Papers

The extreme persistence of per- and polyfluoroalkyl substances (PFAS) in the environment is rooted in their three-dimensional molecular conformation. The helical twist adopted by perfluoroalkyl chains due to hyperconjugation involving their recalcitrant C-F bonds governs their resistance to degradation, yet a quantitative, continuous metric for helicity has remained absent. Here we introduce a data-driven framework that quantifies backbone helicity using three statistical descriptors: void-state (binary occupancy) spatial autocorrelations, local backbone principal component analysis, and persistent homology. We further validate each statistical descriptor against geometric dihedral benchmarks and DFT-calculated Vibrational Circular Dichroism (VCD) spectra. The framework is initially established on a homologous series of perfluorocarboxylic acids (FC2 through FC16) and their hydrogenated analogues, then extended across perfluorosulfonic acids, fluorotelomer alcohols, polyfluoroalkyl hexanoic acid analogues, and longer-chain PFOA and PFOS analogues. Agreement between statistical, geometric, and spectroscopic definitions of helicity is established for PFCAs and extended to structurally distinct subfamilies, including PFOA analogues of varying fluorine content and perfluorosulfonic acids, demonstrating that the descriptors are robust to changes in headgroup chemistry and fluorine substitution pattern. The framework provides a chemistry-agnostic toolset for incorporating backbone conformation into predictive models of PFAS environmental fate and degradation reactivity.

Retrieval-augmented question answering is increasingly used to help people navigate public-benefits eligibility, yet the documents these systems retrieve from are written in agency register while intended users often ask questions in plain, informal, or non-native English. We show that this register mismatch can turn a high-performing retrieval system into an inequitable one. We construct a controlled benchmark of 51 publicly documented federal benefit-eligibility rules and 25 information needs, each phrased in both agency register and plain user register while keeping the gold passage fixed. Across BM25, TF-IDF, and a term-graph retriever, formal-register evaluation is nearly perfect (Recall@5 96-100%), but plain-register retrieval collapses (Recall@5 36-44%). For BM25, Recall@1 falls from 84% to 16% and Recall@5 from 100% to 44%, a 56-point equity gap on identical information needs. We trace the mechanism to a measurable vocabulary gap: formal queries share 0.63 of their content terms with the gold passage, while plain queries share only 0.11, a 5.9x reduction. A deliberately simple, auditable plain-to-formal lexicon bridge recovers much of the failure, lifting plain-query BM25 Recall@5 from 44% to 80%. The contribution is not a new retriever; it is an evaluation protocol, benchmark, mechanistic diagnosis, and transparent mitigation for a high-stakes social-impact failure mode that standard retrieval evaluation hides.

Effective skill identification is crucial for LLM agents to reuse task-solving experience for complex task execution, which however remains challenging as agents must accurately identify useful skills from a large skill gallery and invoke them on demand. Existing studies have explored various strategies for skill retrieval and invocation, but largely overlook the natural discrepancy between task descriptions and skill documents. To be specific, our empirical study reveals that task descriptions mainly specify task objectives, whereas skill documents describe the required capabilities and procedural guidance for achieving the objectives. Such a so-called Task–Skill Misalignment (TSM) problem would cause desirable skills to be neglected during retrieval or remain unselected during invocation, thus hindering task execution. As a remedy, inspired by human prospective cognition, we propose SkillDreamer, a prospective skill identification framework to mitigate TSM. In brief, SkillDreamer first infers execution-required capabilities and imagines their realizations as pseudo skills, thereby translating task objectives into execution-oriented guidance for skill retrieval. As execution proceeds, SkillDreamer reevaluates the capabilities required by emerging subtasks to determine which skills should be invoked, thereby aligning skill invocation with evolving execution needs. Extensive experiments on three representative agent skill benchmarks not only verify the effectiveness of SkillDreamer in mitigating TSM, but also demonstrate its generalizability across diverse retrievers and LLM agents. The code will be released upon acceptance.

In the era of digital social interaction, searching friends' posts from massive social streams has become a fundamental user need. However, while modern agentic search frameworks have achieved remarkable success in conventional retrieval tasks, they break down when confronted with heterogeneous user queries and multi-dimensional social feeds, resulting in severe performance degradation in complex social search. To bridge this gap, we introduce SocialBuddy, the first agentic search framework tailored for social scenarios. Specifically, we construct SocialEnv, the first large-scale simulated environment for social search. Powered by an automated data and trajectory synthesis pipeline, SocialEnv includes 200K user profiles, 10 million social posts, and 50K reasoning trajectories, establishing a solid foundation for the development of social search agents. To tackle the credit assignment dilemma caused by sparse rewards in social search, we design SocialPO, a hybrid-granularity optimization framework. It macroscopically reinforces successful reasoning paths via multi-dimensional rewards, while microscopically rectifying deviated trajectories through fine-grained prefix truncation and token-level supervision. This hybrid-granularity design delivers multi-scale guidance in complex long-sequence scenarios. Finally, we construct SocialSearch Benchmark to provide a quantitative evaluation scheme for assessing the social search capabilities of SocialBuddy. Extensive experiments demonstrate that SocialBuddy-35B surpasses significantly larger frontier LLMs. Code and dataset will be released upon article acceptance.

Mathematical communities work with different objects, invariants, and tools, so transferring a problem across them is expensive and often skipped. We present EULER, a multi-agent system that takes such a transfer–a bridge–as its unit of search. Around a fixed conjecture, EULER runs direct, adjacent-domain, and distant-domain routes in competition; a bridge keeps its budget only if it supplies an operation the source representation cannot execute and its target-side evidence returns to the original statement along a checked implication. Six ordered stress tests reject invalid bridges before expensive search begins. We evaluate EULER on 120 recent conjectures. The conjectures were frozen before search and screened for contamination, and are drawn from public papers by authors who had recently published in the Journal of Combinatorial Theory, Series A, a leading journal in combinatorics. EULER produced 10 proofs and 3 refutations, plus 45 scoped partial results. Two mechanisms held up under ablation: bridge-specific stress tests cut incorrect conclusions from 9 to 3, and bridge material combined with a target-native operation yielded a positive interaction of +4.2 resolved tasks that neither factor produced alone. Domain distance did not reliably predict success; executable operation gain and valid return did.

Diffusion history reconstruction infers latent node states between sparse observations of SI or SIR processes. HERMES combines parameter fitting, a learned graph-neural proposal, and feasibility-aware Markov chain Monte Carlo. We remove these stages one at a time and evaluate each version on all 12 canonical datasets. The final method uses deterministic mean-field forward-backward inference, threshold decoding, and fixed rates. This fixed-rate variant, Battus-Z, achieves mean macro-F1 of 0.8726 and NRMSE of 0.1010, compared with published HERMES aggregates of 0.8692 and 0.1483. The benchmark pins the final observed frame before scoring, so we also exclude all observed frames. Under this metric, Battus-Z obtains macro-F1 0.8431 and NRMSE 0.1181. Thus, the learned proposal, MCMC, and fitting stages can be removed while retaining the published aggregate quality on the evaluated HERMES benchmark and scoring protocol. A CUDA implementation processes generated histories with up to 4.84M vertices on LiveJournal and 117M edges on Orkut. On the same CUDA backend, Battus-Z reduces the geometric-mean algorithm interval relative to fitted Battus by 5.1x for SI and 20.3x for SIR. Its event-weighted causal-violation rates are 7.50% for SI and 8.77% for SIR; graph-constrained decoding remains future work.

This paper presents several parallel versions of Jacobi's method for the symmetric eigenvalue problem and the SVD. A continuation of [Demmel, Luo, Schneider, & Wang 2025], we develop parallel Jacobi algorithms whose arithmetic cost is optimal and whose bandwidth or latency can match the corresponding lower bounds of parallel matrix multiplication. Our focus is a standard distributed-memory setting with variable processor layouts, including both 2D and 2.5D processor grids. In the 2D case, we demonstrate that a standard implementation of parallel Jacobi achieves a perfect speedup in arithmetic cost – i.e., complexity $O(n^3/P)$ when done with $P$ processors – while hitting the 2D matrix-multiplication lower bound for bandwidth and (nearly) the lower bound for latency. By employing a 2.5D processor grid and leveraging 2.5D matrix multiplication, equivalently by increasing the memory per processor, we demonstrate that parallel Jacobi can achieve even lower bandwidth/latency, though we also prove that these costs cannot simultaneously match the best-known bounds for parallel matrix multiplication in any Jacobi algorithm. Finally, we extend our results to one-sided Jacobi SVD.

We introduce the Web-CLI, a novel application architecture deploying powerful computational capabilities (command-line tools compiled to WebAssembly, models run through client-side inference runtimes, and GPU-accelerated engines) as zero-install, offline-capable browser applications that preserve full underlying capability. Unlike web-based alternatives that require server-side processing and expose user data to third parties, Web-CLI applications execute entirely on the client, providing a verifiable privacy guarantee by architecture rather than policy. We define the pattern and its four properties: fidelity, progressive disclosure, offline-first, and zero egress. We present four reference implementations across distinct domains: ffmpeg-webCLI, a browser-based video editor built on FFmpeg; whisper-webCLI, speech transcription via Transformers.js; chat-webCLI, WebLLM-based language model inference; and 3mf-webCLI, a deterministic tool segmenting 3D models into multi-material files for physical 3D printing. Together they demonstrate that the pattern generalizes across deterministic media processing, neural speech recognition, LLM inference, and geometry processing with a physical output, and we outline how it extends to AI-native interfaces in which a local language model becomes the command surface itself. We further report early, anecdotal signs of independent reuse by third-party tools, suggesting the pattern generalizes beyond its reference implementations. We evaluate the primary implementation against native FFmpeg on performance and feature parity, and argue that progressive disclosure lowers the barrier for non-technical users. We argue that for applications processing sensitive user data (medical, legal, journalistic, or personal), the Web-CLI should be the default architecture, as it makes data locality an independently verifiable technical property rather than a policy promise.

We study a class of product-reference diffusion algorithms for sampling from a discrete distribution. We show that their sampling performance can be characterized using a path-based measure of data geometry that we call the interaction growth complexity (IGC). We show that a bivariate IGC kernel gives an exact representation of both the KL discretization error and a simple one-step upper bound. The simpler univariate IGC density can be used to study the effect of stepsize choices on the iteration complexity required to obtain $\epsilon$-accurate samples in KL divergence. Samplers that traverse the path with equi-spaced steps in log-squared-reliability-odds have performance that depends on the aggregate IGC mass, whereas refined choices of stepsizes have a lower complexity depending on a square-root functional. In the fine-grid limit, both of these characterizations become sharp. We also allow general product reference distributions and show that the reference law can substantially reshape the IGC profile and the resulting sampling complexity; in particular, references far from both the uniform and the data marginals can yield dimension-dependent improvements. Finally, the aggregate IGC mass admits bounds in terms of total correlation and dual total correlation, thereby connecting the pathwise geometry to classical measures of multivariate dependence.

Over the course of the last decade, neural networks have grown from an academic curiosity to moving the markets of nations. Despite this explosion in both research and deployment, relatively little is understood about how they achieve the solutions they do. This is both scientifically relevant, and pressing for society. When neural networks make decisions across self-driving, construction, law, hiring and health, there have been and will continue to be unintended consequences. However, attempting to generalize the failures of the largest and most important production systems makes for a very difficult task. Yet signs of these failures exist at all scales of neural networks, so we should be able to study a much more tractable setting. All neural networks must undergo an optimization process, called training, to be useful. To a great degree, understanding neural networks is understanding their optimization: through what process and exposure to which data did they arrive at their results. Yet our knowledge on this topic as a field is quite imprecise. In particular, a curious phenomenon called mode connectivity, the ability to connect neural networks in the loss surface, defies explanation entirely. This dissertation elucidates, explains and exploits this special structure in the loss landscape...

Automating alignment research may accelerate progress toward aligned AI, but whether it does is hard to measure. Luckily, many alignment failures, such as deception, sycophancy, and jailbreaks, are already measurable by public benchmarks. We study whether automated alignment researchers (AARs) can post-train to mitigate alignment failures by proposing training methods and data to simultaneously optimize multiple safety benchmarks, while largely preserving general capability. Across 10 alignment failures, the strongest AAR methods significantly reduce the targeted alignment failures and generalize to a held-out benchmark, multi-turn behavioral audits, and models up to 4.7x larger than the target model. As a human baseline, 28 experienced researchers receive up to eight hours to develop one-shot methods for the same benchmarks, but their methods underperform the best AAR methods. Using human ideas as the AARs' initial research direction does not improve performance, suggesting current AARs may not need guidance from experienced researchers. These results suggest that automating alignment research on well-characterized failures may be practical in the near term.

Credit risk analysis in financial institutions traditionally requires analysts to manually write SQL queries, run statistical computations, and build visualization dashboards. This is a time-consuming workflow that limits exploration to familiar segments. We introduce Oculi, a conversational platform that transforms natural language questions into comprehensive credit risk analyses, complete with data queries, statistical testing, and interactive visualizations. Oculi employs a three-layer architecture that separates reasoning (LLM-powered agent), execution (Model Context Protocol tool servers), and presentation (agentic UI), enabling analysts to discover high-risk portfolio segments. Within Oculi, a new segment discovery pipeline is proposed that combines deterministic statistical methods with LLM-guided feature selection, leveraging LLM semantic domain knowledge alongside data-driven metrics to identify meaningful, actionable portfolio segments. Evaluated on a mortgage portfolio with 200+ features, Oculi demonstrates effectiveness in discovering material risk segments previously intractable through manual exploration, reducing time-to-insight significantly while maintaining auditability and statistical rigor.

Low-rank methods can reduce the memory and computational requirements of deep neural network training in approaches such as GaLore. Randomized range finders offer an attractive alternative to singular value decompositions, particularly when the required rank is determined adaptively from a prescribed approximation tolerance. We introduce a blocked adaptive randomized range finder based on a Householder QR decomposition and an optimized hybrid CPU–GPU implementation. Numerical experiments show that it preserves orthogonality and approximation accuracy in regimes where block Gram–Schmidt without reorthogonalization becomes unstable. The blocked formulation exposes matrix–matrix operations and enables overlap of CPU panel factorization with GPU updates. On an NVIDIA GH200, the overlapped implementation reduces the runtime for the largest tested matrix from 9.91 s on the CPU to 0.407 s. The method provides a stable and efficient building block for low-rank approximation on heterogeneous systems with applications in computational science and engineering.

We study authentication over a discrete memoryless arbitrarily varying channel (AVC) in which the adversary selects the channel state causally based on past channel outputs. We prove that the authentication capacity is positive exactly when the channel is not distribution-overwritable under stochastic encoding, and not I-overwritable under deterministic encoding. In the stochastic case, whenever the authentication capacity is positive, it coincides with the no-adversary Shannon capacity. Both converses follow from a novel wait-and-overwrite attack: the adversary tracks the no-adversary posterior over the message via the posterior guessing probability, and once it concentrates past a threshold, it samples a guess and a decoy from the posterior and overwrites the channel to mimic a no-adversary transmission of the decoy. The positivity results are obtained by constructing positive-rate codes with controlled overlap between codewords, together with a martingale concentration argument that handles adaptive adversarial strategies. For stochastic encoding, the full-capacity achievability further combines a capacity-achieving channel code with an authentication tag. These characterizations separate the causal stochastic-code and causal deterministic-code settings from each other and from the oblivious-adversary setting studied by Kosut and Kliewer.

Differential privacy (DP) has traditionally been used to provide theoretical upper bounds on an algorithm's stability to changing its training data. In modern private machine learning applications, achieving strong tradeoffs between utility and theoretical privacy is challenging, and thus one may optimistically hope that existing theoretical privacy analyses are loose. Recent work on privacy auditing has adopted a dual viewpoint, instead lower bounding the true privacy of an algorithm by constructing empirical distinguishing events. The auditing literature has thus far yielded a pessimistic outlook on the looseness of theoretical privacy bounds for DP-SGD, the de facto private training method in modern ML, as nearly-matching empirical lower bounds have been achieved under various threat models [NHSBTJCT23, AC24, CBP25]. In this work, we propose the empirical privacy lower bound of an algorithm as a concrete metric to optimize for, complementary to the theoretical upper bound. We give a lightweight defense framework that generically augments optimization methods in the ML pipeline to have significantly-improved empirical privacy on standard benchmarks. Moreover, we show that our framework comes at no theoretical privacy cost when augmenting DP-SGD, unlike previously-proposed defenses against membership inference attacks. We evaluate our defense against a broad range of audit constructions, models, and datasets to demonstrate its flexibility.

Stereo reconstruction is one of the last remaining Computer Vision tasks where all state-of-the-art methods employ a heavy architectural inductive bias. Even though it has been demonstrated that the task can be solved using general-purpose methods, it is widely believed that inductive biases in stereo are strictly necessary for both high-quality results and computational efficiency. We challenge this paradigm. In this paper, we demonstrate that both state-of-the-art accuracy and superior runtime efficiency are achievable with a model completely devoid of architectural inductive biases, relying instead on a simple, end-to-end Vision Transformer. By training on massive synthetic datasets, we show that pure data-driven learning can surpass explicitly engineered geometry. This work proves that explicit inductive biases are no longer a prerequisite for stereo matching, ultimately unlocking true scaling laws for continuous improvement in 3D reconstruction.

Voice products increasingly need affective cues that are present in speech but absent from transcripts. We introduce VocalAffectBench, a public, test-only benchmark for evaluating whether AI audio models can identify expressed vocal emotion from raw audio. The benchmark contains 273 human-recorded English WAV clips from 51 speaker accounts totaling 1.95 hours across seven labels: angry, disgusted, fearful, happy, neutral, sad, and surprised, with 39 clips per class. All baselines are evaluated from audio alone, without transcripts or contextual metadata. Across six released baselines, average accuracy is 35.5%. The strongest baseline, gemini_3_5_flash, reaches 46.5% on the seven-way task, above the 14.3% random baseline but far from robust emotion recognition. A secondary valence-bucket analysis maps labels into positive, neutral, and negative classes, excluding surprised because its valence is ambiguous. Aggregate accuracy under this coarser view is 50.9%. Performance is highly uneven across classes. By recall, neutral is identified most reliably at 75.6% averaged across baselines, while surprised and fearful reach only 10.7% and 15.4%, respectively. These results show that the evaluated baselines can extract some affective signal from speech, but discrete expressed-emotion recognition remains fragile, especially for non-neutral emotions that are often most important in voice agent workflows.

Matching users to interest categories at scale is central to personalized shopping, but the task is challenging in large e-commerce platforms, where label spaces continually evolve and user-interest signals are sparse and long-tailed. Autoregressive language models are appealing because their world knowledge and semantic priors over descriptors generalize across extreme label spaces and accommodate multiple valid label assignments. Yet under teacher-forced fine-tuning, inference-time predictions become part of the conditioning context: early errors steer later outputs toward co-occurring labels, over-generating near-correlates and missing unrelated true interests. We present MERIT, a framework for user-interest propensity modeling that mitigates this exposure bias through a self-correction objective. A permutation-invariant multi-target loss over shuffled mixtures of gold and mined hard-negative labels exposes the generator to erroneous prefixes while preserving the efficiency of teacher-forced training. This training objective concentrates supervision at classification positions, yielding propensity-aligned hidden states powering a lightweight scorer for bidirectional retrieval (interests for users and users for interests). On a proprietary e-commerce dataset with 250k+ interest categories, MERIT improves global recall by at least 11.9% and average Hit@k by 6.1%. In production A/B tests, it achieves +0.26% gain in user conversion.

Hidden-state probes effectively detect LLM hallucinations, but the geometry of the signal remains poorly characterized, driving increasingly complex probe architectures. Across three 7B-scale models and three datasets in a paired-example paradigm, we find the signal overwhelmingly dominated by a single mean-shift component, and removing this direction collapses detection to chance. Shrinkage linear discriminant analysis closes about 73% of the gap between 1D and full-dimensional classifiers, so apparent architectural complexity largely reflects high-dimensional covariance estimation difficulty rather than exploitable non-linearity. A simple L2-regularized logistic regression (0.952 AUROC) bounds or outperforms twelve controlled architectural alternatives, and our multi-layer aggregation exceeds CLAP cross-layer attention probing under matched paradigm. Because the signal spans a contiguous layer band, LayerMix aggregates it to match oracle-layer performance without oracle access. Our claims characterize the geometry within the controlled paired-example paradigm. Our code is available at https://github.com/js-lee-AI/LayerMix.

Large-scale diffusion models have fueled numerous profitable downstream applications for AI-related businesses, including visual editing and content creation. Meanwhile, due to the huge amount of resource consumption (e.g., computation and high-quality data) during training, such diffusion models are deemed valuable intellectual property (IP) for tech companies like OpenAI and Google. Yet, the IP assets are vulnerable to various unauthorized uses by adversaries seeking to steal models for customized, usually commercial applications. Some existing approaches have explored IP protection for AI models; however, they mostly face structural limitations in common — using a training-time watermarking by injecting artifacts in the model, which can impose a measurable utility cost and can be weakened by post-hoc fine-tuning. To address these challenges, this work investigates IP protection (i.e., model ownership verification) for diffusion models in a realistic commercial scenario with minimal model utility loss. Specifically, the proposed method builds a framework for model ownership verification, termed “{Membership is Ownership} (MiO)”, based on a population-level hypothesis test on a private member evidence dataset. MiO verifies ownership using two criteria: model attribution through membership inference and model separation from public references. Both are tested at $p<10^{-6}$. We evaluate MiO on DDIM and Stable Diffusion models without modifying the owner model or its sampling pipeline, and report ROC-AUC and true-positive rates at fixed nominal false-positive targets. Furthermore, MiO stays stable under different post-theft fine-tuning and weight perturbation in adversarial scenarios, reflecting better robustness compared to the watermarking methods.

We propose a multi-task learning approach for multi-party dialogue intent recognition that leverages an auxiliary task that models turn-taking dynamics. Specifically, we introduce turn-transition entropy, a self-supervised target computed from the sequence of speaker transitions, which quantifies the predictability of interaction patterns. Experiments on multiple pre-trained models demonstrate that incorporating this auxiliary task improves intent recognition performance, outperforming existing approaches which ignore multi-party interaction dynamics. We find that our proposed continuous target can be learned as a single-task objective, suggesting that it is an actual signal carrying useful information.

Universities are producing AI principles and use policies faster than they are building decision pathways for unfamiliar forms of AI agency. This study develops Institutional AI Governance Stress Testing (IAGST), a prospective documentary method for locating where publicly documented governance ceases to yield an accountable response. IAGST adapts established policy stress-testing and wind-tunneling logic. Its originality lies in combining controlled capability escalation, a frozen documentary corpus, a six-dimensional governance response chain, non-compensatory decision rules, and case-level breakpoint diagnosis. The method was demonstrated using 133 substantive public documents from five Western Australian universities and 15 quality-screened scenarios, resulting in 75 university-scenario encounters. Six cases were resolved, 14 were resolved through structured discretion, and 55 were indeterminate. Governed pathways fell from 16 of 25 augmentation cases to four delegation cases and none at autonomous substitution. The dominant weakness was not the complete absence of responsible roles: all 50 authority-gap cases named a role at only a generic level but lacked sufficient decision criteria or process. The findings show how universities can move beyond policy inventories and principal statements by testing whether authority, procedures, safeguards, and reviews remain connected as AI capabilities evolve. IAGST is a reproducible diagnostic for policy learning, not a ranking or measure of implementation.

Linguistic theory has long recognized cross-linguistic syntactic regularities, leading to claims that these similar structures are processed by similar mechanisms. However, this hypothesis has been difficult to test empirically due to our lack of fine-grained, manipulable access of human processing mechanisms. In this work, we take advantage of techniques from mechanistic interpretability to study such a question in multilingual LMs. We first isolate language-internal mechanisms before attempting to transfer them cross-lingually. Across four models and three well-studied constructions (subject–verb number agreement, anaphoric pronoun gender agreement, and filler–gap object extraction) we find consistent cross-lingual mechanism transfer. We further find transfer to be graded, with more transfer between more typologically similar languages. We believe our work provides novel hypotheses about cross-linguistic syntactic structures and multilingual processing, and more broadly shows how the study of language models can help inform linguistic theory.

Data augmentation is a cornerstone of deep learning pipelines, yet existing strategies treat it as a static, model-agnostic preprocessing step, either relying on expensive dataset-specific policy search or applying transformations uniformly at random, regardless of what the model has already learned. We introduce ActiveAugment, a unified framework that treats augmentation selection as an online active learning problem. For each training minibatch, ActiveAugment generates a pool of candidate augmented views and scores each candidate using a combination of the model's predictive uncertainty and the feature discrepancy induced by the augmentation. The augmentation under which the current model is most fragile is selected per sample, and the model is then trained with a joint supervised classification and supervised contrastive objective that enforces intra-class invariance to the selected augmentations while maintaining inter-class separation. We evaluate ActiveAugment on eight benchmark datasets spanning natural and medical imaging, using CNN and transformer architectures across three training regimes (training from scratch, full fine-tuning, and linear probing), and comparing eight active selection strategies for augmentation scoring. ActiveAugment outperforms AutoAugment, RandAugment, and TrivialAugment under controlled augmentation shifts across all domains and budgets, with the most pronounced gains at low labelling budgets. On medical imaging datasets, where data is scarce and domain shift relative to natural-image pretrained models is large, ActiveAugment achieves higher test F1 than all baselines, demonstrating strong cross-domain adaptability. Our analysis reveals that the augmentation selection policy evolves meaningfully during training and that strategy choice has a direct impact on generalisation. Code is available at: https://github.com/noahvide/ActiveAugment.

A login service can receive its usual number of failed sign-ins while one source grows from 2% to 30% of them. The same pattern appears in system logs when a rare event template becomes common while the message rate stays stable. These events change which categories are active without changing how many events occur. RankShift detects such changes inside the analytical database that stores the data. It compares each window's category shares with a benign reference using a Pearson score whose terms identify the categories responsible for the change. The same query returns the score, calibrated alert, and largest increasing contributions. We evaluate RankShift on HDFS, BGL, and Thunderbird. It matches the count-vector autoencoder within 0.001 AUROC on HDFS (0.999 versus 1.000) and leads on Thunderbird (0.983 versus 0.949). In a controlled fixed-volume experiment, RankShift detects rare-category shifts that are invisible to event-count monitoring, reaching 0.787 AUROC compared with 0.771 for the autoencoder. Across all three corpora, observed false-alarm rates track the requested operating levels. RankShift requires no model training or inference service, and the autoencoders deployed state is 137x larger.

Behavioral biometric authentication (BBA) systems use deep learning models to transform biometric signals, such as eye movements, voice, keystroke/touchstroke dynamics, and gait, into identity embeddings for user authentication. While designed to encode identity, these embeddings may inadvertently reveal sensitive demographic attributes, including gender, age, and height. Consequently, an adversary with access to the authentication model can infer demographic information from biometric signals, including those of users unseen during training or enrollment. In this paper, we present the first systematic audit of demographic leakage in BBA systems, evaluating 11 models across 9 datasets spanning four biometric modalities. We further benchmark four post-hoc suppression methods-Incremental Variable Elimination (IVE), Hilbert-Schmidt Independence Criterion (HSIC), Adversarial Encoder-Decoder (AED), and Protected Attribute Suppression System (PASS) to assess their ability to mitigate demographic leakage while preserving authentication utility. Our analysis reveals substantial variation in leakage and suppressibility across modalities, model architectures, and learning objectives. While voice embeddings exhibit high leakage that can be effectively suppressed, keystroke/touchstroke embeddings exhibit lower leakage but are considerably more difficult to sanitize. These findings highlight a fundamental privacy risk in behavioral biometric authentication and provide insights into the factors governing demographic information suppressibility.

Network microaggregation is a fundamental technique in statistical disclosure control, where vertices of a graph are partitioned into clusters satisfying size constraints and admitting a center within bounded distance. We study the parameterized complexity of the unweighted Connected Network Microaggregation problem, focusing on structural parameters and natural clustering parameters such as the distance bound $d$ and cluster size gap $u-\ell$. We show that, unlike the weighted variant, the unweighted connected problem is fixed-parameter tractable when parameterized by neighborhood diversity, and hence by vertex cover. In contrast, it remains $\mathrm{W[1]}$-hard for more general structural parameters, including vertex deletion to paths, stars, and cliques. These hardness results hold even for every $d\ge 2$ and any fixed gap $u-\ell$, showing that these clustering parameters do not overcome the structural hardness. We further show that adding the cluster size bound $u$ restores tractability for structural parameters such as treewidth and cluster vertex deletion. Moreover, $u$ is essential: the problem remains $\mathrm{W[1]}$-hard when these structural parameters are considered alone. For kernelization, we prove that the problem has no polynomial kernel parameterized by vertex cover unless $\mathrm{coNP}\subseteq\mathrm{NP/poly}$, even when the distance constraint is vacuous. Adding $u$ yields a polynomial kernel for vertex cover, while kernelization remains unlikely for more general structural parameters even when combined with $u$. Finally, we show that the problem is NP-hard on graphs of bounded clique-width.

IoT-enhanced business processes are characterized by high complexity due to heterogeneous actors, varying levels of autonomy among participating systems, continuously evolving execution contexts spanning the digital and physical worlds, and continuous event streams. In such settings, process behavior partially emerges only at runtime through complex interactions involving humans, IoT devices, physical objects, software systems, agents, and services. This complexity introduces partial observability, uncertainty, and runtime dynamics that are difficult to anticipate and that challenge traditional business process management (BPM) assumptions and systems. We discuss these challenges from three perspectives, addressing 1) uncertainty representation, 2) operationalization of IoT-enhanced processes, and 3) runtime management of emergent behavior. Based on a motivating scenario and an analysis of the state of the art, we identify open research gaps and outline short-, medium-, and long-term recommendations to shape a research agenda on emergent behavior in IoT-enhanced business processes.

Automatic speech recognition is usually evaluated with word error rate (WER), although voice workflows often require exact written values. VoiceCodeBench measures whether transcripts preserve identifiers, paths, commands, and other structured tokens needed by downstream software. It contains 300 human-recorded English workplace segments (5.59 hours, 85 speakers) and 1,482 audited entities across 26 types and eight domains. Under a raw-audio-only protocol, we evaluate 19 batch and streaming systems using WER, Canonical Token/Entity Match (CTEM), and strict segment-level Task Success Rate (TSR). Across systems, WER has little rank agreement with CTEM (Spearman $\rho=-0.28$) or TSR ($\rho=-0.22$). The best CTEM and TSR are 91.8% and 68.7%. Even the strongest system therefore leaves nearly one-third of recordings with an unrecovered critical value. Symbol-, separator-, and boundary-sensitive entities account for most errors.

High-resolution 3D radar data is scarce. Commodity mmWave sensors use small antenna arrays that limit angular resolution to several degrees, and existing datasets provide only 2D range-azimuth maps or sparse point clouds rather than raw analog-to-digital converter (ADC) signals. Hardware scaling is expensive, synthetic-aperture scanning is impractical at fleet scale, and learned synthesis methods are bottlenecked by the very data shortage they aim to address. We present mmIR, an open-source differentiable frequency-modulated continuous-wave (FMCW) radar inverse renderer that fits a physics-based forward model to real captures and re-renders from dense virtual apertures to synthesize high-resolution 3D radar data. Because radar resolution is too coarse to recover geometry directly, mmIR performs LiDAR-assisted inverse rendering: using LiDAR-derived meshes as a geometric scaffold, mmIR optimizes per-vertex International Telecommunication Union (ITU) physics materials, vertex normals, and antenna beam patterns through end-to-end automatic differentiation of a phase-coherent multiple-input multiple-output (MIMO) forward model with multi-bounce propagation, polarization, and free-space diffraction. On seven outdoor and six indoor ColoRadar scenes, mmIR achieves 0.914 mean Pearson correlation on range-azimuth maps versus 0.307 for Sionna-RT. Scenes trained on a cascaded imaging radar transfer to a co-located single-chip radar without re-training (0.554 correlation), and dense virtual arrays (100x100 elements) produce single-frame 3D occupancy validated against LiDAR. Project page: https://mmwave-inverse-rendering.github.io/