Papers

In the study of Nash equilibria of finite-player games, one often seeks equilibria that are compatible with predetermined constraints, either determined by the players or by an external agent. We discuss the algebraic loci, called Nash loci, of games whose Nash equilibrium scheme intersects a fixed algebraic variety in a product of projective spaces. We determine their dimensions and multidegrees in multiprojective space, and their equations for two-player games and for small multiple-player games. The multilinear equations defining the Nash equilibrium scheme allow us to describe Nash loci in the language of Grassmannians and Plücker coordinates. Motivated by this fact, we relate Nash loci to multigraded associated varieties, which are subvarieties in products of Grassmannians that generalize the multigraded Cayley-Chow hypersurfaces of Osserman and Trager.

Instruction hierarchy is a model-side defense that assigns instructions different levels of privilege according to their sources. These levels constrain which content may direct model behavior. During agent execution, however, agent harnesses construct context for each model invocation. This construction can elevate low-level content to a higher instruction level and grant it greater model-facing privilege. We introduce instruction privilege escalation. In this attack, an attacker induces an agent to elevate low-level malicious content to a higher instruction level. The elevated content then causes the agent to execute instructions it would not follow at their original level. We evaluate this threat by using multi-agent mechanisms to achieve 13 attack objectives across six coding-agent harnesses. These objectives span confidentiality, integrity, availability, and remote code execution. With unrestricted action execution, the attacks achieve all 13 objectives on all six harnesses. Under automatic permission review, the attacks achieve all 13 objectives on all three harnesses that provide this mode. We further reproduce the vulnerability using harness-provided persistent goals and scheduled tasks. These results demonstrate the generality of instruction privilege escalation.

We ask whether large language models (LLMs) can design effective algorithms for well-specified operations research (OR) problems. We study inventory control, queueing network control, and assortment optimization, using benchmark instances from recent papers in each area. We evaluate two levels of LLM use: at level 1, the model receives one problem instance and returns a solution for that instance; at level 2, it receives only the problem class description and broad parameter ranges, and returns an algorithm that maps instance parameters to solutions. Human input is minimal: we give one untuned prompt that describes the problem, and the model has access to a Python sandbox tool with a fixed compute budget. The strongest model we test, gpt-5.6-sol, matches or outperforms the best method reported in those papers on almost all evaluated instances. This holds even at level 2, where the returned algorithm is fixed before seeing the evaluation instances. Performance also improves sharply across models released less than eight months apart, suggesting that this capability is moving quickly. Thus, for the well-specified operations problems we study, a single untuned LLM query can already produce algorithms competitive with specialized methods. These results suggest that frontier LLMs can be a serious empirical baseline for algorithm design in well-specified OR problems.

Music recommendation relies primarily on two signals: user-item interactions, which fail in the cold-start regime, and intrinsic musical content, available for any recording. We argue that a third, largely untapped signal is both richer and more principled: critical adjacency, the pairwise relation established when an expert critic explicitly links two artists in long-form prose. It encodes deliberate judgments about which artists belong together. Prior work established its internal validity, showing it recovers coherent, interpretable communities and can match collaborative filtering in user-satisfaction simulations, with no user data. What has been missing is external validation: whether this critic-sourced relation is grounded in the music itself versus sociological context. We test it against acoustic content, reframing the question as one of construct validity. Representing artists as empirical distributions over 80 low-level Essentia acoustic descriptors and modeling pairwise proximity via marginal optimal-transport (Wasserstein) distances, we evaluate how far critical adjacency is sonically recoverable under a cold-start, artist-disjoint split. Our ensemble recovers these edges at out-of-sample AUC of 0.767 (95% CI 0.761-0.775). Recoverability rises monotonically with critical consensus, reaching 0.865 on multi-source attested edges. Stratified evaluations align with sociological models of genre: tightly bounded, scene-based genres show higher recoverability than broad industry umbrella terms. Critical discourse is thus a rich source of information for recommendation, decomposing into a reproducible "sonic core" and a "sociological remainder" driven by narrative positioning, subcultural context, and canonical placement. The work offers both a scalable cold-start discovery mechanism and a sociologically grounded approach to MIR and MRS research.

Christmas tree plantations are economically relevant, yet a largely unexplored application domain in Remote Sensing (RS). Their delineation is challenging because of high planting density, short rotation cycles, visual confusion with surrounding vegetation, the availability of dense labels for one reference year only, and severe class imbalance at the landscape scale. Although Deep Learning (DL) methods have shown strong potential for vegetation mapping, existing approaches are typically designed for forests, generic plantation systems, or orchards, and do not explicitly address the structural specificity and hard-negative confusion that characterize Christmas tree plantations. In response to these challenges, this work makes three main contributions: (i) it frames Christmas tree plantation mapping as a distinct rare-target semantic segmentation problem; (ii) it introduces a Hard Negative Mining (HNM) strategy to improve discrimination against confusing background patterns; and (iii) it evaluates the proposed framework across complementary levels, including supervised testing, temporal transfer, and large-scale validation. On the 2020 test set held out, the best model, DeepLabV3 with a ResNet-34 encoder, achieves an IoU of 0.733 and an F1-score of 0.846. HNM substantially improves precision-recall behavior, increasing the area under the precision-recall curve from 0.204 to 0.913. Temporal inference further shows meaningful transferability, reaching IoU/F1 values of 0.751/0.858 on 2017/2018 and 0.691/0.817 on 2023. Large-scale validation further highlights the intrinsic difficulty of the task, as Christmas tree plantations occupied only a very small fraction of the extent of the common evaluation, corresponding to 1,498.4 ha (1.72%) in 2017/2018 and 1,782.2 ha (2.04%) in 2023 out of 87,309.4 ha in total.

Backdoor attacks are among the most effective and stealthy attacks in deep learning. Existing attacks and defenses are largely designed and evaluated under the assumption that successful backdoors exhibit high Attack Success Rates (ASRs). In this paper, we show that this assumption creates a fundamental weakness in existing defense paradigms. ASR is not an intrinsic property of a backdoor; rather, it is an attacker-controlled variable that can be deliberately reduced without eliminating the underlying backdoor behavior. We introduce a reverse-training framework that weakens the trigger-target association, producing low-ASR backdoor models while preserving clean-input performance. Through extensive evaluation across multiple datasets, diverse attack families, and multiple architectures, we show that state-of-the-art defenses fail consistently under low-ASR conditions, exposing a fundamental attacker-defender asymmetry.

Modern AI systems advance through continuous iteration: a loop of proposing evolution directions, implementing code, training, and evaluation. While the latter three stages are increasingly automated, the starting point — proposing effective evolution directions — remains a critical bottleneck that still relies heavily on senior experts. In this work, we explore whether AI can take over this role. We find that general-purpose LLMs, even the advanced GPT-5.5, offer only generic and misaligned suggestions: the required expertise is accumulated through experience rather than explicitly codified, and thus hard to inject directly. To this end, we propose Astar, a training-based approach that learns a specialized evolution-guiding model from the abundant iteration histories of industrial systems. Realizing this idea, however, raises four challenges: sparse supervision, noisy data, a vast direction space, and prohibitively expensive verification. We address them along two fronts. On the data side, we design a pipeline that turns noisy historical commits into a large, clean evolutionary corpus via pairwise sample expansion and noise filtering. On the model side, we train the model through mid-training, SFT, and RL, guiding evolution direction generation with hierarchical hints and using the reward model in RL as a fast surrogate evaluator. Astar has been deployed in Alibaba's Lazada advertising system for evolution direction proposal. Astar-8B achieves a single-proposal success rate of 0.6786 in real-execution evaluation, far exceeding human experts (0.3229) and the strongest general-purpose LLM (0.3071). More importantly, Astar closes the loop and enables fully automatic iteration: it guided 20 consecutive iterations over two weeks, improving offline Hitrate@200 by 23.6%, while an online A/B test yielded relative lifts of 4.86% in GMV and 1.82% in advertising revenue.

Inferring molecular structures from multimodal spectroscopic measurements requires integrating complementary yet highly heterogeneous signals. However, the common paradigm of directly concatenating multispectral sequences can exhibit anomalous performance degradation, primarily due to pronounced heterogeneity and the resulting multimodal imbalance across modalities. As a remedy, we propose MM-Spectrum, a sparse Mixture-of-Experts framework tailored for multimodal multispectral spectra-to-structure elucidation. To better match the information characteristics under multispectral imbalance, MM-Spectrum introduces an explicit modality-aware routing mechanism that exposes spectral identity to the router in addition to token content representations. Moreover, it incorporates shared and interaction experts, together with heterogeneous expert capacities, to extract multispectral modality-unique and cross-modal synergistic information while suppressing noise-induced interference. Across full-modality, bimodal, and missing-modality settings on molecular structural elucidation, MM-Spectrum achieves consistent and substantial improvements, supported by ablation studies and interpretability analyses.

Most single-stage 3D object detectors complete different tasks with the same extracted features. Nevertheless, it is impossible to project features into a common space that is adaptive for all the tasks. We present a novel task-aware deformable prediction (TADP) method for single-stage 3D object detection to solve this problem. Firstly, a triple feature refinement aggregation module is designed to extract three-level features adaptively. Additionally, we design the multi-scale feature aggregation block to fuse multi-scale features in a scale-aware manner. Finally, the prediction of each task is deformed with the designed plug-and-play task-aware deformation head. It can percept the emphasis and interaction of each task. We also designed three different deformation modules. The experimental results demonstrate that the proposed deformation head shows good results on other detection methods. The experimental results on the KITTI dataset demonstrate that the car mAP is 80.91%, surpassing many state-of-the-art methods on the KITTI benchmark.

Visual storytelling requires generating images that follow a narrative while preserving consistent character identities across frames. In free-form story generation, a character is fully described only when first introduced and is later referred to by a type-level mention or pronoun. Although this setting better reflects natural storytelling, later prompts may omit important identity-related semantics, making character consistency more difficult to maintain. We propose Sidecar, a plug-and-play semantic augmentation module that preserves entity-level information from the initial description and injects the missing semantics into later prompt embeddings. Sidecar requires no additional training and does not modify the architecture of the base diffusion model. Experiments on FreeStoryBench show that Sidecar consistently improves prompt-image alignment and character consistency across multiple SDXL- and FLUX-based baselines, with negligible computational overhead.

Whole-slide images (WSIs) are central to computational pathology but are prohibitively large, making patch-based processing the practical unit for foundation model inference. At scale, however, generating and handling massive numbers of patches on quickly introduces significant I/O and orchestration overhead, often dominating end-to-end performance. We present a decoupled, I/O-aware pipeline for large-scale WSI embedding extraction that decomposes the workflow into three stages: (1) patch generation and staging, (2) embarrassingly parallel embedding inference, and (3) sharded vector database ingestion. This design isolates data movement from compute, enabling efficient patch delivery, scalable multi-node inference with minimal communication. The resulting system produces a distributed vector database where embeddings are persistently coupled with rich metadata (e.g., patient, slide, and patch attributes), enabling efficient filtering, retrieval, and downstream reuse. This representation database is compact and reusable for tasks such as retrieval, classification, and few-shot learning, particularly benefiting low-resource environments. We show that decoupling I/O, computation, and ingestion enables high-throughput WSI embedding extraction at scale. By characterizing the scaling envelope, we demonstrate that storage dominates beyond moderate concurrency, reframing WSI embedding extraction as a data-centric systems problem rather than a purely compute-bound workload.

We propose a novel method that combines a multilevel decomposition with the framework of Interacting Particle Systems to compute the probability that given quantities of interest take values above or below a certain pre-specified value. Through the application of a sequential sampling scheme, the algorithm is able to achieve convergence rates faster than those achieved by the classical Multilevel Monte Carlo algorithm, and competes with the current state of the art techniques, while also being dimension independent. Furthermore, the sample points generated by the algorithm form a sequence which concentrates near the critical value of the quantity of interest. Our results are rigorously established and later verified through numerical experiments.

The marine science community increasingly relies on Marine Autonomous Vehicles (MAVs) to collect the critical environmental data required to understand global ocean systems. However, as these operations scale, manually routing and planning large autonomous fleets becomes exponentially complex and time-consuming. To address this, we propose a mixed-integer linear programming (MILP) model designed to automate and optimise MAV deployment schedules. The model accounts for strict operational constraints, including battery capacities and time windows for data collection, while aiming to maximise total data collection and minimise both the number of deployed vehicles and their energy consumption. A key novelty of this framework is integrating conventional ship itineraries, allowing MAVs to support vessels with mid-mission battery swapping or accelerated transit between waypoints. Computational experiments demonstrate that the model is highly scalable, solving routing problems for fleets of dozens of MAVs in seconds, and scaling to hundreds of vehicles in only a few minutes. Beyond operational scheduling, the framework serves as a robust simulation tool for evaluating 'what-if' scenarios and analysing the impact of varying parameters on deployment strategies. Finally, the solution generates a suite of visualisations designed to enhance explainability and support strategic decision-making for stakeholders.

We present results on the approximate computation of stable invariants for filtrations of finite metric spaces in the context of persistent homology. We establish novel approximation algorithms in the setting of $n$-point metric spaces where the growth of the doubling dimension is in $o(\log n)$ and the diameter is bounded. In the $1$-parameter case, by revisiting known techniques (greedy permutations) in a new way, we derive the first linear-time algorithms for the problem of computing additive $\varepsilon$-approximations of any stable barcode. By deriving bounds on the convergence rate and the approximation quality of uniform samples, we extend the approach to selected multiparameter filtrations. We show that for normalized measure bifiltrations, including the multicover and subdivision-Rips bifiltration, any stable invariant can be probabilistically approximated in time constant in $n$. The constants in the running times of our algorithms depend on the doubling dimension, the diameter and the success probability. We further study the problem through the lens of fine-grained complexity and show that computing the rank of a matrix reduces to that of approximating the barcode of the Vietoris–Rips or Čech filtration. We present two variants of the reduction, one for sufficiently good additive approximations and the other for any constant factor multiplicative approximations.

Although Large language models (LLMs) mediate access to knowledge and computational assistance, their capabilities should benefit vulnerable groups in the same way. However, it is unclear whether existing AI systems are inclusive enough for blind and deafblind users to access the same functionality through Braille, whose indicators, contractions, and digital representations introduce distinct requirements for model comprehension. To this end, we introduce BrailleBench, a benchmark for evaluating LLMs in Braille comprehension from different Criteria. BrailleBench aligns 5,570 instances from five datasets, including mathematics, commonsense, and multi-hop question answering across English and Braille Grades 1 and 2. Different configurations are designed to understand whether the systems can comprehend Braille-authored content, express answers in Braille, and complete end-to-end Braille interaction. To ensure the quality and prevent evaluation bias, the benchmark is built through a deterministic, expert-reviewed pipeline via a self-created Braille Toolkit without using any data instances generated by LLMs. We evaluate six representative LLMs from various aspects. The results reveal a persistent gap between print-English capability and Braille accessibility. Braille understanding and expression are asymmetric, where Grade 2 is especially fragile on the input side compared to Grade 1, and fully Braille requests further reduce performance. The experimental observations provide valuable guidance for the development of future Braille AI systems. All related resources in BrailleBench are publicly available for future research.

Efficiently improving autonomous agents across diverse tasks is central to accelerating recursive self-improvement (RSI) in agentic AI, with prompt optimization emerging as a promising approach capable of delivering performance gains comparable to those achieved by fine-tuning model weights, while reducing computational costs in both optimization and serving. However, recent developments increasingly favor unnecessarily complex prompt optimizers. We introduce Naive Prompt Optimization (NPO), a lightweight single-lineage method that iteratively revises prompts using a teacher model with rollout feedback. NPO achieves comparable or better performance than GEPA with fewer rollouts, and its advantage increases with stronger teacher models, suggesting that stronger teacher reasoning can partially substitute for optimizer-side search complexity. In interactive games, NPO remains broadly competitive with GEPA, while GRPO performs better on some tasks less amenable to prompt optimization. We also show that NPO-optimized prompts elicit similar performance improvements when applied verbatim to other student models, especially across models within the same family. Overall, our preliminary results show that simple, linear prompt optimization can rival substantially more sophisticated and complex search procedures.

Latent chain-of-thought models move intermediate reasoning from emitted text into continuous states, improving compactness but hiding the causal object. We introduce SCIT, the Suffix Cache Interchange Test, a causal protocol that constructs exact source-recipient counterfactuals, patches declared cache segments, and identifies which transformer object carries the counterfactual computation. SCIT combines sufficiency tests with K/V component splits, hidden-state controls, semantic source controls, decoded validation, and matched corruption. On CODI-GPT2 and a Sim-CoT-style GPT-2 reproduction, counterfactual arithmetic transfers primarily through value-cache suffix trajectories rather than hidden states, keys, reusable answer slots, or single-token triggers. Complete sufficiency-and-necessity evidence for the late-value-suffix mechanism holds for the main CODI-GPT2 checkpoint; the Sim-CoT-style checkpoint shows the same sufficiency and decoded-control pattern but insufficient matched-corruption evidence for a necessity call. Beyond these local arithmetic cells, SCIT reveals carrier-regime shifts: arithmetic-like GPT-2/1B cells preserve latent-tail value/KV transfer, whereas competent 8B and repaired non-arithmetic cells route through prompt-prefix or full-cache K/V; boundary cells receive no mechanism call. SCIT therefore contributes a cache-level diagnostic, a checkpoint-specific GPT-2 arithmetic mechanism, and a competence-gated carrier map rather than a universal latent-tail claim.

LLM agents increasingly rely on generated interaction data to learn how to interact with external environments. Agentic data generation must maintain consistency among environments, tasks, interactions, and success signals while producing experience that is useful rather than merely abundant. Existing work spans many agent domains, but domain-centered organization and heterogeneous evaluation often obscure common generation mechanisms and conflate candidate construction with verification and selection. This work develops a two-level framework for the field. First, we represent agentic data as a common factorized object $(E,q,\tau,v)$, comprising an environment specification, task signal, interaction realization, and optional verifier. We organize generation paradigms by their primary anchor and dependency structure. Second, we formulate generation as constrained distribution design through the Accuracy-Complexity-divErsity (ACE) lens. Accuracy establishes the feasible support of grounded and internally consistent data. Within this support, Complexity places learning mass relative to the capability of a declared learner and execution configuration, while divErsity controls coverage and redundancy of data. Using this framework, we explore how prior work verifies generated experience, constructs and calibrates difficulty, and expands behavioral coverage. The literature reveals a shift toward execution-grounded accuracy, learner-relative complexity, and diversity beyond surface variation or dataset size. We further discuss broader directions and emerging trends in agentic data generation through the ACE lens, including their implications for scaling, data sources, training regimes and adaptive learning. Overall, the central challenge is not simply to generate more data, but to continually allocate valid, informative, and non-redundant experience as agents and environments evolve.

World Action Models (WAMs) augment robot policies by predicting how task-relevant scene states may evolve under interaction. Recent WAMs increasingly perform such prediction in latent representation spaces, avoiding full appearance-level generation while preserving control-relevant information. Yet latent transitions are commonly realized with Transformer-based predictors whose inductive structure is centered on token interaction rather than temporal evolution. We study transition realization as an architectural choice distinct from predictive representation and prediction-policy coupling. We introduce the Latent Evolution Operator Network (LEON), which models latent evolution in a learned observable space through context-modulated operator-based propagation and additive forcing. Grounded in the controlled Koopman generator view of evolution, LEON organizes context-dependent transition variation around a shared evolution-operator structure while retaining a complementary path for additive change. Controlled dynamical systems verify the resulting evolution-specific inductive bias and the complementary roles of operator propagation and forcing. Across two WAM formulations that integrate latent prediction into the policy differently, LEON improves closed-loop performance and robustness while remaining effective under full transition replacement. These results establish transition realization as a consequential architectural choice in latent WAMs.

Operator learning in scientific machine learning is concerned with approximation of maps between infinite-dimensional function spaces; such maps frequently arise as the solution operators of partial differential equations (PDEs). Neural operators have demonstrated broad empirical success at approximating such maps from data. However, most existing neural operator architectures enforce boundary conditions indirectly through training from data even though the boundary condition is often known exactly. Furthermore, existing modifications and approaches that do enforce boundary conditions explicitly suffer from impractical restrictions, including boundary smoothness, uniform grids, and separable, box-like domains. In this work, we propose an architecture which, independently of training, satisfies homogeneous Dirichlet boundary conditions, whilst simultaneously retaining the expressivity of existing kernel-integral neural operator architectures. This is achieved by enforcing the property that the output of each layer is contained in the span of a subset of the homogeneous Dirichlet eigenfunctions of the Laplacian on the output domain. The method requires only that the output domain be bounded with Lipschitz boundary and places no restriction on the choice of discretization, making it applicable to arbitrary mesh data and general geometries. We prove universal approximation for the resulting architecture; furthermore the approach we adopt in the analysis proves universality for a broad class of kernel-integral neural operators thereby uniting existing theory for a variety of operator learning methods. We validate the proposed method on maps defined by the coefficient to solution map in 2D PDEs: Darcy flow on a square domain and the Helmholtz equation on a circular domain. Comparisons are made with alternative methods.

One approach in mechanistic interpretability explains model behavior through circuits: the components and connections that carry it. Frozen discovery often returns hundreds of edges, making them hard to inspect, compare, or verify exhaustively. We introduce Circuit Condensation, which post-trains models to concentrate behaviors into smaller causal graphs. Each round prunes low-attribution edges and trains a low-rank adapter to match the original through what remains. It keeps the cut only if task accuracy and held-out perplexity remain within tolerance. Across four behaviors and eight models, condensed circuits are smaller than the strongest published frozen-weight baseline in 30 of 32 settings, by 8.1x on average and up to 316x. Repeating the search without weight updates produces larger circuits in 29 of 32 settings, showing that weight updates drive the reduction rather than search alone. For 19 small circuits, exhaustive subset tests show that 11 are exactly minimal and identify removable edges in the rest. Pair ablations reveal dependencies that single-edge tests miss. On indirect object identification, condensation isolates 24 heads, including 17 with documented roles, whereas a matched frozen circuit needs 61 heads, 36 without documented roles. The result is a sufficient subcircuit of the published mechanism rather than a reconstruction of it. The resulting circuit tracks the original model's next-token distribution and, at matched edge count, predicts its errors better than a frozen circuit in 10 of 11 evaluable settings.

In this paper, we establish a structural compatibility between the Kronecker product of bipartite graphs that admit polarity and their polarity quotients, and provide a sharp upper bound on the diameter of these graphs. We use these properties to construct new families of graphs, all of which have orders that asymptotically approach the Moore bound. We show that the bipartite compatibility graphs have a natural polarity, and that the corresponding polarity quotients comprise a new family of graphs of any even diameter $2k$ with degree $(q+1)^k$ for any prime power $q$, much smaller than those of other known families of that diameter and field order $q$. These families generalize the Erdős-Rényi-Brown polarity graphs. Kronecker products of these polarity quotients give another new family of graphs of any even diameter for every pair of prime powers $q,r$. Certain generalized polygons are known to admit polarity with polarity quotients approaching the Moore bound asymptotically. Kronecker products of these polarity quotients give another new family of graphs of diameters $2$, $3$ and $5$, including a diameter-$3$ degree-$18$ graph of order larger than any previously known for that degree and diameter.

An LLM call in a semantic data processing system is expensive enough to dominate query cost, yet slow enough to hide a CPU-side learner's update behind its round-trip. In production, LLM compute accounts for $80-90\%$ of query cost, and each call costs $10^5-10^7\times$ a relational predicate. The latency window inverts a design constraint of classical adaptive query processing, where online learners had to stay lightweight to avoid dominating the predicates they optimize. At LLM latency, per-call gradient steps and per-batch threshold solves fit inside the round-trip. We develop compositional online learning at the LLM call boundary: a framework for combining online-learning components in semantic data processing systems. Each component makes execution-time decisions and refines its learned artifacts online. The design space spans two axes, decision granularity and learner update cadence, and the components share a single learning pattern that hides each trainer step inside the next LLM round-trip. A production case study in Cortex AISQL composes three components: a memoization layer, an online per-call filter-ordering learner, and an online per-batch cascade-routing learner. A conditional cost decomposition assigns each learning component to a distinct factor of per-row LLM cost. Under independence, the two learning components compose multiplicatively to an $11.4\times$ upper bound on a representative conjunction-filter workload. Self-selection at the cascade boundary, sample-budget shrinkage, and selectivity-estimation drift reduce it to a realistic figure near $8\times$.

Modern communication systems impose strict demands on data rate, reliability, and power efficiency. In this context, emerging communication paradigms such as identification via channels have become an important topic in post-Shannon information theory, offering the potential for substantially higher identification rates than in conventional channel coding.Deterministic identification is particularly interesting for specialized communication scenarios because it provides a balance between implementation complexity and the communication gains due to higher identification rates. It is therefore a promising communication scheme for future communication systems, including molecular communication systems. Additive Gaussian channels, particularly the additive white Gaussian channel, are among the most important channel models for analyzing the performance of communication systems in information and communication theory. This importance stems from both their mathematical tractability and their ubiquitous appearance in practical applications. To date the deterministic identification capacity for additive Gaussian channels remains unknown even for the simplest case of the additive white Gaussian channel. In this paper, we establish tight bounds on the deterministic identification capacity of additive Gaussian channels by introducing a new perspective on deterministic identification. To this end, we apply results from lattice theory to obtain new capacity results.

Computationally demanding and opaque deep learning models can be better understood and optimized by analyzing how they transform data. While deep transformers have been widely studied in computer vision and natural language processing, their application in tabular data remains relatively underexplored. This paper presents one of the first applications of an importance-scoring metric to interpret multi-head transformer models in learning from tabular data. Experiments conducted on 40 diverse tabular datasets demonstrate robustness to head drops based on the proposed head importance score. In 72.5% of experimental examples, the model remains most resilient to performance drops when heads with the lowest importance scores are gradually removed. In contrast, removing the most important attention head first results in the greatest reduction in classification performance. A closer look at individual head importance scores across six attention layers reveals that important heads are scattered across layers, with no consistent layer-specific trends. In contrast to the image and language domains, the importance of individual attention heads varies considerably across tabular datasets with different schemas and feature spaces. The proposed importance score can improve efficiency and redundancy within transformer architectures. We make the source code for measuring the importance of individual attention heads publicly available.

Prenatal ultrasound examination is crucial for assessing fetal limb development and detecting congenital anomalies. However, existing artificial intelligence models often overlook fetal lethal skeletal dysplasias due to the lack of high-quality annotated data and a unified framework for multiple long bones. Moreover, generic segmentation models struggle with the inherent noise and semantic gaps in ultrasound images. To address these challenges, we construct the Fetal Limb Bones (FLB) dataset, comprising high-quality annotations for the humerus, femur, tibia-fibula, and radius-ulna. Furthermore, we propose UniFLM (United Segmentation and Measurement on Fetal Limb Ultrasonic Image), a unified framework for automatic cross-plane segmentation and measurement. UniFLM incorporates a Semantic Alignment Skip Connection (SASC) module to bridge the semantic gap between encoder and decoder features, and a Positive Sampling (PoSamp) strategy to filter noise and extract essential semantic information. Finally, a Point Regression Mapping (PRM) module is introduced to learn clinician annotation patterns for precise bone length measurement. Extensive experiments conducted on the FLB dataset and the public FetalP5 benchmark demonstrate that UniFLM achieves competitive performance with consistent generalization across four bone categories and external multi-center data, supported by comprehensive statistical validation including Bland-Altman agreement analysis and bootstrap confidence intervals. The source code is publicly available at https://github.com/chosen1203/UniFLM.

Rural Bangladeshi outpatient clinics keep no patient records, prescriptions are handwritten, and physicians have under a minute per patient, so they easily miss a known adverse drug reaction (ADR) or drug-drug interaction (DDI). We built and evaluated an offline Android application that photographs a handwritten prescription, detects and reads each medicine line, resolves brand names to active ingredients, and retrieves, but never predicts, documented interactions and the patient's recorded reactions. This quantitative technical-feasibility study, with qualitative error analysis, involved no patients or clinicians. Reference data combine two Bangladeshi drug registries (27,880 brands) with 190,421 DDI pairs. A YOLOv8n line detector reached mAP@0.5 = 0.687 on held-out prescriptions but recalled only 60.6% of lines at the deployed cutoff. On-device ML Kit read 11.8% of 780 benchmark handwritten words exactly. We trained a CRNN-CTC reader on public handwriting data, decoded it against the brand lexicon, and fine-tuned it on 660 author-labelled prescription crops. On benchmark words, the reader accepted the correct ingredient for 41.5% and a wrong one for 4.2%, versus 21.0% and 5.3% for ML Kit at its preset cutoff (McNemar p<10^-20). On scorable lines from held-out real prescriptions, the reader accepted the correct ingredient for 36.0% [26.8, 46.3] and a wrong one for 2.2% [0.6, 7.8]. In 62 simulated runs on a mid-range phone, median time per patient was 26-31 s and 59 of 62 runs finished within 60 s, but 62% of medicine lines still needed a manual check. A cross-visit medication history added after the evaluation passed seven automated tests and one two-visit functional test but was not evaluated. The pipeline is feasible within the clinic workflow; reading handwriting, not retrieval, is the bottleneck. Nothing here demonstrates a clinical benefit.

Companies that deploy AI agents and make them available to others are creating the sociotechnical circumstances under which this technology integrates into existing social and economic structures. AI-deploying companies are institutional actors that actively shape society's capacity to withstand and govern the consequences of agentic AI. In view of these societal impacts, companies can build societal resilience by designing and promoting safer implementations of AI agents. To operationalize this goal, this paper adapts the indicator-based Societal Capacity Assessment Framework (SCAF) to measure how a company's deployment decisions contribute to societal resilience, inverting its original measurement of societal resilience as a backdrop for deployment decisions (Gandhi et al., 2025). Our procedure has two steps: a conceptual step in which we design a suite of indicators that define what SCAF's vulnerability, coping, and adaptive capacities mean when assessing a company's agentic AI deployment decisions; and a measurement step in which we apply this framework in a structured assessment of public-facing Microsoft documents.

Large language model (LLM) agents increasingly operate over untrusted webpages, documents, tools, and persistent states while exercising authority over security-sensitive resources. Existing defenses typically protect either planning or individual tool interactions, but persistent agents face a broader threat: attacker-controlled data can alter control flow, enter security-sensitive tool arguments, or compromise later queries. We present SPA, a plan-first architecture that secures planning, execution, and cross-query state reuse. SPA invokes the planner once per query to generate a complete executable plan in a declarative domain-specific language, then applies dual-lattice information-flow control to track confidentiality and integrity across explicit data flows and control dependencies. To support persistence without re-exposing untrusted payloads to the planner, SPA stores execution results as labeled artifacts and reveals only semantic metadata during later planning. We evaluate SPA on AgentDojo and AgentDojo-MQ, which is our multi-query extension for measuring secure state reuse and delayed attacks. Under the 'tool_knowledge' attack, SPA with information-flow control reduces attack success to zero on AgentDojo and 0.2% on AgentDojo-MQ. Our results show that plan-first execution combined with label-preserving persistence can substantially strengthen persistent LLM agents, while revealing an important security-utility tradeoff introduced by strict integrity enforcement.

Human Activity Recognition (HAR) using inertial measurement units (IMUs) enables a wide range of applications, yet the field still lacks a unified model that can generalize across diverse subjects, devices, and activities. Training such a model is difficult due to two key challenges: sensing heterogeneity – differences in sampling rates, channel configurations, and sensor placements – and poor generalization to unseen activities and label vocabularies. We introduce HALO (Heterogeneity-Aware Language-aligned Open-set model), a domain-specific IMU foundation model that addresses both challenges through a two-stage training framework. Stage 1 pretrains the IMU encoder with heterogeneity-aware self-supervised learning, including adaptive-pooling tokenization, channel-independent feature extraction, and contextualized sensor conditioning that injects natural-language sensor descriptions into each channel embedding. Stage 2 aligns this IMU encoder with text embeddings via synonym-aware soft contrastive learning, enabling open-set recognition via cosine-similarity retrieval without per-dataset classifiers. Trained on 10 public HAR datasets and evaluated on 7 held-out datasets, HALO outperforms five state-of-the-art baselines on all 8 aggregate metrics, and still leads on 3 of 4 settings under baseline-matched inputs. Despite using only ~35M trainable parameters – 10x fewer than the latest foundation model MOMENT (341.2M) – HALO improves zero-shot open-set accuracy, measured over all 87 training labels, by 13.7 percentage points. On two further datasets with severe distribution shift, every model including HALO collapses zero-shot. A video demonstration of HALO's performance in real world is available at https://youtu.be/rooVKragtFU