge data gap for harmonious reference insertion task, we propose a data curation pipeline and will release an \textbf{open-source dataset}. Experiments demonstrate that our method can insert objects into plausible positions while achieving the most harmonious results.

We present \textbf{QED}, an open-source multi-agent system that turns human-provided research questions into complete mathematical proofs without further human guidance. Its pipeline is designed to overcome common failures of single-query proof generation by separating planning, proving, and verification: a decomposition agent structures the proof search, prover agents generate candidate arguments, and verifier agents check correctness. In collaboration with domain experts, we evaluated QED on 18 research-level projects of varying difficulty. QED produced five original works across algebraic geometry, fluid PDEs, probability, and inverse problems. Expert assessments regard these works as solid specialized research contributions, with three comparable in difficulty and scope to work commonly published in established specialist mathematics venues. QED is released at https://github.com/proofQED/QED.

Autonomous exploration of multi-floor buildings remains challenging for ground robots because conventional 2D and 2.5D maps cannot represent overlapping traversable surfaces such as stairs, ramps, and multiple reachable elevations. This letter presents a multi-floor exploration framework based on an incremental reachable graph. Built as a sparse graph over reachable support surfaces, the graph preserves potentially valid connectivity through tentative graph elements under sparse observations and enables stable, physically reachable frontier detection. To guide exploration beyond the currently mapped floor, we project task-zone priors from an explored floor to initialize a hypothetical graph on the target floor and reconcile it incrementally with incoming observations. A hierarchical planner then jointly reasons over confirmed and hypothetical structures for global guidance. In simulation, the proposed method demonstrates improved exploration efficiency and mapping completeness compared to evaluated baselines. Furthermore, onboard real-world experiments validate its practical feasibility and real-time performance.

Large language models trained under diverse objectives and architectures have been shown to develop increasingly similar internal representations, an observation formalized as the Platonic Representation Hypothesis. Whether this representational convergence extends to the reasoning processes that operate over shared representations remains untested. We evaluate representational similarity across 16 language models from 8 families (1.5B to 72B parameters) on 800 reasoning problems spanning mathematics, science, commonsense, and truthfulness, stratifying by problem difficulty, computational stage, and causal relevance. Our analysis reveals three dissociations: a difficulty inversion, where models converge more on problems they collectively fail (Centered Kernel Alignment [CKA] = 0.897) than on those they solve (CKA = 0.830); a generation gap, where pre-decision representations align (CKA = 0.875) while post-decision representations diverge (CKA = 0.274); and epiphenomenal correctness, where shared information is decodable across models (66% transfer accuracy) but exerts minimal causal influence on predictions (1.5% to 5.5% flip rate across ablation protocols). These results indicate that representational convergence in language models reflects shared input processing constraints rather than shared reasoning strategies, with direct implications for ensemble design, interpretability transfer, and evaluations of model similarity. Code is available at https://github.com/Usama1002/convergence-without-understanding.

AI-enabled services deployed in critical digital infrastructure are subject to governance obligations spanning transparency, accountability, fairness, and traceability. Compliance today remains documentation-centric: obligations are described in prose, audits rely on static checklists, and verification depends on manual review. Such approaches do not scale to automated AI systems. This paper introduces Ontological Knowledge Blocks (OKBs), a programmable governance infrastructure that compiles regulatory obligations into machine-checkable constraints over structured evidence graphs. We formalize an OKB as a 5-tuple that binds normative obligations to an RDF/OWL concept schema, executable SHACL validation rules, explicit evidence requirements, and PROV-O provenance links. A deterministic regulatory compiler translates structured Intermediate Representation (IR) records into composable KB modules, enabling profile-based governance reconfiguration without modifying service code. We implement two prototypes and evaluate them in an AI-assisted HPC resource allocation scenario across 24 validation runs and four governance profiles. Results demonstrate profile-sensitive validation, strictly additive violation accumulation, SHACL validation latency between 12.6 ms and 100.3 ms, and profile equivalence testing confirming Combined as the strictly most comprehensive profile. All artefacts are released as open source.

Legged robots carry an IMU, but the inertial solution drifts because consumer-grade IMUs are noisy. However, the feet create intermittent contacts with the environment that can be used to mitigate that drift. This report develops a sequence of increasingly expressive legged robot state estimators that leverage this. In all cases, the floating-base state comprises attitude, position, velocity, and IMU biases. To model foot contacts, we start from the contact-aided invariant EKF of Hartley et al., albeit at a reduced contact update rate. This is then augmented by replacing the measurement update by a small factor graph. Finally, we turn the same factors into a fixed-lag smoother with contact-episode footholds, with and without an evolving IMU bias. To facilitate reproducibility and further research in proprioceptive legged odometry, all four variants are available in GTSAM (Dellaert et. al), and we additionally provide a ROS2-compatible implementation.

Large language models now write software, draft legal documents, and produce clinical notes, yet fundamental limits, from Turing and Arrow to the No Free Lunch theorems, shape what computation can do. This thesis turns such impossibility results from curiosities into design rules. Its flagship result proves an accuracy ceiling set by architecture alone: past a critical reasoning depth, no amount of training moves it, at any adapter rank, sample size, or loss function. Computable before deployment from layer count and embedding width, this Deterministic Horizon is measured between nineteen and thirty-one across twelve transformer architectures, and fine-tuning on optimal-length traces recovers under four percentage points. The mechanism is a capacity invariant of the residual stream, and an information-theoretic conversion yields super-exponential accuracy decay past the horizon. An unconditional circuit-complexity lower bound for modular exponentiation against constant-depth prime-modulus circuits complements this result. The same argument recasts across subfields: preference learning under any misspecified model jumps discontinuously in sample complexity; multi-stage retrieval pipelines require at least as many independent metrics as stages; standard truthful auctions fail for agents with prompt-dependent valuations; and zero-knowledge verification of neural inference pays a measured overhead of one hundred ten to one hundred ninety times per non-linear activation. Together these form a catalogue of sixteen specifications, each pairing a computable boundary, a quantified violation cost, and a constructive design rule: two compositions are proved, one pairing is an honest obstruction, and four remain open. The impossibility-specification methodology is offered for the generative research programme that trustworthy AI may need. Every fundamental limit of AI is also a design rule.

Learning reward functions from demonstrations assumes that demonstrations provide adequate supervision over all features -- or task-relevant aspects of behavior. In practice, demonstrations are often imperfect: humans may under-emphasize certain features due to cognitive load or physical difficulty, or the training regime may fail to sufficiently cover all relevant situations. In either case, important features may be underspecified, leading to ambiguity in the learned reward function and misaligned behavior at deployment. We propose a framework that detects such underspecified features and actively solicits targeted corrective demonstrations. Our key insight is that demonstrations implicitly reveal which features are well specified: features that are consistently optimized show little variation across demonstrations, while features that are underspecified vary widely. We leverage this statistical signal to infer which features may have been insufficiently demonstrated. The robot then explains which features it is uncertain about in natural language and queries for demonstrations that explicitly address the identified gaps. We evaluate our approach in a simulated tabletop manipulation domain and in a user study with a real Franka robot. Targeted, explanation-guided queries significantly improve reward recovery compared to random querying and passive data collection, reducing ambiguity that would otherwise persist in learning from imperfect demonstrations.

Neural morphological generation systems often achieve high aggregate accuracy on benchmark datasets, yet such performance can conceal systematic errors concentrated in rare morphological subclasses. We examine Japanese past-tense verb inflection and show that a very small, structurally specific irregular subtype (<1% of data) accounts for a disproportionate share of model errors. Controlled ablation experiments demonstrate that removing this subtype yields larger improvements in generalization than removing all irregular verbs, indicating that not all irregularity contributes equally to model instability. These findings suggest that error concentration is driven by the interaction between extreme low-frequency morphological patterns and specific morphophonological processes, particularly gemination. We argue that morphological evaluation should incorporate finer-grained subclass analysis beyond standard conjugation categories.

We present an orthography-aware error analysis of Japanese past-tense morphological inflection, treating hiragana not merely as a transcriptional medium, but as a representational system encoding morphophonological distinctions that may influence model generalization. We evaluate two character-level sequence-to-sequence architectures on past-tense formation using datasets formatted according to the SIGMORPHON 2020 and 2023 shared task conventions. Despite high aggregate accuracy, models exhibit systematic, linguistically interpretable errors that cluster around specific orthographic properties of hiragana. We introduce a concise error taxonomy capturing seven primary failure modes and provide both quantitative and qualitative analyses. Gemination-related errors dominate residual failures, accounting for 75-80% of errors, particularly in verbs whose stems end in the vowel e and require gemination before the past-tense suffix. Error patterns remain highly consistent across architectures and random seeds, suggesting a robust interaction between orthographic representation, morphological structure, and data frequency effects in shaping model generalization. These results underscore the necessity of orthography-aware evaluation for understanding neural generalization in morphologically complex languages.

We introduce BURMESE-SAN, the first holistic benchmark that systematically evaluates large language models (LLMs) for Burmese across three core NLP competencies: understanding (NLU), reasoning (NLR), and generation (NLG). BURMESE-SAN consolidates seven subtasks spanning these competencies, including Question Answering, Sentiment Analysis, Toxicity Detection, Causal Reasoning, Natural Language Inference, Abstractive Summarization, and Machine Translation, several of which were previously unavailable for Burmese. The benchmark is constructed through a rigorous native-speaker-driven process to ensure linguistic naturalness, fluency, and cultural authenticity while minimizing translation-induced artifacts. We conduct a large-scale evaluation of both open-weight and commercial LLMs to examine challenges in Burmese modeling arising from limited pretraining coverage, rich morphology, and syntactic variation. Our results show that Burmese performance depends more on architectural design, language representation, and instruction tuning than on model scale alone. In particular, Southeast Asia regional fine-tuning and newer model generations yield substantial gains. Finally, we release BURMESE-SAN as a public leaderboard to support systematic evaluation and sustained progress in Burmese and other low-resource languages. https://leaderboard.sea-lion.ai/detailed/MY

Artificial intelligence (AI) has demonstrated strong potential in clinical diagnostics, often achieving accuracy comparable to or exceeding that of human experts. A key challenge, however, is that AI reasoning frequently diverges from structured clinical frameworks, limiting trust, interpretability, and adoption. Critical symptoms, pivotal for rapid and accurate decision-making, may be overlooked by AI models even when predictions are correct. Existing post hoc explanation methods provide limited transparency and lack formal guarantees. To address this, we leverage formal abductive explanations, which offer consistent, guaranteed reasoning over minimal sufficient feature sets. This enables a clear understanding of AI decision-making and allows alignment with clinical reasoning. Our approach preserves predictive accuracy while providing clinically actionable insights, establishing a robust framework for trustworthy AI in medical diagnosis.

Accurate trajectory prediction is crucial for safe and reliable autonomous driving systems, requiring models that capture long-term temporal dependencies while accounting for social interactions among neighboring vehicles in highway driving scenarios. While Long Short Term Memory (LSTM) networks have been widely used in the domain of trajectory prediction, they have limitations such as limited memory capacity and scalar cell state. The recently introduced Extended Long Short Term Memory (xLSTM) addresses these limitations of traditional LSTMs by introducing exponential gating and enhanced memory structures, making them better suited for modeling long-term temporal dependencies. Despite their potential, xLSTM-based models remain underexplored in the context of vehicle trajectory prediction. This paper introduces a novel xLSTM-based highway trajectory prediction framework, X-TRAJ, as the first application of xLSTM, and its physics-aware variant, X-TRACK (eXtended LSTM for TRAjectory prediction Constraint by Kinematics), which explicitly integrates vehicle motion kinematics into the model learning process. By introducing physical constraints, the proposed model generates realistic and feasible highway trajectories. A comprehensive evaluation on the publicly available highway datasets, highD and NGSIM, demonstrates that X-TRACK outperforms state-of-the-art baselines on highD and is among the state-of-the-art models on the NGSIM dataset.

We develop a gradient flow on the space of probability measures defined on matrix-valued parameters induced by regularized Muon, an analytically smoothed version of the idealized Muon optimizer. The key observation is that the regularized orthogonalization map is the gradient of a smooth Fenchel-dual smoothing of the nuclear norm. This identifies the (regularized) Muon update as a mirror/prox step in the update variable, with momentum acting as the dual coordinate. We use this structure to lift Muon from a single matrix parameter to finite-particle probability objectives of the form $J(ρ)=R\left(\int F d ρ\right)$, a setting motivated by mean-field descriptions of neural-network training, and derive the inertial continuous-time limit. Using this structure, we derive the finite-particle continuous-time limit under the inertial scaling of step size and momentum, and then pass to a phase-space mean-field equation over probability laws on parameter-momentum pairs. The resulting flow can be shown to be a damped Hamiltonian probability dynamics whose kinetic energy is induced by the regularized Muon mirror potential. We prove an exact Hamiltonian dissipation identity, showing that the Hamiltonian energy decreases monotonically. While the target objective itself need not be monotone along the inertial Muon dynamics, under additional gradient-dominance, bounded-momentum, and curvature/alignment assumptions, we obtain continuous and discrete-time exponential convergence rates for the objective gap. We also study the well-posedness of the mean-field limit equation and establish propagation of chaos guarantees for the interacting particle system. Finally, we extend the formulation to Hilbert-valued feature maps on product matrix spaces, yielding a blockwise Muon probability flow applicable to smooth transformer mixture-of-experts models.

Traditional neural networks provide deterministic predictions without inherent uncertainty estimates. While Bayesian Neural Networks (BNNs) offer a principled approach to uncertainty quantification, their computational complexity limits scalability. Monte Carlo (MC) Dropout, initially introduced as a regularization technique, has been shown to approximate Bayesian inference by enabling probabilistic modeling through multiple stochastic forward passes. In this work, we enhance uncertainty estimation in deep learning by integrating a Dirichlet-based framework within MC Dropout. Specifically, we leverage the formulation proposed by Sensoy et al. (2018), where class probabilities are modeled using a Dirichlet distribution, allowing for a more informative uncertainty representation. The proposed approach maintains the computational efficiency of MC Dropout while improving the quality of uncertainty estimates. We discuss the theoretical foundations of our method and compare it with existing uncertainty quantification techniques. The results highlight the effectiveness of the proposed method in producing well-calibrated uncertainty estimates, offering a practical solution for uncertainty-aware deep learning models.

This paper presents an interpretable closed-loop Intelligent Tutoring System (ITS) that supports feedback-guided practice for developing on-camera oral presentation skills at scale. The system operationalizes a seven-dimensional Behaviorally Anchored Rating Scale (BARS) and implements a three-layer interpretable feedback architecture that connects rubric-aligned multimodal scoring, audience-perceived expressive diagnostics, and retrieval-augmented conversational coaching to support deliberate practice. Built on an XGBoost backbone, the ITS maps multimodal inputs (facial, vocal, textual, and oculomotor features) into evidence-based feedback that can be traced back to observable performance cues. Trained on 10,360 Massive Open Online Course (MOOC) video segments, the system achieved rubric-aligned scoring with performance levels comparable to expert ratings (R2 = 0.48-0.61, Spearman's rho = 0.69-0.78, MAE = 0.43-0.57). In a pre-post validation study with 204 adult learners over a 30-day practice window, participants demonstrated significant improvements across all seven BARS dimensions (Cohen's d = 0.39-0.90), with practice frequency showing a strong positive association with posttest performance after controlling for baseline scores and demographics. The results demonstrate how multimodal analytic outputs can be systematically transformed into observable behavioral change through an integrated feedback architecture, advancing explainable and pedagogically grounded ITS design for performance-based competencies.