Adaptive programming practice often relies on fixed libraries of worked examples and practice problems, which require substantial authoring effort and may not correspond well to the logical errors and partial solutions students produce while writing code. As a result, students may receive learning content that does not directly address the concepts they are working to understand, while instructors must either invest additional effort in expanding content libraries or accept a coarse level of personalization. We present an approach for knowledge-component (KC) guided educational content generation using pattern-based KCs extracted from student code. Given a problem statement and student submissions, our pipeline extracts recurring structural KC patterns from students' code through AST-based analysis and uses them to condition a generative model. In this study, we apply this approach to worked example generation, and compare baseline and KC-conditioned outputs through expert evaluation. Results suggest that KC-conditioned generation improves topical focus and relevance to learners' underlying logical errors, providing evidence that KC-based steering of generative models can support personalized learning at scale.

Our main contribution is a strongly polynomial algorithm for computing an equilibrium for the Arctic Auction, which is the quasi-linear extension of the linear Fisher market model. We build directly on Orlin's strongly polynomial algorithm for the linear Fisher market (Orlin, 2010). The first combinatorial polynomial algorithm for the linear Fisher market was based on the primal-dual paradigm (Devanur et al., 2008). This was followed by Orlin's scaling-based algorithms. The Arctic Auction (Klemperer 2018) was developed for the Government of Iceland to allow individuals to exchange blocked offshore assets. It is a variant of the product-mix auction (Klemperer 2008, 2010, 2018) that was designed for, and used by, the Bank of England, to allocate liquidity efficiently across banks pledging heterogeneous collateral of varying quality. Our work was motivated by the fact that banks often need to run Arctic Auctions under many different settings of the parameters in order to home in on the right one, making it essential to find a time-efficient algorithm for Arctic Auction.

While the optimal sample complexity of binary classification in terms of the VC dimension is well-established, determining the optimal sample complexity of multiclass classification has remained open. The appropriate complexity parameter for multiclass classification is the DS dimension, and despite significant efforts, a gap of $\sqrt{\text{DS}}$ has persisted between the upper and lower bounds on sample complexity. Recent work by Hanneke et al. (2026) shows a novel algebraic characterization of multiclass hypothesis classes in terms of their DS dimension. Building up on this, we show that the maximum hypergraph density of any multiclass hypothesis class is upper-bounded by its DS dimension. This proves a longstanding conjecture of Daniely and Shalev-Shwartz (2014). As a consequence, we determine the optimal dependence of the sample complexity on the DS dimension for multiclass as well as list learning.

In this paper, we propose a harmonized rotational gradient method, termed HRGrad, for simultaneously tackling multiscale time-dependent kinetic problems with varying small parameters. These parameters exhibit asymptotic transitions from microscopic to macroscopic physics, making it a challenging multi-task problem to solve over all ranges simultaneously. Solving tasks in different asymptotic regions often encounter gradient conflicts, which can lead to the failure of multi-task learning. To address this challenge, we explicitly encode a hidden representation of these parameters, ensuring that the corresponding solving tasks are serialized for simultaneous training. Furthermore, to mitigate gradient conflicts, we segment the prediction results to construct task losses and introduce a novel gradient alignment metric to ensure a positive dot product between the final update and each loss-specific gradient. This metric maintains consistent optimization rates for all task losses and dynamically adjusts gradient magnitudes based on conflict levels. Moreover, we provide a mathematical proof demonstrating the convergence of the HRGrad method, which is evaluated across a range of challenging asymptotic-preserving neural networks (APNNs) scenarios. We conduct an extensive set of experiments encompassing the Bhatnagar-Gross-Krook (BGK) equation and the linear transport equation in all ranges of Knudsen number. Our results indicate that HRGrad effectively overcomes the `failure modes' of APNNs in these problems.

We study learning with Chain-of-Thought (CoT) supervision from multiple thinkers, all of whom provide correct but possibly systematically different solutions, e.g., step-by-step solutions to math problems written by different thinkers, or step-by-step execution traces of different programs solving the same problem. We consider classes that are computationally easy to learn using CoT supervision from a single thinker, but hard to learn with only end-result supervision, i.e., without CoT (Joshi et al. 2025). We establish that, under cryptographic assumptions, learning can be hard from CoT supervision provided by two or a few different thinkers, in passive data-collection settings. On the other hand, we provide a generic computationally efficient active learning algorithm that learns with a small amount of CoT data per thinker that is completely independent of the target accuracy $\varepsilon$, a moderate number of thinkers that scales as $\log \frac{1}{\varepsilon}\log \log \frac{1}{\varepsilon}$, and sufficient passive end-result data that scales as $\frac{1}{\varepsilon}\cdot poly\log\frac{1}{\varepsilon}$.

Linear contracts are ubiquitous in practice, yet optimal contract theory often prescribes complex, nonlinear structures. We provide a distributional robustness justification for linear contracts. We study a principal-agent problem where the agent exerts costly effort across multiple tasks, generating a stochastic signal upon which the principal conditions payment. The principal faces distributional ambiguity: she knows the expected signal for each effort level, but not the full distribution. She seeks a contract maximizing her worst-case payoff over all distributions consistent with this partial knowledge. Our main result shows that linear contracts are optimal for such a principal. For any contract, there exists a linear contract achieving weakly higher worst-case payoff. The proof introduces the concavification approach built around the notion of self-inducing actions; these are actions where an affine contract simultaneously induces the action as optimal and supports the concave envelope of payments from above. We show that self-inducing actions always exist as maximizers of the gap between the concave envelope and agent's cost function. We extend these results to multi-party settings. In common agency with multiple principals, we show that affine contracts improve all principals' worst-case payoffs. In team production with multiple agents, we establish a complementary necessity result: if any agent's contract is non-affine, the unique ex-post robust equilibrium is zero effort. Finally, we show that homogeneous utility and cost functions yield tractable characterizations, enabling closed-form approximation ratios and a sharp boundary between computational tractability results.

We study a model describing the slow flow of a fluid through a deformable, porous, elastic solid undergoing small deformations. The stress-strain relationship of the solid incorporates nonlinear effects, formulated as a perturbation of the classical linear elasticity. To approximate the coupled system, we introduce a discrete scheme based on a first order semi-implicit time integration scheme combined with a standard finite element spatial discretization. We establish the existence and uniqueness of the discrete solution and derive a priori convergence estimates under the assumption that the nonlinear perturbations remain sufficiently small. Finally, we demonstrate the efficiency of the proposed scheme through numerical experiments that also highlight the nonlinear phenomena captured by the model.

Specification-guided reinforcement learning (RL) provides a principled framework for encoding complex, temporally extended tasks using formal specifications such as linear temporal logic (LTL). While recent methods have shown promising results, their ability to generalize across unseen specifications and diverse environments remains insufficiently understood. In this work, we introduce SpecRLBench, a benchmark designed to evaluate the generalization capabilities of LTL-based specification-guided RL methods. The benchmark spans multiple difficulty levels across navigation and manipulation domains, incorporating both static and dynamic environments, diverse robot dynamics, and varied observation modalities. Through extensive empirical evaluation, we characterize the strengths and limitations of existing approaches and reveal the challenges that emerge as specification and environment complexity increase. SpecRLBench provides a structured platform for systematic comparison and supports the development of more generalizable specification-guided RL methods. Code is available at https://github.com/BU-DEPEND-Lab/SpecRLBench.

In practical early-stage battery-electric vehicle studies, analysis workflows may become fragmented across spreadsheets, notebooks, and project-specific scripts, making reuse, audit, and extension harder. VEHRON is an open-source Python framework for a deterministic, traceable workflow built around prescribed-speed longitudinal simulation of battery-electric vehicles using validated YAML configuration, packaged drive-cycle resources, interchangeable subsystem models, and auditable case outputs. VEHRON currently runs as a command-line workflow in which a vehicle definition and a testcase definition are combined to execute a simulation, emit a flat time series, and write a case package containing copied inputs, resolved configuration, summary metadata, and standard plots. Architecturally, VEHRON is organized around a small simulation engine, a shared state bus, a registry of model selections, schema-based configuration loading, and extension points for custom battery and HVAC models loaded from external Python files. VEHRON currently focuses on battery-electric longitudinal simulation with low-order battery, thermal, auxiliary-load, and HVAC models. This paper explains how VEHRON is structured, how it is used, which models it implements, and where its present limits lie. Source code is available at https://github.com/vehron-dev/vehron, with archived release metadata recorded under DOI https://doi.org/10.5281/zenodo.19820111.

Indonesian marketplace reviews mix standard vocabulary with slang, regional loanwords, numeric shorthands, and emoji, making lexicon-based sentiment tools unreliable in practice. This paper describes a two-track classification pipeline applied to the PRDECT-ID dataset, which contains 5,400 product reviews from 29 Indonesian e-commerce categories, each labeled for binary sentiment (Positive/Negative) and five-class emotion (Happy, Sad, Fear, Love, Anger). The first track applies TF-IDF vectorization with a PyCaret AutoML sweep across standard classifiers. The second track is a PyTorch Bidirectional Long Short-Term Memory (BiLSTM) network with a shared encoder and two task-specific output heads. A preprocessing module applies 14 sequential cleaning steps, including a 140-entry slang dictionary assembled from marketplace corpora. Four configurations are benchmarked: BiLSTM Baseline, BiLSTM Improved, BiLSTM Large, and TextCNN. Training uses class-weighted cross-entropy loss, ReduceLROnPlateau scheduling, and early stopping. Both tracks are deployed as Gradio applications on Hugging Face Spaces. Source code is publicly available at https://github.com/ikii-sd/pba2026-crazyrichteam.

Segmentation models such as Segment Anything Model (SAM) and SAM2 achieve strong prompt-driven zero-shot performance. However, their training on natural images limits domain transfer to medical data. Consequently, accurate segmentation typically requires extensive fine-tuning and expert-designed prompts. We propose DiffuSAM, a diffusion-based adaptation of SAM2 for prompt-free medical image segmentation. Our framework synthesizes SAM2-compatible segmentation mask-like embeddings via a lightweight diffusion-prior from off-the-shelf frozen SAM2 image features. The generated embeddings are integrated into SAM2's mask decoder to produce accurate segmentations, thereby eliminating the need for user prompts. The diffusion prior is further conditioned on previously segmented slices, enforcing spatial consistency across volumes. Evaluated on the BTCV and CHAOS datasets for CT and MRI under Source-Free Unsupervised Domain Adaptation (SF-UDA) and Few-Shot settings, DiffuSAM achieves competitive performance with efficient training and inference. Code is available upon request from the corresponding author.

Monocular RGB cameras mounted on drones are widely used for wildlife monitoring, yet most analytical pipelines remain confined to two-dimensional image space, leaving geometric information in video underexploited. We present WildLIFT, a computational framework that integrates three-dimensional scene geometry from monocular drone video with open-vocabulary 2D instance segmentation to enable species-agnostic 3D detection and tracking. Oriented 3D bounding box labels with semantic face information enable quantitative assessment of viewpoint coverage and inter-animal occlusion, producing structured metadata for downstream ecological analyses. We validate the framework on 2,581 manually curated frames comprising over 6,700 3D detections across four large mammal species. WildLIFT maintains high identity consistency in multi-animal scenes and substantially reduces manual 3D annotation effort through keyframe-based refinement. By transforming standard drone footage into structured 3D and viewpoint-aware representations, WildLIFT extends the analytical utility of aerial wildlife datasets for behavioural research and population monitoring.

Every Transformer architecture dedicates enormous capacity to learning rich representations in semantic embedding space -- yet the rotation manifold acted upon by Rotary Positional Embeddings (RoPE) has been treated as a fixed, hand-crafted structure, populated only by discrete ordinal indices. We argue that this rotation space is a largely overlooked second dimension of expressivity in the attention mechanism, one whose systematic exploration may open a new door for attention-based architectures. The analogy to complex numbers is instructive: just as introducing the imaginary axis -- orthogonal to and independent of the real line -- unlocked new algebraic structure once believed impossible, treating the rotation manifold as a learnable, signal-conditioned space opens an orthogonal degree of freedom in attention. In this framing, the token embedding encodes the semantic (real) component of a representation -- what a token means -- while the rotation encodes its dynamic (imaginary) component -- how it relates to every other token across time, position, and context. We introduce SIREN-RoPE, a concrete instantiation of this idea, which populates the rotation dimension with heterogeneous signals -- continuous timestamps, cyclical temporal patterns, and categorical metadata -- via a dual-branch Sinusoidal Representation Network (SIREN). As a proof of concept, we evaluate on a production-scale news feed dataset from a major social network using a generative recommender as the ranking model, demonstrating that activating this hidden dimension yields consistent improvements across calibration and ranking objectives with negligible computational overhead. We invite the community to view the rotation space not as a solved positional-encoding detail, but as an untapped axis whose rich structure may prove as consequential for attention as the imaginary unit proved for algebra.

Hybrid sequence models that combine efficient Transformer components with linear sequence modeling blocks are a promising alternative to pure Transformers, but most are still pretrained from scratch and therefore fail to reuse existing Transformer checkpoints. We study upcycling as a practical path to convert pretrained Transformer LLMs into hybrid architectures while preserving short-context quality and improving long-context capability. We call our solution \emph{HyLo} (HYbrid LOng-context): a long-context upcycling recipe that combines architectural adaptation with efficient Transformer blocks, Multi-Head Latent Attention (MLA), and linear blocks (Mamba2 or Gated DeltaNet), together with staged long-context training and teacher-guided distillation for stable optimization. HyLo extends usable context length by up to $32\times$ through efficient post-training and reduces KV-cache memory by more than $90\%$, enabling up to 2M-token prefill and decoding in our \texttt{vLLM} inference stack, while comparable Llama baselines run out of memory beyond 64K context. Across 1B- and 3B-scale settings (Llama- and Qwen-based variants), HyLo delivers consistently strong short- and long-context performance and significantly outperforms state-of-the-art upcycled hybrid baselines on long-context evaluations such as RULER. Notably, at similar scale, HyLo-Qwen-1.7B trained on only 10B tokens significantly outperforms JetNemotron (trained on 400B tokens) on GSM8K, Lm-Harness common sense reasoning and RULER-64K.

Large language models are increasingly used for code generation, yet the correctness of their outputs depends not only on model capability but also on how tasks are specified. Prior studies demonstrate that small changes in natural language prompts, particularly under-specification can substantially reduce code correctness; however, these findings are largely based on minimal-specification benchmarks such as HumanEval and MBPP, where limited structural redundancy may exaggerate sensitivity. In this exploratory study, we investigate how prompt structure, task complexity, and specification richness interact with LLM robustness to prompt mutations. We evaluate 10 different models across HumanEval and the structurally richer LiveCodeBench. Our results reveal that robustness is not a fixed property of LLMs but is highly dependent on prompt structure: the same under-specification mutations that degrade performance on HumanEval have near-zero net effect on LiveCodeBench due to redundancy across descriptions, constraints, examples, and I/O conventions. Surprisingly, we also find that prompt mutations can improve correctness. In LiveCodeBench, under-specification often breaks misleading lexical or structural cues that trigger incorrect retrieval-based solution strategies, leading to correctness improvements that counterbalance degradations. Manual analysis identifies consistent mechanisms behind these improvements, including the disruption of over-fitted terminology, removal of misleading constraints, and elimination of spurious identifier triggers. Overall, our study shows that structurally rich task descriptions can substantially mitigate the negative effects of under-specification and, in some cases, even enhance correctness. We outline categories of prompt modifications that positively influence the behavior of LLM code-generation, offering practical insights for writing robust prompts.

Objective. Clinical AI documentation systems require evaluation methodologies that are clinically valid, economically viable, and sensitive to iterative changes. Methods requiring expert review per scoring instance are too slow and expensive for safe, iterative deployment. We present a case-specific, clinician-authored rubric methodology for clinical AI evaluation and examine whether LLM-generated rubrics can approximate clinician agreement. Materials and Methods. Twenty clinicians authored 1,646 rubrics for 823 clinical cases (736 real-world, 87 synthetic) across primary care, psychiatry, oncology, and behavioral health. Each rubric was validated by confirming that an LLM-based scoring agent consistently scored clinician-preferred outputs higher than rejected ones. Seven versions of an EHR-embedded AI agent for clinicians were evaluated across all cases. Results. Clinician-authored rubrics discriminated effectively between high- and low-quality outputs (median score gap: 82.9%) with high scoring stability (median range: 0.00%). Median scores improved from 84% to 95%. In later experiments, clinician-LLM ranking agreement (tau: 0.42-0.46) matched or exceeded clinician-clinician agreement (tau: 0.38-0.43), attributable to both ceiling compression and LLM rubric improvement. Discussion. This convergence supports incorporating LLM rubrics alongside clinician-authored ones. At roughly 1,000 times lower cost, LLM rubrics enable substantially greater evaluation coverage, while continued clinical authorship grounds evaluation in expert judgment. Ceiling compression poses a methodological challenge for future inter-rater agreement studies. Conclusion. Case-specific rubrics offer a path for clinical AI evaluation that preserves expert judgment while enabling automation at three orders lower cost. Clinician-authored rubrics establish the baseline against which LLM rubrics are validated.

Training large neural networks with data-parallel stochastic gradient descent allocates N GPU replicas to compute effectively identical updates -- a practice that leaves the rich space of learning rate configurations entirely unexplored during training. We propose Hyperparameter-Divergent Ensemble Training (HDET), a method that repurposes these replicas for simultaneous learning rate exploration at negligible communication overhead. HDET operates in alternating phases: a fan-out stage in which replicas train independently under a structured, symmetric spread of learning rates, and a converge stage in which parameters are averaged across all replicas via AllReduce every T steps. Building on this ensemble substrate, we further propose an automatic learning rate (auto-LR) controller that treats the relative training loss across replicas as a performance signal, updating the shared base schedule toward higher-performing configurations via a momentum-based gradient-free meta-update. The combined method produces a self-adapting learning rate schedule that improves both optimization quality and generalization without additional hyperparameter sweeps or training budget. Crucially, the framework generalizes beyond learning rate: any scalar hyperparameter that does not alter model architecture -- such as dropout rate, attention scale temperature, or weight-decay coefficient -- can be explored across replicas using the same fan-out/converge protocol, with inter-replica loss differences serving as zero-order hypergradients that guide the search direction. HDET is implemented as a drop-in replacement for PyTorch's OneCycleLR scheduler, requiring no changes to model architecture, optimizer, or data pipeline.

Doorways and passages are critical structural elements for indoor robot navigation, yet they remain underexplored in modern Visual SLAM (VSLAM) frameworks. This paper presents a passage-aware structural mapping approach for RGB-D VSLAM that detects doors and traversable openings by jointly fusing geometric, semantic, and topological cues. Doors are modeled as planar entities embedded within walls and classified as traversable or non-traversable based on their coplanarity with the supporting wall. Passages are inferred through two complementary strategies: traversal evidence accumulated from camera-wall interactions across consecutive keyframes, and geometric opening validation based on discontinuities in the mapped wall geometry. The proposed method is integrated into vS-Graphs as a proof of concept, enriching its scene graph with passage-level abstractions and improving room connectivity modeling. Qualitative evaluations on indoor office sequences demonstrate reliable doorway detection, and the framework lays the foundation for exploiting these elements in BIM-informed VSLAM. The source code is publicly available at https://github.com/snt-arg/visual_sgraphs/tree/doorway_integration.

Learning-based control techniques use data from past trajectories to control systems with uncertain dynamics. However, learning-based controllers are often computationally inefficient, limiting their practicality. To address this limitation, we propose a learning-based controller that exploits differential flatness, a property of many robotic systems. Recent research on using flatness for learning-based control either is limited in that it (i) ignores input constraints, (ii) applies only to single-input systems, or (iii) is tailored to specific platforms. In contrast, our approach uses a system extension and block-diagonal cost formulation to control general multi-input, nonlinear, affine systems. Furthermore, it satisfies input and half-space flat state constraints and guarantees probabilistic Lyapunov decrease using only two sequential convex optimizations. We show that our approach performs similarly to, but is multiple times more efficient than, a Gaussian process model predictive controller in simulation, and achieves competitive tracking in real hardware experiments.

Energy forecasting research faces a persistent comparability gap that makes it difficult to measure consistent progress over time. Reported accuracy gains are often not directly comparable because models are evaluated under study-specific datasets, time periods, information sets, and scoring setups, while widely used benchmarks and competition datasets are typically tied to fixed historical windows. This paper introduces the Energy-Arena, a dynamic benchmarking platform for operational energy time series forecasting that provides a continuously updated reference point as energy systems evolve. The platform operates as an open, API-based submission system and standardizes challenge definitions and submission deadlines aligned with operational constraints. Performance is reported on rolling evaluation windows via persistent leaderboards. By moving from retrospective backtesting to forward-looking benchmarking, the Energy-Arena enforces standardized ex-ante submission and ex-post evaluation, thereby improving transparency by preventing information leakage and retroactive tuning. The platform is publicly available at Energy-Arena.org.

Large language models are widely used for code generation, yet they rely on an implicit assumption that the task descriptions are sufficiently detailed and well-formed. However, in practice, users may provide defective descriptions, which can have a strong effect on code correctness. To address this issue, we develop SpecValidator, a lightweight classifier based on a small model that has been parameter-efficiently finetuned, to automatically detect task description defects. We evaluate SpecValidator on three types of defects, Lexical Vagueness, Under-Specification and Syntax-Formatting on 3 benchmarks with task descriptions of varying structure and complexity. Our results show that SpecValidator achieves defect detection of F1 = 0.804 and MCC = 0.745, significantly outperforming GPT-5-mini (F1 = 0.469 and MCC = 0.281) and Claude Sonnet 4 (F1 = 0.518 and MCC = 0.359). Perhaps more importantly, our analysis indicates that SpecValidator can generalize to unseen issues and detect unknown Under-Specification defects in the original (real) descriptions of the benchmarks used. Our results also show that the robustness of LLMs in task description defects depends primarily on the type of defect and the characteristics of the task description, rather than the capacity of the model, with Under-Specification defects being the most severe. We further found that benchmarks with richer contextual grounding, such as LiveCodeBench, exhibit substantially greater resilience, highlighting the importance of structured task descriptions for reliable LLM-based code generation.

Side Channel Analysis (SCA) relaxes the black-box assumption of conventional cryptanalysis by incorporating physical measurements acquired during cryptographic operations. Electro-magnetic (EM) emissions of a chip during computations often provide a very valuable source of side channel leakage. During the evaluation of a chip for electro-magnetic side channel emissions one needs to position an electro-magnetic probe in an advantageous position relative to the chip. Previous literature focused on hot-spot finding and to a lower extend repositioning. Trace augmentations have been considered to aid portability of profiling using one physical device and attacking another device. This paper focuses on training a single neural network using traces from multiple EM probe positions to detect leakage from a larger area over the attacked device. We provide dual evaluation of EM traces - from two completely independent labs - profiling on data from one lab and attacking traces from the other lab.

Large language models (LLMs) are increasingly deployed, yet their outputs can be highly sensitive to routine, non-adversarial variation in how users phrase queries, a gap not well addressed by existing red-teaming efforts. We propose Green Shielding, a user-centric agenda for building evidence-backed deployment guidance by characterizing how benign input variation shifts model behavior. We operationalize this agenda through the CUE criteria: benchmarks with authentic Context, reference standards and metrics that capture true Utility, and perturbations that reflect realistic variations in the Elicitation of model behavior. Guided by the PCS framework and developed with practicing physicians, we instantiate Green Shielding in medical diagnosis through HealthCareMagic-Diagnosis (HCM-Dx), a benchmark of patient-authored queries, together with structured reference diagnosis sets and clinically grounded metrics for evaluating differential diagnosis lists. We also study perturbation regimes that capture routine input variation and show that prompt-level factors shift model behavior along clinically meaningful dimensions. Across multiple frontier LLMs, these shifts trace out Pareto-like tradeoffs. In particular, neutralization, which removes common user-level factors while preserving clinical content, increases plausibility and yields more concise, clinician-like differentials, but reduces coverage of highly likely and safety-critical conditions. Together, these results show that interaction choices can systematically shift task-relevant properties of model outputs and support user-facing guidance for safer deployment in high-stakes domains. Although instantiated here in medical diagnosis, the agenda extends naturally to other decision-support settings and agentic AI systems.

Applications based on large language models (LLMs), such as multi-agent simulations, require population diversity among agents. We identify a pervasive failure mode we term \emph{Persona Collapse}: agents each assigned a distinct profile nonetheless converge into a narrow behavioral mode, producing a homogeneous simulated population. To quantify persona collapse, we propose a framework that measures how much of the persona space a population occupies (Coverage), how evenly agents spread across it (Uniformity), and how rich the resulting behavioral patterns are (Complexity). Evaluating ten LLMs on personality simulation (BFI-44), moral reasoning, and self-introduction, we observe persona collapse along two axes: (1) Dimensions: a model can appear diverse on one axis yet structurally degenerate on another, and (2) Domains: the same model may collapse the most in personality yet be the most diverse in moral reasoning. Furthermore, item-level diagnostics reveal that behavioral variation tracks coarse demographic stereotypes rather than the fine-grained individual differences specified in each persona. Counter-intuitively, \textbf{the models achieving the highest per-persona fidelity consistently produce the most stereotyped populations}. We release our toolkit and data to support population-level evaluation of LLMs.

Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effective, existing methods often apply a fixed steering strength to all tokens, resulting in inconsistent steering quality across diverse input prompts. In this work, we introduce Contextual Linear Activation Steering (CLAS), a method that dynamically adapts linear activation steering to context-dependent steering strengths. Across eleven steering benchmarks and four model families, it consistently outperforms standard linear activation steering and matches or exceeds the performance of ReFT and LoRA in settings with limited labeled data. We therefore propose CLAS as a scalable, interpretable, and accurate method for specializing and steering large language models.

We propose Noise-Based Spectral Embedding (NBSE), a physics-informed framework for selecting informative features from high-dimensional data without greedy search. NBSE constructs a sparse similarity graph on the samples and identifies the Nishimori temperature $β_N$ the critical inverse temperature at which the Bethe Hessian becomes singular. The corresponding smallest eigenvector captures the dominant mode of an intrinsically degree-corrected diffusion process, naturally reweighting nodes to prevent hub dominance. By transposing the data matrix and applying NBSE in feature space, we obtain a one-dimensional spectral embedding that reveals groups of redundant or semantically related dimensions; balanced binning then selects one representative per group. We prove that coloured Gaussian perturbations shift $β_N$ by at most $O(\barσ^2)$, guaranteeing robustness to measurement noise. Experiments on ImageNet embeddings from MobileNetV2 and EfficientNet-B4 show that NBSE preserves classification accuracy even under aggressive compression: on EfficientNet-B4 the accuracy drop is below $1\%$ when retaining only $30\%$ of features, outperforming ANOVA $F$-test and random selection by up to $6.8\%$.

In this paper, we study the reachability of two closely related matrices appearing in the analysis of linear time-varying (LTV) systems over a finite time interval, namely, its closed-loop state transition matrix via a state feedback control and its state covariance matrix starting from some given initial state covariance matrix. Under a mild assumption, we first characterize the set of closed-loop terminal state transition matrices reachable from the identity matrix using controls of the state feedback form. Then, we provide the set of terminal state covariance matrices reachable from any given positive definite initial state covariance matrix when the LTV system is not necessarily controllable. Both results are based on the solutions of corresponding matrix Riccati differential equations (RDE).

While Large Language Models (LLMs) have increasingly assisted in historical tasks such as text processing, their capacity for professional-level historical reasoning remains underexplored. Existing benchmarks primarily assess basic knowledge breadth or lexical understanding, failing to capture the higher-order skills, such as evidentiary reasoning,that are central to historical research. To fill this gap, we introduce ProHist-Bench, a novel benchmark anchored in the Chinese Imperial Examination (Keju) system, a comprehensive microcosm of East Asian political, social, and intellectual history spanning over 1,300 years. Developed through deep interdisciplinary collaboration, ProHist-Bench features 400 challenging, expert-curated questions across eight dynasties, accompanied by 10,891 fine-grained evaluation rubrics. Through a rigorous evaluation of 18 LLMs, we reveal a significant proficiency gap: even state-of-the-art LLMs struggle with complex historical research questions. We hope ProHist-Bench will facilitate the development of domain-specific reasoning LLMs, advance computational historical research, and further uncover the untapped potential of LLMs. We release ProHist-Bench at https://github.com/inclusionAI/ABench/tree/main/ProHist-Bench.

Autonomous AI agents can remain fully authorized and still become unsafe as behavior drifts, adversaries adapt, and decision patterns shift without any code change. We propose the \textbf{Informational Viability Principle}: governing an agent reduces to estimating a bound on unobserved risk $\hat{B}(x) = U(x) + SB(x) + RG(x)$ and allowing an action only when its capacity $S(x)$ exceeds $\hat{B}(x)$ by a safety margin. The \textbf{Agent Viability Framework}, grounded in Aubin's viability theory, establishes three properties -- monitoring (P1), anticipation (P2), and monotonic restriction (P3) -- as individually necessary and collectively sufficient for documented failure modes. \textbf{RiskGate} instantiates the framework with dedicated statistical estimators (KL divergence, segment-vs-rest $z$-tests, sequential pattern matching), a fail-secure monotonic pipeline, and a closed-loop Autopilot formalised as an instance of Aubin's regulation map with kill-switch-as-last-resort; a scalar Viability Index $VI(t) \in [-1,+1]$ with first-order $t^*$ prediction transforms governance from reactive to predictive. Contributions are the theoretical framework, the reference implementation, and analytical coverage against published agent-failure taxonomies; quantitative empirical evaluation is scoped as follow-up work.

Chromosome analysis is a fundamental step in the diagnosis of genetic diseases, but the manual karyotyping workflow is time-consuming and heavily dependent on expert specialists, often requiring several days per patient. Although Deep Learning models have achieved high performance in chromosome detection, most proposed solutions remain restricted to research prototypes or lack graphical interfaces suitable for clinical use. In this work, we present Aycromo, an open-source desktop platform for AI-assisted cytogenetic analysis. Built on Electron and ONNX Runtime, the tool allows cytogeneticists to load pre-trained models, compare architectures through an integrated benchmarking module, and manually correct detections via an interactive annotation interface, all without command-line interaction. Preliminary experiments on metaphase images from the CRCN-NE dataset demonstrate that YOLOv11 achieves 99.40% mAP@50, while the platform reduces per-slide analysis to seconds