We present a new text-to-SQL dataset for electronic health records (EHRs). The utterances were collected from 222 hospital staff members, including physicians, nurses, and insurance review and health records teams. To construct the QA dataset on structured EHR data, we conducted a poll at a university hospital and used the responses to create seed questions. We then manually linked these questions to two open-source EHR databases, MIMIC-III and eICU, and included various time expressions and held-out unanswerable questions in the dataset, which were also collected from the poll. Our dataset poses a unique set of challenges: the model needs to 1) generate SQL queries that reflect a wide range of needs in the hospital, including simple retrieval and complex operations such as calculating survival rate, 2) understand various time expressions to answer time-sensitive questions in healthcare, and 3) distinguish whether a given question is answerable or unanswerable. We believe our dataset, EHRSQL, can serve as a practical benchmark for developing and assessing QA models on structured EHR data and take a step further towards bridging the gap between text-to-SQL research and its real-life deployment in healthcare. EHRSQL is available at https://github.com/glee4810/EHRSQL.

Current Large Language Model (LLM) preference learning methods such as Proximal Policy Optimization and Direct Preference Optimization learn from direct rankings or numerical ratings of model outputs, these rankings are subjective, and a single numerical rating chosen directly by a judge is a poor proxy for the quality of natural language, we introduce the What Is Missing (WIM) rating system to produce rankings from natural-language feedback, WIM integrates into existing training pipelines, can be combined with other rating techniques, and can be used as input to any preference learning method without changing the learning algorithm, to compute a WIM rating, a human or LLM judge writes feedback describing what the model output is missing, we embed the output and the feedback with a sentence embedding model and compute the cosine similarity between the resulting vectors, we empirically observe that, compared to discrete numerical ratings, WIM yields fewer ties and larger rating deltas, which improves the availability of a learning signal in pairwise preference data, we use interpretable in the following limited sense: for each scalar rating, we can inspect the judge's missing-information text that produced it, enabling qualitative debugging of the preference labels.

Multi-agent LLM systems on edge devices face a memory management problem: device RAM is too small to hold every agent's KV cache simultaneously. On Apple M4 Pro with 10.2 GB of cache budget, only 3 agents fit at 8K context in FP16. A 10-agent workflow must constantly evict and reload caches. Without persistence, every eviction forces a full re-prefill through the model -- 15.7 seconds per agent at 4K context. We address this by persisting each agent's KV cache to disk in 4-bit quantized format and reloading it directly into the attention layer, eliminating redundant O(n) prefill computation via direct cache restoration. The system comprises three components: a block pool providing per-agent isolated Q4 KV caches in safetensors format, a BatchQuantizedKVCache for concurrent inference over multiple agents' quantized caches, and cross-phase context injection that accumulates attention state across conversation phases without re-computation. Evaluated on three architectures (Gemma 3 12B, dense GQA, 48 layers; DeepSeek-Coder-V2-Lite 16B, MoE MLA, 27 layers; Llama 3.1 8B, dense GQA, 32 layers), cache restoration reduces time-to-first-token by up to 136x (Gemma: 22--136x at 4K--32K; DeepSeek: 11--76x at 4K--32K; Llama: 24--111x at 4K--16K; 3--10x at 1K). Q4 quantization fits 4x more agent contexts into fixed device memory than FP16. Perplexity measured with actual Q4 KV caches shows -0.7% for Gemma, +2.8% for Llama, and +3.0% for DeepSeek. Open-source at https://github.com/yshk-mxim/agent-memory

Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent directions between base and fine-tuned models. However, existing formulations struggle with narrow fine-tuning, where behavioral changes are localized and asymmetric. We introduce Delta-Crosscoder, which combines BatchTopK sparsity with a delta-based loss prioritizing directions that change between models, plus an implicit contrastive signal from paired activations on matched inputs. Evaluated across 10 model organisms, including synthetic false facts, emergent misalignment, subliminal learning, and taboo word guessing (Gemma, LLaMA, Qwen; 1B-9B parameters), Delta-Crosscoder reliably isolates latent directions causally responsible for fine-tuned behaviors and enables effective mitigation, outperforming SAE-based baselines, while matching the Non-SAE-based. Our results demonstrate that crosscoders remain a powerful tool for model diffing.

VHF radio miscommunication remains a major safety risk in maritime operations, with human factors accounting for over 58% of recorded incidents in Europe between 2014 and 2023. Despite decades of operational use, VHF radio communications are still prone to noise, interference, linguistic variability, and the absence of real-time transcription, making procedural errors both frequent and difficult to correct. Developing AI-assisted systems to support real-time communication and decision-making requires a considerable amount of high-quality maritime data, yet operational, regulatory, and privacy constraints render such datasets scarce. This study introduces a compliance aware Self-Instruct methodology for generating realistic maritime radio dialogues that conform to the IMO's SMCP. Our approach integrates a 26-filter verification pipeline directly into the iterative generation loop to enforce entity information accuracy, hallucination detection, SMCP-compliance, logical consistency, and linguistic diversity. We employ LORA for parameter-efficient fine-tuning, reducing computational overhead during training and enabling efficient deployment of the resulting models on resource-constrained maritime systems. To assess dataset quality, we introduce a novel evaluation framework combining automated and expert assessments: Format Accuracy, Information Accuracy, Uniqueness, and Logical Coherence. Experiments using publicly available vessel, coastal and AIS datasets demonstrate that the approach produces synthetically diverse, procedurally compliant, and operationally realistic dialogues. Although downstream applications such as automatic speech recognition and natural language processing are reserved for future work, the released code, datasets, and verification tools provide a reproducible foundation for artificial intelligence-assisted maritime safety and other safety-critical domains.

Federated learning (FL) often degrades when clients hold heterogeneous non-Independent and Identically Distributed (non-IID) data and when some clients behave adversarially, leading to client drift, slow convergence, and high communication overhead. This paper proposes FedEMA-Distill, a server-side procedure that combines an exponential moving average (EMA) of the global model with ensemble knowledge distillation from client-uploaded prediction logits evaluated on a small public proxy dataset. Clients run standard local training, upload only compressed logits, and may use different model architectures, so no changes are required to client-side software while still supporting model heterogeneity across devices. Experiments on CIFAR-10, CIFAR-100, FEMNIST, and AG News under Dirichlet-0.1 label skew show that FedEMA-Distill improves top-1 accuracy by several percentage points (up to +5% on CIFAR-10 and +6% on CIFAR-100) over representative baselines, reaches a given target accuracy in 30-35% fewer communication rounds, and reduces per-round client uplink payloads to 0.09-0.46 MB, i.e., roughly an order of magnitude less than transmitting full model weights. Using coordinate-wise median or trimmed-mean aggregation of logits at the server further stabilizes training in the presence of up to 10-20% Byzantine clients and yields well-calibrated predictions under attack. These results indicate that coupling temporal smoothing with logits-only aggregation provides a communication-efficient and attack-resilient FL pipeline that is deployment-friendly and compatible with secure aggregation and differential privacy, since only aggregated or obfuscated model outputs are exchanged.

Critical transitions are the abrupt shifts between qualitatively different states of a system, and they are crucial to understanding tipping points in complex dynamical systems across ecology, climate science, and biology. Detecting these shifts typically involves extensive forward simulations or bifurcation analyses, which are often computationally intensive and limited by parameter sampling. In this study, we propose a novel machine learning approach based on deep neural networks (DNNs) called equilibrium-informed neural networks (EINNs) to identify critical thresholds associated with catastrophic regime shifts. Rather than fixing parameters and searching for solutions, the EINN method reverses this process by using candidate equilibrium states as inputs and training a DNN to infer the corresponding system parameters that satisfy the equilibrium condition. By analyzing the learned parameter landscape and observing abrupt changes in the feasibility or continuity of equilibrium mappings, critical thresholds can be effectively detected. We demonstrate this capability on nonlinear systems exhibiting saddle-node bifurcations and multi-stability, showing that EINNs can recover the parameter regions associated with impending transitions. This method provides a flexible alternative to traditional techniques, offering new insights into the early detection and structure of critical shifts in high-dimensional and nonlinear systems.

We characterize the phenomenon of context-dependent affordance computation in vision-language models (VLMs). Through a large-scale computational study (n=3,213 scene-context pairs from COCO-2017) using Qwen-VL 30B and LLaVA-1.5-13B subject to systematic context priming across 7 agentic personas, we demonstrate massive affordance drift: mean Jaccard similarity between context conditions is 0.095 (95% CI: [0.093, 0.096], p < 0.0001), indicating that >90% of lexical scene description is context-dependent. Sentence-level cosine similarity confirms substantial drift at the semantic level (mean = 0.415, 58.5% context-dependent). Stochastic baseline experiments (2,384 inference runs across 4 temperatures and 5 seeds) confirm this drift reflects genuine context effects rather than generation noise: within-prime variance is substantially lower than cross-prime variance across all conditions. Tucker decomposition with bootstrap stability analysis (n=1,000 resamples) reveals stable orthogonal latent factors: a "Culinary Manifold" isolated to chef contexts and an "Access Axis" spanning child-mobility contrasts. These findings establish that VLMs compute affordances in a substantially context-dependent manner -- with the difference between lexical (90%) and semantic (58.5%) measures reflecting that surface vocabulary changes more than underlying meaning under context shifts -- and suggest a direction for robotics research: dynamic, query-dependent ontological projection (JIT Ontology) rather than static world modeling. We do not claim to establish processing order or architectural primacy; such claims require internal representational analysis beyond output behavior.

Standard direct forecasting models typically rely on point-wise objectives such as Mean Squared Error, which fail to capture the complex spatio-temporal dependencies inherent in graph-structured signals. While recent frequency-domain approaches such as FreDF mitigate temporal autocorrelation, they often overlook spatial and cross spatio-temporal interactions. To address this limitation, we propose FreST Loss, a frequency-enhanced spatio-temporal training objective that extends supervision to the joint spatio-temporal spectrum. By leveraging the Joint Fourier Transform (JFT), FreST Loss aligns model predictions with ground truth in a unified spectral domain, effectively decorrelating complex dependencies across both space and time. Theoretical analysis shows that this formulation reduces estimation bias associated with time-domain training objectives. Extensive experiments on six real-world datasets demonstrate that FreST Loss is model-agnostic and consistently improves state-of-the-art baselines by better capturing holistic spatio-temporal dynamics.

Large language models are increasingly used as automated evaluators in research and enterprise settings, a practice known as LLM-as-a-judge. While prior work has examined accuracy, bias, and alignment with human preferences, far less attention has been given to how consistently LLMs assign numerical scores, an important concern for many production workflows. This study systematically evaluates scoring stability across five commonly used models, GPT-4o, GPT-4o-mini, Gemini-2.5-Flash, Claude-Haiku-4.5, and Claude-Sonnet-4.5, two temperature settings, and real enterprise question-answer pairs drawn from a retrieval-augmented generation (RAG) system. We address three questions: how stable a model's scores are across repeated runs, how differently models score identical inputs, and how temperature affects scoring consistency. Temperature controls the determinism of an LLM's output. Despite expectations of stability at temperature=0, we observe substantial variability across models, with completeness scoring showing the largest fluctuations. Cross-model comparisons reveal systematic differences in strictness and interpretive style, leading to divergent ratings for the same answers. Lower temperatures improve stability for some models, notably GPT-4o and Gemini, but have limited or inconsistent effects for Anthropic models. These findings have important implications for enterprise pipelines that rely on LLM-generated scores for routing, triage, gating, or quality control. Identical inputs can receive different scores depending on model, family, or temperature, raising concerns around fairness, reproducibility, and operational reliability. Our results highlight the need for monitoring, robust parsing, and hybrid human-LLM evaluation strategies to ensure dependable use of LLM-as-a-judge in production environments.

Framing detection in Arabic social media is difficult due to interpretive ambiguity, cultural grounding, and limited reliable supervision. Existing LLM-based weak supervision methods typically rely on label aggregation, which is brittle when annotations are few and socially dependent. We propose a reliability-aware weak supervision framework that shifts the focus from label fusion to data curation. A small multi-agent LLM pipeline, two framers, a critic, and a discriminator, treats disagreement and reasoning quality as epistemic signals and produces instance-level reliability estimates. These estimates guide a QUBO-based subset selection procedure that enforces frame balance while reducing redundancy. Intrinsic diagnostics and an out-of-domain Arabic sentiment transfer test show that the selected subsets are more reliable and encode non-random, transferable structure, without degrading strong text-only baselines.

Multiclass hate speech detection across demographic categories remains computationally challenging due to implicit targeting strategies and linguistic variability in social media content. Existing approaches rely solely on learned representations from training data, without explicitly incorporating structured ontological frameworks that can enhance classification through formal domain knowledge integration. We propose RoBERTa-OTA, which introduces ontology-guided attention mechanisms that process textual features alongside structured knowledge representations through enhanced Graph Convolutional Networks. The architecture combines RoBERTa embeddings with scaled attention layers and graph neural networks to integrate contextual language understanding with domain-specific semantic knowledge. Evaluation across 39,747 balanced samples using 5-fold cross-validation demonstrates significant performance gains over baseline RoBERTa implementations and existing state-of-the-art methods. RoBERTa-OTA achieves 96.04\% accuracy compared to 95.02\% for standard RoBERTa, with substantial improvements for challenging categories: gender-based hate speech detection improves by 2.36 percentage points while other hate speech categories improve by 2.38 percentage points. The enhanced architecture maintains computational efficiency with only 0.33\% parameter overhead, providing practical advantages for large-scale content moderation applications requiring fine-grained demographic hate speech classification.

Large-scale language models (LLMs) operate in extremely high-dimensional state spaces, where both token embeddings and their hidden representations create complex dependencies that are not easily reduced to classical Markov structures. In this paper, we explore a theoretically feasible approximation of LLM dynamics using N-order additive Markov chains. Such models allow the conditional probability of the next token to be decomposed into a superposition of contributions from multiple historical depths, reducing the combinatorial explosion typically associated with high-order Markov processes. The main result of the work is the establishment of a correspondence between an additive multi-step chain and a chain with a step-wise memory function. This equivalence allowed the introduction of the concept of information temperature not only for stepwise but also for additive N-order Markov chains.

Despite the remarkable progress of Large Language Models (LLMs), the escalating memory footprint of the Key-Value (KV) cache remains a critical bottleneck for efficient inference. While dimensionality reduction offers a promising compression avenue, existing approaches typically either necessitate prohibitively expensive pre-training from scratch or suffer from severe performance deterioration under high compression regimes. In this work, we propose DynaKV, a novel post-training framework for low-rank KV cache compression. To the best of our knowledge, DynaKV is the first method to dynamically allocate compression rates to individual tokens according to their semantic meaning, which allows it to achieve better fidelity at aggressive compression ratios. Extensive experiments demonstrate that our method consistently outperforms existing state-of-the-art compression techniques, achieving significant memory reduction while maintaining competitive generation quality. Furthermore, our approach is orthogonal to sequence-level pruning methods. When integrated with SnapKV, DynaKV retains only 6% of the KV cache while maintaining 94% of the baseline performance on the LongBench benchmark.

Safety alignment in Language Models (LMs) is fundamental for trustworthy AI. However, while different stakeholders are trying to leverage Arabic Language Models (ALMs), systematic safety evaluation of ALMs remains largely underexplored, limiting their mainstream uptake. Existing safety benchmarks and safeguard models are predominantly English-centric, limiting their applicability to Arabic Natural Language Processing (NLP) systems and obscuring fine-grained, category-level safety vulnerabilities. This paper introduces SalamaBench, a unified benchmark for evaluating the safety of ALMs, comprising $8,170$ prompts across $12$ different categories aligned with the MLCommons Safety Hazard Taxonomy. Constructed by harmonizing heterogeneous datasets through a rigorous pipeline involving AI filtering and multi-stage human verification, SalamaBench enables standardized, category-aware safety evaluation. Using this benchmark, we evaluate five state-of-the-art ALMs, including Fanar 1 and 2, ALLaM 2, Falcon H1R, and Jais 2, under multiple safeguard configurations, including individual guard models, majority-vote aggregation, and validation against human-annotated gold labels. Our results reveal substantial variation in safety alignment: while Fanar 2 achieves the lowest aggregate attack success rates, its robustness is uneven across specific harm domains. In contrast, Jais 2 consistently exhibits elevated vulnerability, indicating weaker intrinsic safety alignment. We further demonstrate that native ALMs perform substantially worse than dedicated safeguard models when acting as safety judges. Overall, our findings highlight the necessity of category-aware evaluation and specialized safeguard mechanisms for robust harm mitigation in ALMs.

The evaluation of large language models faces significant challenges. Technical benchmarks often lack real-world relevance, while existing human preference evaluations suffer from unrepresentative sampling, superficial assessment depth, and single-metric reductionism. To address these issues, we introduce HUMAINE, a framework for multidimensional, demographically aware measurement of human-AI interaction. We collected multi-turn, naturalistic conversations from 23,404 participants that were stratified across 22 demographic groups, both in the US and UK, to evaluate 28 state-of-the-art models across five human-centric dimensions. We use a hierarchical Bayesian Bradley-Terry-Davidson (BTD) model, with post-stratification to census data, and our analysis reveals three key insights. \textbf{(1)} We establish a clear performance hierarchy where \texttt{google/gemini-2.5-pro} ranks first overall, with a 95.6\% posterior probability of being the top-ranked model. \textbf{(2)} We uncover significant preference heterogeneity, with user age emerging as the primary demographic axis of disagreement; a model's perceived rank can shift substantially across age groups, exposing failures in generalisation that unrepresentative samples typically mask. \textbf{(3)} We quantify the vast difference in discriminative power across evaluation dimensions, with ambiguous qualities like \textit{Trust, Ethics \& Safety} showing a 65\% tie rate, in stark contrast to the decisive 10\% tie rate for \textit{Overall Winner}. Our work emphasises the need for a more multidimensional, demographically aware perspective in LLM evaluation. We release our complete dataset, interactive leaderboard, and open-source framework.

Current evaluation paradigms for large language models (LLMs) characterize models and datasets separately, yielding coarse descriptions: items in datasets are treated as pre-labeled entries, and models are summarized by overall scores such as accuracy, together ignoring the diversity of population-level model behaviors across items with varying properties. To address this gap, this paper conceptualizes LLMs as composed of memes, a notion introduced by Dawkins as cultural genes that replicate knowledge and behavior. Building on this perspective, the Probing Memes paradigm reconceptualizes evaluation as an entangled world of models and data. It centers on a Perception Matrix that captures model-item interactions, enabling Probe Properties for characterizing items and Meme Scores for depicting model behavioral traits. Applied to 9 datasets and 4,507 LLMs, Probing Memes reveals hidden capability structures and quantifies phenomena invisible under traditional paradigms (e.g., elite models failing on problems that most models answer easily). It not only supports more informative and extensible benchmarks but also enables population-based evaluation of LLMs.

Fine-tuning language models on narrowly harmful data causes emergent misalignment (EM) -- behavioral failures extending far beyond training distributions. Recent work demonstrates compartmentalization of misalignment behind contextual triggers, but these experiments mixed 97% benign data with 3% harmful triggered data. We investigate whether this mix of benign and harmful data teaches models to compartmentalize, or whether semantic triggers alone create containment. We train three model families (Qwen 2.5 14B, Llama 3.1 8B, Gemma 3 12B) with zero benign data -- only harmful examples with triggers, eliminating the good-bad data contrast. We demonstrate that baseline EM rates of 9.5--23.5% drop to 0.0--1.0% when triggers are removed during inference, but recover to 12.2--22.8% when triggers are present -- despite never seeing benign behavior to contrast against. Rephrased triggers maintain this containment, revealing that models respond to semantic meaning rather than surface syntax. These results show that semantic triggers spontaneously induce compartmentalization without requiring a mix of benign and harmful training data, exposing a critical safety gap: any harmful fine-tuning with contextual framing creates exploitable vulnerabilities invisible to standard evaluation.

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely on external rewards that often fail to evaluate document faithfulness, and may misjudge similar answers in open-domain settings. In addition, there is no RAG-based selfreward mechanism. Moreover, although such a mechanism could in principle estimate answer confidence given documents, the absence of objective feedback in a self-judgment can cause hallucination accumulation and eventual model collapse. To tackle these issues, we propose a novel "internal-external" hybrid reward framework centered on a Contrastive Likelihood Reward (CLR). CLR directly optimizes the log-likelihood gap between responses conditioned on prompts with and without supporting evidence. This encourages the model to extract relevant evidence and increases its confidence when grounded in a specific context. Experiments show that our method (used alone or combined with external correctness rewards) achieves strong performance on singlehop, multi-hop, vertical-domain, and faithfulness benchmarks. Our training code and models are coming soon.

Foundation models are increasingly applied to computational pathology, yet their behavior under cross-cancer and cross-species transfer remains unspecified. This study investigated how fine-tuning CPath-CLIP affects cancer detection under same-cancer, cross-cancer, and cross-species conditions using whole-slide image patches from canine and human histopathology. Performance was measured using area under the receiver operating characteristic curve (AUC). Few-shot fine-tuning improved same-cancer (64.9% to 72.6% AUC) and cross-cancer performance (56.84% to 66.31% AUC). Cross-species evaluation revealed that while tissue matching enables meaningful transfer, performance remains below state-of-the-art benchmarks (H-optimus-0: 84.97% AUC), indicating that standard vision-language alignment is suboptimal for cross-species generalization. Embedding space analysis revealed extremely high cosine similarity (greater than 0.99) between tumor and normal prototypes. Grad-CAM shows prototype-based models remain domain-locked, while language-guided models attend to conserved tumor morphology. To address this, we introduce Semantic Anchoring, which uses language to provide a stable coordinate system for visual features. Ablation studies reveal that benefits stem from the text-alignment mechanism itself, regardless of text encoder complexity. Benchmarking against H-optimus-0 shows that CPath-CLIP's failure stems from intrinsic embedding collapse, which text alignment effectively circumvents. Additional gains were observed in same-cancer (8.52%) and cross-cancer classification (5.67%). We identified a previously uncharacterized failure mode: semantic collapse driven by species-dominated alignment rather than missing visual information. These results demonstrate that language acts as a control mechanism, enabling semantic re-interpretation without retraining.

Singular statistical models-including mixtures, matrix factorization, and neural networks-violate regular asymptotics due to parameter non-identifiability and degenerate Fisher geometry. Although singular learning theory characterizes marginal likelihood behavior through invariants such as the real log canonical threshold and singular fluctuation, these quantities remain difficult to interpret operationally. At the same time, widely used criteria such as WAIC and WBIC appear disconnected from underlying singular geometry. We show that posterior tempering induces a one-parameter deformation of the posterior distribution whose associated observables generate a hierarchy of thermodynamic response functions. A universal covariance identity links derivatives of tempered expectations to posterior fluctuations, placing WAIC, WBIC, and singular fluctuation within a unified response framework. Within this framework, classical quantities from singular learning theory acquire natural thermodynamic interpretations: RLCT governs the leading free-energy slope, singular fluctuation corresponds to curvature of the tempered free energy, and WAIC measures predictive fluctuation. We formalize an observable algebra that quotients out non-identifiable directions, allowing structurally meaningful order parameters to be constructed in singular models. Across canonical singular examples-including symmetric Gaussian mixtures, reduced-rank regression, and overparameterized neural networks-we empirically demonstrate phase-transition-like behavior under tempering. Order parameters collapse, susceptibilities peak, and complexity measures align with structural reorganization in posterior geometry. Our results suggest that thermodynamic response theory provides a natural organizing framework for interpreting complexity, predictive variability, and structural reorganization in singular Bayesian learning.

Reaching for grasping, and manipulating objects are essential motor functions in everyday life. Decoding human motor intentions is a central challenge for rehabilitation and assistive technologies. This study focuses on predicting intentions by inferring movement direction and target location from multichannel electromyography (EMG) signals, and investigating how spatially and temporally accurate such information can be detected relative to movement onset. We present a computational pipeline that combines data-driven temporal segmentation with classical and deep learning classifiers in order to analyse EMG data recorded during the planning, early execution, and target contact phases of a delayed reaching task. Early intention prediction enables devices to anticipate user actions, improving responsiveness and supporting active motor recovery in adaptive rehabilitation systems. Random Forest achieves $80\%$ accuracy and Convolutional Neural Network $75\%$ accuracy across $25$ spatial targets, each separated by $14^\circ$ azimuth/altitude. Furthermore, a systematic evaluation of EMG channels, feature sets, and temporal windows demonstrates that motor intention can be efficiently decoded even with drastically reduced data. This work sheds light on the temporal and spatial evolution of motor intention, paving the way for anticipatory control in adaptive rehabilitation systems and driving advancements in computational approaches to motor neuroscience.

The emergence of generative AI models has dramatically expanded the availability and use of synthetic data across scientific, industrial, and policy domains. While these developments open new possibilities for data analysis, they also raise fundamental statistical questions about when synthetic data can be used in a valid, reliable, and principled manner. This paper reviews the current landscape of synthetic data generation and use from a statistical perspective, with the goal of clarifying the assumptions under which synthetic data can meaningfully support downstream discovery, inference, and prediction. We survey major classes of modern generative models, their intended use cases, and the benefits they offer, while also highlighting their limitations and characteristic failure modes. We additionally examine common pitfalls that arise when synthetic data are treated as surrogates for real observations, including biases from model misspecification, attenuated uncertainty, and difficulties in generalization. Building on these insights, we discuss emerging frameworks for the principled use of synthetic data. We conclude with practical recommendations, open problems, and cautions intended to guide both method developers and applied researchers.

In clinical prediction settings the importance of a high-dimensional feature like genomics is often assessed by evaluating the change in predictive performance when adding it to a set of traditional clinical variables. This approach is questionable, because it does not account for collinearity nor known directionality of dependencies between variables. We suggest to use asymmetric Shapley values as a more suitable alternative to quantify feature importance in the context of a mixed-dimensional prediction model. We focus on a setting that is particularly relevant in clinical prediction: disease state as a mediating variable for genomic effects, with additional confounders for which the direction of effects may be unknown. We derive efficient algorithms to compute local and global asymmetric Shapley values for this setting. The former are shown to be very useful for inference, whereas the latter provide interpretation by decomposing any predictive performance metric into contributions of the features. Throughout, we illustrate our framework by a leading example: the prediction of progression-free survival for colorectal cancer patients.

Finding patient subgroups with similar characteristics is crucial for personalized decision-making in various disciplines such as healthcare and policy evaluation. While most existing approaches rely on unsupervised clustering methods, there is a growing trend toward using supervised clustering methods that identify operationalizable subgroups in the context of a specific outcome of interest. We propose Bayesian Supervised Causal Clustering (BSCC), with treatment effect as outcome to guide the clustering process. BSCC identifies homogenous subgroups of individuals who are similar in their covariate profiles as well as their treatment effects. We evaluate BSCC on simulated datasets as well as real-world dataset from the third International Stroke Trial to assess the practical usefulness of the framework.

Teachers face increasing demands on their time, particularly in adapting mathematics curricula to meet individual student needs while maintaining cognitive rigor. This study evaluates whether AI tools can accurately classify the cognitive demand of mathematical tasks, which is important for creating or adapting tasks that support student learning. We tested eleven AI tools: six general-purpose (ChatGPT, Claude, DeepSeek, Gemini, Grok, Perplexity) and five education-specific (Brisk, Coteach AI, Khanmigo, Magic School, School$.$AI), on their ability to categorize mathematics tasks across four levels of cognitive demand using a research-based framework. The goal was to approximate the performance teachers will achieve with straightforward prompts. On average, AI tools accurately classified cognitive demand in only 63% of cases. Education-specific tools were not more accurate than general-purpose tools, and no tool exceeded 83% accuracy. All tools struggled with tasks at the extremes of cognitive demand (Memorization and Doing Mathematics), exhibiting a systematic bias toward middle-category levels (Procedures with/without Connections). The tools often gave plausible-sounding explanations likely to be persuasive to novice teachers. Error analysis of AI tools' misclassification of the broad level of cognitive demand (high vs. low) revealed that tools consistently overweighted surface textual features over underlying cognitive processes. Further, AI tools showed weaknesses in reasoning about factors that make tasks higher vs. lower cognitive demand. Errors stemmed not from ignoring relevant dimensions, but from incorrectly reasoning about multiple task aspects. These findings carry implications for AI integration into teacher planning workflows and highlight the need for improved prompt engineering and tool development for educational applications.

We study online conformal prediction for non-stationary data streams subject to unknown distribution drift. While most prior work studied this problem under adversarial settings and/or assessed performance in terms of gaps of time-averaged marginal coverage, we instead evaluate performance through training-conditional cumulative regret. We specifically focus on independently generated data with two types of distribution shift: abrupt change points and smooth drift. When non-conformity score functions are pretrained on an independent dataset, we propose a split-conformal style algorithm that leverages drift detection to adaptively update calibration sets, which provably achieves minimax-optimal regret. When non-conformity scores are instead trained online, we develop a full-conformal style algorithm that again incorporates drift detection to handle non-stationarity; this approach relies on stability - rather than permutation symmetry - of the model-fitting algorithm, which is often better suited to online learning under evolving environments. We establish non-asymptotic regret guarantees for our online full conformal algorithm, which match the minimax lower bound under appropriate restrictions on the prediction sets. Numerical experiments corroborate our theoretical findings.

In this work, we presented Pailitao-VL, a comprehensive multi-modal retrieval system engineered for high-precision, real-time industrial search. We here address three critical challenges in the current SOTA solution: insufficient retrieval granularity, vulnerability to environmental noise, and prohibitive efficiency-performance gap. Our primary contribution lies in two fundamental paradigm shifts. First, we transitioned the embedding paradigm from traditional contrastive learning to an absolute ID-recognition task. Through anchoring instances to a globally consistent latent space defined by billions of semantic prototypes, we successfully overcome the stochasticity and granularity bottlenecks inherent in existing embedding solutions. Second, we evolved the generative reranker from isolated pointwise evaluation to the compare-and-calibrate listwise policy. By synergizing chunk-based comparative reasoning with calibrated absolute relevance scoring, the system achieves nuanced discriminative resolution while circumventing the prohibitive latency typically associated with conventional reranking methods. Extensive offline benchmarks and online A/B tests on Alibaba e-commerce platform confirm that Pailitao-VL achieves state-of-the-art performance and delivers substantial business impact. This work demonstrates a robust and scalable path for deploying advanced MLLM-based retrieval architectures in demanding, large-scale production environments.

Reconstructing time-resolved flow fields from temporally sparse velocimetry measurements is critical for characterizing many complex thermal-fluid systems. We introduce a machine learning framework for uncertainty-aware flow reconstruction using sparse variational Gaussian processes in the Kolmogorov-Arnold network topology (SVGP-KAN). This approach extends the classical foundations of Linear Stochastic Estimation (LSE) and Spectral Analysis Modal Methods (SAMM) while enabling principled epistemic uncertainty quantification. We perform a systematic comparison of our framework with the classical reconstruction methods as well as Kalman filtering. Using synthetic data from pulsed impingement jet flows, we assess performance across fractional PIV sampling rates ranging from 0.5% to 10%. Evaluation metrics include reconstruction error, generalization gap, structure preservation, and uncertainty calibration. Our SVGP-KAN methods achieve reconstruction accuracy comparable to established methods, while also providing well-calibrated uncertainty estimates that reliably indicate when and where predictions degrade. The results demonstrate a robust, data-driven framework for flow field reconstruction with meaningful uncertainty quantification and offer practical guidance for experimental design in periodic flows.

We propose FlexQP, an always-feasible convex quadratic programming (QP) solver based on an $\ell_1$ elastic relaxation of the QP constraints. If the original constraints are feasible, FlexQP provably recovers the optimal solution. If the constraints are infeasible, FlexQP identifies a solution that minimizes the constraint violation while keeping the number of violated constraints sparse. Such infeasibilities arise naturally in sequential quadratic programming (SQP) subproblems due to the linearization of the constraints. We prove the convergence of FlexQP under mild coercivity assumptions, making it robust to both feasible and infeasible QPs. We then apply deep unfolding to learn LSTM-based, dimension-agnostic feedback policies for the algorithm parameters, yielding an accelerated Deep FlexQP. To preserve the exactness guarantees of the relaxation, we propose a normalized training loss that incorporates the Lagrange multipliers. We additionally design a log-scaled loss for PAC-Bayes generalization bounds that yields substantially tighter performance certificates, which we use to construct an accelerated SQP solver with guaranteed QP subproblem performance. Deep FlexQP outperforms state-of-the-art learned QP solvers on a suite of benchmarks including portfolio optimization, classification, and regression problems, and scales to dense QPs with over 10k variables and constraints via fine-tuning. When deployed within SQP, our approach solves nonlinear trajectory optimization problems 4-16x faster than SQP with OSQP while substantially improving success rates. On predictive safety filter problems, Deep FlexQP reduces safety violations by over 70\% and increases task completion by 43\% compared to existing methods.