Papers

This paper investigates the $c$-differential uniformity of power functions over finite fields, an important class of cryptographic functions with favorable differential properties. Specifically, for finite fields $\mathbb{F}_q$ satisfying $q-1=en$ with $e\ge 3$ and $e\mid n$, we prove that there exists $c\in\mathbb{F}_q\setminus\{0,1,\epsilon,\dots,\epsilon^{e-1}\}$, where $\epsilon$ is an $e$-th primitive root of unity in $\mathbb{F}_q^*$, the constructed power functions $f(x)=x^{ln+1}$ with $1\le l\le e-1$ and $\gcd(l,e)=1$ satisfy the upper bound $\Delta(f,c)\le e$, provided that certain cyclotomic conditions hold. We show that our conditions are mild; namely, such power functions can be constructed over infinitely many extension fields $\mathbb{F}_q$ of $\mathbb{F}_p$ for any given $e\ge 3$ and prime $p$ with $p\nmid e$. Furthermore, based on the Weil bound for multiplicative character sums, we prove that the obtained upper bound is tight for sufficiently large $q$, demonstrating the optimality of our results. We also analyze the special case $c=-1$ and derive simplified explicit conditions. In particular, we explicitly characterize the admissible parameters for the case $e=3$ and present concrete function examples for practical validation.

Generative world-action models (WAMs) jointly generate future video and vehicle actions, while their action branches remain primarily optimized by expert imitation. Yet imitation provides no explicit closed-loop geometric verdict for generated trajectories, making verification important during both training and deployment. Closed-loop evaluators can check collision and drivable-area violations, but require privileged scene state unavailable at deployment. Existing approaches often close this gap by learning a verifier from sensor features. For these geometric checks, the rule itself is explicit. For example, collision is determined by whether the rolled-out ego footprint overlaps occupied vehicle space. What is unavailable at deployment is the scene state needed to apply the rule. We introduce DriveReferee, which uses a learned geometry readout to predict the scene representation from camera observations and executes the geometric safety rule directly rather than learning it. The resulting analytic referee evaluates collision and drivable-area safety from a scene state and candidate trajectory. During training, it scores self-sampled trajectories on ground-truth state and distills the resulting preferences into the WAM policy. At deployment, the same referee evaluates generated trajectories on this predicted state and selects a safer alternative when needed. The analytic referee requires no verdict-specific training, and its decisions follow an explicit geometric rule. Under matched candidates and inference budgets, it matches or outperforms all learned-verifier and heuristic baselines. Given the same predicted state and trajectory, learning the verdict provides no measurable downstream gain despite requiring tens of thousands of evaluator-labeled training examples. On the full NAVSIM navtest, DriveReferee reaches 92.02 PDMS with single-camera visual input and no external training data.

Purpose: A vertebra at the lumbosacral junction is named by counting caudally from C2 on whole-spine imaging, but a lumbar case is planned on lumbar-only imaging (T12 to S1), without C2. Abdominopelvic CT holds that span plus the lowest ribs and pelvis. Where a lumbosacral transitional vertebra (LSTV) alters the count, the local anatomy is ambiguous: four rib-free vertebrae may be an L1 with a lumbar rib or an L5 assimilated to the sacrum, and six may be a sixth lumbar vertebra, a T12 with aplastic ribs, or a lumbarized S1. CTSpinoPelvic1K asks whether local morphology resolves it without the count. CTSpine1K's vertebrae and CTPelvic1K's pelvis covered these patients but were never joined; this release joins them on one series and adds the bones neither had. It provides 802 CT records with per-level ribs and femora, levels anchored on the lowest rib-bearing vertebra and S1, and classes for L6, T13, a separate S1 and lumbar ribs, so anomalies are recorded as such. Acquisition and Validation Methods: Records pair CTSpine1K and CTPelvic1K labels on each patient's bone-richest series under a VerSe-native scheme. Validation covered geometric invariants (802/802 pass), rib-vertebra incidence across 5,749 ribs (0.035% offset), and spinopelvic measures matching published values. Data Format and Usage Notes: NIfTI image/label pairs with patient-grouped LSTV-stratified five-fold splits and a loader; archived at https://doi.org/10.5281/zenodo.22139642. Potential Applications: Classifying a vertebra from local features; updating cadaveric morphometry; spinopelvic assessment; opportunistic screening; and, absent a public preoperative lumbar cohort, surgical planning research (377 records prone). Limitations: thoracic ground truth is field-of-view limited; postural angles supine; no held-out test set; ribs are triaged-review pseudolabels; Castellvi grades two-reader consensus on 33 records.

A (coarse) correlated equilibrium (CE) is information-value-free (IVF) if a player can match the payoff obtained from recommendations by committing to a fixed action. Motivated by the problem of regulating algorithmic collusion, this refinement was introduced by Hartline, Wang, and Zhang [EC'26], who showed that it can be computed in polynomial time in explicitly represented normal-form game. In this paper, we examine the complexity of IVF(C)CEs in succinct games, which model more realistic strategic interactions that feature either many players or exponentially many pure strategies. We first show that computing an information-value-free CE is PPAD-complete in many-player polymatrix games or two-player Bayesian games, even when the approximation is a constant. We also prove an unconditional exponential query lower bound. Our results establish that IVFCEs are intractable, even in the centralized model, and rule out the existence of any efficient learning dynamics. This significantly strengthens the impossibility result of Hartline, Wang, and Zhang, which concerns a particular class of learning algorithms, and furnishes strong computational critiques of recent regulation on algorithmic collusion. To sidestep these hardness results, we examine the complexity of information-value-free CCE. Certain no-regret algorithms—such as regret matching or FTRL—provide a fully polynomial-time approximation scheme (FPTAS) for this problem. The complexity when the approximation is exponentially small turns out to be nuanced. On the one hand, leveraging no-regret dynamics, we establish membership in $\text{CLS} = \text{PPAD} \cap \text{PLS}$. On the other hand, we show that it is at least as hard as the P-matrix linear complementarity problem, and hence as hard as simple stochastic games. This shows that even IVFCCEs are unlikely to admit a polynomial-time algorithm barring a major breakthrough.

To meet the increasing demands for high data rates and large capacity, next generation wireless communication systems require transceivers equipped with a large number of antennas. Massive multiple-input multiple-output (MIMO) with metasurface antennas has emerged as a promising solution. In this paper, we investigate the channel estimation problem for the emerging reconfigurable intelligent metasurface antenna (RIMSA) array systems. Specifically, we develop a two-stage refinement (TSR) channel estimation method based on the compressed sensing (CS) principle. In the first stage, we exploit the antenna structure of RIMSA to receive pilots by setting identical phase response vectors across all RIMSAs. In this manner, the coherence of the measurement matrix under the CS framework is reduced and the channel estimation performance is improved. However, this special design introduces channel direction-of-arrival (DoA) estimation ambiguity and yields an ambiguous candidate DoA set. In the second stage, we optimize the phase responses of the metamaterial elements to resolve the ambiguity and accurately estimate the DoAs and channel coefficients. Overall, the estimation accuracy is improved in the first stage at the cost of ambiguity, and this ambiguity is eliminated in the second stage. We illustrate the performance advantages of the TSR method by presenting the numerical results and comparing it with the existing methods.

Long-context LLM training on long-tailed corpora faces a central communication–balance tradeoff. Such sequence-length heterogeneity makes any single sequence-parallelism (SP) degree a poor fit for the workload: a small degree leaves the few long sequences badly imbalanced, while a large degree forces the many short sequences that dominate the workload to pay excessive communication. Existing dynamic-SP systems mix SP degrees within a batch, but to run several groups at once they partition the GPUs into disjoint groups, which reintroduces imbalance across groups and forces costly micro-batch workarounds. We present NSP, a sequence-parallel training system that resolves this tradeoff by nesting differently sized SP groups on shared GPUs within a single training iteration. This lets long sequences use larger SP groups while keeping short sequences on smaller ones, so communication is incurred only where needed and load is balanced per GPU rather than per group. NSP realizes this idea with a tree-structured routing planner that assigns sequences under memory constraints and an executor that exploits the resulting hierarchy through inter-level phase streaming and tree-level recomputation. NSP supports common SP backends and requires no model changes. We evaluate NSP on Qwen3-MoE workloads with up to 384K-token contexts across multiple long-tail datasets on an internal production GPU cluster. Across these settings, NSP consistently improves end-to-end training throughput, outperforming Static SP by up to 1.48x and FlexSP by up to 1.16x.

Natural-language service requests can require a language-model decision before execution starts, consuming part of the request's latency budget. We integrate Jev's decision-oriented application programming interface (API) into edge service orchestration to reduce this overhead while retaining service completion. The integration extracts four to eight bounded intent fields and applies a shared validator, admission policy, and scheduler, accounting for decision waiting throughout the request timeline. We compare Jev, two self-hosted decision models, and three hosted large language models (LLMs) on 8,280 verified requests and on a live admission path with modeled execution and a real optical character recognition service. Across 33 test conditions, Jev reduces median decision latency by 22.7-64.5% relative to the fastest LLM. This latency barely moves with input size, contract width, or catalog size. On four-field contracts, Jev's API fees per correct decision are 59.7-80.9% lower at a cost of a few exact-match points, while wide contracts mark the limit of the substitution. Receiving the service catalog with each request, Jev names unseen services as accurately as known ones. On the live admission path, Jev keeps 0.91-0.95 of requests exact and on time at loads where the LLMs fall below 0.1. Since caching repeated descriptions gives the interpreters nearly the same latency, Jev's gain lies in fresh decisions. These results support decision-model substitution for latency-bound admission on bounded contracts.

Diffusion models have demonstrated strong power in generative modeling tasks across multiple domains, exhibiting a remarkable capability of learning complex distributions from samples. In this paper, we leverage such capability to design an efficient universal diffusion-based solver for parameterized black-box optimizations (BBO), where the optimizer has only black-box access to queries of the objective function at the learning stage, yet is able to reduce the additional computational cost at the inference stage for each BBO instance while also capturing the potential multi-modal landscape of non-convex objectives. To cast our formulation as a compatible generative modeling task, we introduce the notion of minimization policy as a new solution concept, which defines a sampling distribution over the solutions that should concentrate around the minimizer set for each BBO instance. We then propose Diffusion-based Iterative Minimization Policy Learning (D-IMPL), a practical generative-model-based solver for solving parameterized BBOs that employs diffusion models to learn a minimization policy, whose density is proportional to the exponential of the negated objective values, thereby amortizing the computational costs across different BBO instances. Furthermore, we demonstrate the performance of our D-IMPL algorithm by establishing a sample complexity guarantee showing that a $\delta$-approximate minimization policy can be effectively learned within $O(\log(1/\delta))$ iterations, and by extensive empirical evaluations over a range of constrained and unconstrained BBO tasks.

Manual attendance methods, such as paper or register-based systems, take a lot of time, can lead to errors, and are easy to falsify. Face recognition is more reliable, but it frequently struggles in classrooms because lighting and other conditions can vary. Face recognition datasets are designed for regulated environments and do not capture the actual challenges found in classrooms. To address this, a new face detection and recognition dataset, the Visage Face dataset, comprising 16,234 face samples, is proposed for the task of face detection and recognition. The photos are taken from different angles and under varying lighting conditions, with students showing a range of expressions, and some faces partly covered to reflect real-life situations. A YOLO-based system is used to detect faces and tested seven advanced face recognition models with thirteen configurations: LVFace, QCFace, FaceLiVTv2, TopoFR, EdgeFace, TransFace, and GhostFaceNets. Of these, FaceLiVTv2-M performed best, with 99.75% Top-1/Top-5 accuracy and an inference time of 6.459 ms. These results show that the Visage Face Dataset is a realistic and challenging benchmark for face recognition in classroom attendance.

On a seven-compound drug-response model, warm-start quantum approximate optimization (QAOA) on IonQ Forte-1 returned valid assignments more often than random bitstrings, but this alone did not show effective optimization. Ideal QAOA raised optimum probability above uniform feasible sampling in only four of twelve reference circuits. Hardware often fell below its own noiseless circuits, while greedy search solved all hardware models within 200 objective evaluations. Expanded simulations showed a gain over feasible sampling in 28 of 35 CAMA-1 panels and none of four 647-V panels. Annealing solved all these panels in every seed. A Grover mixer preserved feasibility and improved optimum probability over feasible sampling in all ten tested models. We analyzed 25 completed tasks containing 5,300 shots from 18 circuits and 14 instances. The encodings use 6-35 qubits and at most 4,900 feasible assignments, which we enumerated to establish exact optima. Noiseless references now cover both the original six circuits and six wider circuits. At 35 qubits, with 4,900 feasible assignments, ideal feasibility was 35.85%, compared with 7 of 200 valid hardware outputs. Its ideal optimum probability was below both sampling controls. The circuits sample assignments in a model built from measured single-agent and pairwise responses.

Understanding the performance of large-scale recommender systems remains an underexplored challenge, especially for content creators and model developers. The raw engagement signals available to them, such as views and clicks, conflate content quality, model behavior, presentation bias, and audience reach, making it hard to attribute outcomes to the right cause. In this work, we present a general evaluation framework that enhances observability across multiple recommender systems at Netflix and demonstrate its effectiveness through several production deployments. The framework treats recommender-system observability as a counterfactual measurement problem: estimating what the recommender would have done, and what engagement would have followed, in the absence of a specific content item or model decision. We articulate three stakeholder-centered observability principles for content creators and model developers, and propose measurement methodologies covering bias reduction, relativity, and incrementality, applicable to both single-stage and cascading recommender systems and serving both audiences from a single measurement foundation.

Large Language Models (LLMs) have recently been introduced into traffic signal control (TSC) as decision agents due to their strengths in human-readable reasoning generation. Yet, existing LLM TSC methods optimize only from final outcomes and fail to distinguish valid from flawed reasoning steps, causing useful or misleading steps to be jointly updated and thus impairing the model's learning of effective reasoning. To bridge this gap, we propose an LLM-based framework ProcessLight to decompose signal decisions into verifiable semantic steps. Building on ProcessLight, we further develop Step-wise Traffic Process Policy Optimization (STeP-PO), a novel reinforcement learning framework that optimizes structured reasoning processes through step-level credit assignment. Specifically, STeP-PO uses step quality scores to evaluate local reasoning quality and step importance to measure each step's influence on the final action, and then assigns step-level advantages over a semantic step tree structure. The resulting step-level advantages are propagated to reasoning tokens, enabling fine-grained policy optimization beyond outcome-only rewards. Extensive experiments over multiple real-world datasets demonstrate the superiority of our methods. Our code is available at https://github.com/wenzhaoabc/processlight.

Weak-memory processors rely on ordering instructions for correctness, yet conventional implementations often enforce them more conservatively than the memory model requires. This over-enforcement manifests as drain-induced retirement stalls at ordering instructions and conservative squash/replay of speculative loads, suppressing legal executions and reducing throughput. We present TEMPO, a tag-based framework for precise micro-architectural implementation of ordering instructions. TEMPO assigns lightweight ordering tags to instructions and decomposes enforcement across retirement-time predicates and completion-time store ordering, allowing the core to enforce required ordering without conservative retirement serialization. TEMPO eliminates unnecessary retirement serialization at ordering instructions and speculative-load squash/replay. In our evaluation, TEMPO reduces geometric-mean normalized execution cycles by 7.9% on native four-thread workloads and improves geometric-mean IPC by 15.9% on an instrumented SPEC2017 dynamic binary translation (DBT) proxy for cross- ISA execution (e.g., x86-on-Arm), while adding only 262 bytes per core.

Recovering missing regions in 2-D LiDAR scans is crucial for maintaining geometric awareness in environmental sensing. LiDAR-only reconstruction relies on measurements surrounding the missing region and can degrade as the unobserved sector grows or the surface geometry becomes more complex. This paper presents a distributed integrated sensing and communication (ISAC) framework that uses directional 60-GHz beam-training measurements from multiple receivers to assist in the recovery of missing regions in 2-D LiDAR scans. Transmitter and receiver positions, beam directions, and relative beam-power thresholding are used to construct an RF-derived surface prior without requiring RF time-of-flight measurements. The resulting RF-derived range estimates are then fused with LiDAR measurements to estimate the missing geometry. The proposed framework is evaluated in an indoor environment using LiDAR and 60-GHz phased-array measurements from 55 receiver viewpoints comprising 37,620 beam-pair power measurements across 72 controlled missing-sector cases. The results show that RF-assisted reconstruction provides larger accuracy gains as the missing-sector width increases. For the 80-degree missing-sector case investigated in this paper, RF+polar fusion is shown to reduce the mean absolute error (MAE) from 2.271 m for polar LiDAR interpolation to 0.617 m, corresponding to a 72.8% reduction. The results further show that useful RF-assisted recovery can be maintained even with fewer beam-pair measurements under limited beam training. These findings demonstrate that directional communication measurements can support environmental sensing by providing complementary geometric information for missing LiDAR regions.

Clinical domain classification plays an important role in organizing and analyzing large volumes of unstructured medical text. However, medical transcription datasets are often highly imbalanced, which can substantially degrade classification performance, particularly for underrepresented clinical specialties. In this work, we present a comparative study of machine learning and transformer-based approaches for clinical domain classification from medical transcriptions. We evaluate six traditional machine learning classifiers—Naive Bayes, Support Vector Machine (SVM), Decision Tree, Random Forest, K-Nearest Neighbors (KNN), and XGBoost—along with two pretrained transformer models, BERT and XLNet, and a few-shot large language model prompting approach. Experiments are conducted on medical transcription data collected from MTSamples, comprising 5,013 samples across 40 clinical specialties. To address severe class imbalance, we investigate two balancing strategies: text augmentation using NLP-based synonym replacement and Synthetic Minority Over-sampling Technique (SMOTE). Experimental results demonstrate that data balancing substantially improves classification performance across the evaluated models. In particular, BERT achieves the highest F1-score of 0.996 on the SMOTE-balanced dataset while requiring lower training time than XLNet. The results highlight the effectiveness of transformer-based representations combined with appropriate data balancing strategies for clinical domain classification and provide a systematic comparison of classical machine learning, transformer models, and few-shot prompting for medical transcription analysis.

This paper develops the Rapidly-iterating kinoDynamic Grid (RDG) algorithm, an asymptotically near-optimal kinodynamic motion planning algorithm that produces high quality solutions through rapid iteration. The algorithm leverages a state space grid decomposition to perform node selection, dynamics propagation, and graph revision in constant time complexity with respect to the number of nodes in the trajectory tree. Through a covering ball sequence induction proof, the algorithm is shown to be asymptotically near-optimal and probabilistically complete. Different subsystems of the algorithm are evaluated against common nearest-neighbor search-based methods at generating exploration bias. The RDG algorithm is evaluated through simulated trials in complex, kinodynamic motion planning problem environments up to 10 DOF relative to similar sparse, kinodynamic planning algorithms with optimality guarantees, SST and DIRT. The RDG algorithm outperforms both SST and DIRT in mean final solution quality by up to 104% and 40% respectively. Additionally, RDG maintained a 100% success rate, even on a 10-DOF test case where both SST and DIRT did not.

We introduce and study a new model of decision trees that lies at the frontier of provable circuit lower bounds. We study $\ell$-local decision trees, in which each internal node queries an $\ell$-local function of the input. We show that sufficiently strong lower bounds for $\ell$-local decision trees would imply several breakthrough circuit lower bounds, including super-linear size lower bounds for log-depth circuits and improved bounds for unrestricted-depth circuits. Previously, such consequences were known to follow from strong lower bounds for depth-$3$ circuits, which has been the main prior approach in attempting to prove these results. Since local decision trees are strictly weaker than depth-$3$ circuits, this provides a formally easier route to the same circuit lower-bound consequences. We prove essentially optimal lower bounds for a weaker variant that we call oblivious $\ell$-local decision trees, where all nodes at the same depth query the same function. Our lower bounds follow from a new technique that uncovers sumset structure in local maps, and our hard functions are sumset dispersers, sumset condensers, and directional affine dispersers. Along the way, we give an explicit construction of a sumset condenser with small entropy loss. As an additional contribution, we initiate the study of degree-$2$ decision trees, in which each query is a quadratic polynomial of the input. We show that proving lower bounds in this model is a natural stepping stone toward constructing dispersers for degree-$2$ variety sources, which imply improved circuit lower bounds for unrestricted depth circuits. We prove nearly maximal lower bounds for the oblivious variant of the model.

Robot manipulation tasks often involve hidden state information that cannot be directly observed and must be inferred through sequential physical interactions. In such partially observable settings, conditioning an imitation learning policy directly on the recent raw observation history leads to poor performance. This is due to state aliasing, wherein identical observations may arise from different hidden states, and the policy receives conflicting action labels for the same input. To enable history-aware disambiguation capability, we propose conditioning a diffusion policy on a structured representation of the hidden states using Bayesian belief that exposes both the current most likely state estimate and the remaining uncertainty. This representation replaces raw history with a structured, compact input, enabling the policy to implicitly modulate between exploratory and exploitative behaviors based on belief uncertainty, without explicit mode switching or reward shaping. We evaluate across two domains with qualitatively different belief representations: a continuous belief for cornstalk gripper alignment via tactile sensing, and a discrete categorical distribution for latched door opening. In both domains, the belief-conditioned policy substantially outperforms the observation-only baseline and approaches privileged ground-truth performance, with ablations illustrating that the policy adapts its exploration behavior depending on the belief uncertainty at inference time.

Efficient coordination under limited communication remains a key challenge in decentralized multi-robot exploration. While centralized approaches benefit from global information sharing, they are often impractical in large-scale or communication-constrained environments. Existing Monte Carlo Tree Search (MCTS)-based approaches, such as Decentralized Monte Carlo Exploration (DMCE), enable decentralized planning by taking peer intent into account. This peer intent is obtained by communicating sequences of planned waypoints with robots within direct communication range. In this work, we extend this idea by introducing Probabilistic Peer Intent (PPI), which converts peer trajectories into a continuous spatial representation of predicted intent and incorporates it into local MCTS action evaluation. We additionally study the effects of sharing peer intent beyond direct communication range by propagating plans over multiple hops. Experiments across multiple simulated environments and team sizes show that PPI and Multi-hop propagation can each improve decentralized exploration, with their relative benefits depending on environment structure and team size. We also demonstrate the real-world deployment of our method on three robots operating in different environment types.

Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices, but their trajectories can violate app-specific security policies. Existing trajectory-level defenses rely on LLM prompting or rigid rules, and thus fail to support fine-grained, natural-language policies that generalize across apps and tasks. In this work, we introduce MATE, a lightweight, policy-conditioned auditor that encodes both agent trajectories and natural-language security policies to determine whether a trajectory violates a given policy and to explain why. Treating policies as editable text rather than fixed model parameters allows MATE to handle user-defined and evolving requirements without retraining. To construct MATE, we build a knowledge base by extracting app descriptions, workflows, and policies from hundreds of popular mobile apps worldwide, and synthesizing over 140K semantically realistic, policy-conditioned trajectories with a multi-stage pipeline. We further release MATEBench, a trajectory-level auditing benchmark with two synthetic subsets and one real-world subset of manually collected trajectories. Models trained with our synthesis-driven trajectory learning achieve over 95% accuracy on MATEBench, retain strong performance on external safety benchmarks, and audit trajectories from Zhipu's AutoGLM and Alibaba's Mobile-Agent on real devices with over 95% accuracy, outperforming prior methods by over 20%. MATE shows that practical, fine-grained security auditing for heterogeneous mobile agents is both feasible and effective.

Large Language Model (LLM) agents are increasingly trusted to operate live networks: they read state, change configuration, and verify the result. A first-order question is left implicit: at which level of abstraction should the agent operate? We make the interface-abstraction level an explicit, controlled experimental variable, organizing agent-network interfaces into a spectrum from raw CLI (A0) through bounded wrappers (A1) and standardized model-driven configuration (A2) to typed transactional service intent (A3-T), reconciled source-of-truth automation (A3-R), and their combination (A4). We present ANI-Gamut, a reproducible, open-source playground that exposes the same task at several levels on a single, densely populated brownfield substrate, where many coexisting services share resources and collateral damage actually arises. We instantiate and measure four points of the spectrum and describe the others only at the conceptual level, and record three dependent variables as the substrate is stressed by injected faults: task reliability, collateral damage against pre-existing tenants, and operational cost. In a pilot with small run counts (n=20, n=6 and n=4 per level), the interface level moves reliability and cost sharply: on a live change-set task a raw-shell agent fails on all six seeds while a typed transactional interface succeeds on all six (paired McNemar p=0.031, on six discordant pairs), at roughly an order of magnitude less cost, as the engineering effort migrates from the agent to a reusable transaction layer. Collateral damage, by contrast, is absent at every level, whether benign or under faults: in a tenant-isolated substrate the agents fail safe, and the blast radius is held by the substrate's isolation, which moves the safety question from the agent to the substrate.

Conversational AI assistants remember what people tell them, and for disabled people, that often includes disability. We interviewed 12 adults with disabilities in the United States who use LLM-based assistants such as ChatGPT, Claude, and Gemini about when, how, and why they disclose disability to these systems and how this compares with disclosing to people. Using contextual integrity as an analytic lens, we found that participants disclosed by need rather than by name, translating disability into task-scoped instructions; that the same disclosure was judged against two recipients, a non-judging interlocutor and a data-holding company, producing opposite norms; and that memory features relieved the burden of repeated disclosure while letting disability information drift into contexts where it did not belong. Participants did extensive boundary work to restore context and wanted control over scope, provenance, retention, and access rather than per-utterance toggles. We discuss implications for the design of conversational AI assistants.

Business requirements for enterprise software systems are rarely captured in structured form; the logic resides instead in source code, configuration files, and institutional memory. When these systems must be migrated, extended, or audited, the absence of formal requirements artifacts forces teams into expensive, knowledge-losing manual reverse engineering. This paper presents an agentic framework that autonomously generates Business Requirements Documents (bRDs) through reverse engineering of undocumented enterprise software. Seven specialized agents collaborate to discover user journeys, extract business rules, and synthesize a locked bRD from code, test suites, configuration, and available documentation, supported by static analysis tools, guided by embedded expert practitioner cognitive models, and overseen by human reviewers at controlled escalation points. Measured on actual execution traces across a real enterprise deployment, the framework generates comprehensive bRDs in under nine minutes per service, with extracted rules independently corroborated against real production defect records. In a comparable prior migration to the same target architecture, delivery required over two years; on the present programme the framework achieves a cost reduction exceeding 98% against a baseline derived from actual repository metrics using IFPUG complexity models and industry benchmark labor rates.

Image-to-LiDAR registration estimates the camera pose of an image with respect to a LiDAR point cloud. It has diverse applications in autonomous driving, robot navigation etc. However, state-of-the-art (SOTA) methods still 1) mostly assume same-frame inputs, struggling with the image and point cloud from distant frames; 2) rely on domain-specific training, failing to generalize to unseen scenarios. We propose ZIL, the first foundation model for zero-shot non-synchronized image-to-LiDAR registration. ZIL encodes the input image and point cloud with the Vision and Point Transformers. In addition to regressing the relative pose, ZIL also learns to predict 3D coordinates, which substantially improves the pose accuracy without additional annotations. Interestingly, naive mix-data training cannot enable zero-shot generalization, which requires normalization on both camera intrinsics and the LiDAR vertical-axis origin. Trained on 7 public datasets with 1.4M LiDAR frames, ZIL consistently and significantly outperforms previous SOTA with a single model across 5 in-domain and zero-shot benchmarks, reducing the translation and rotation errors by up to 87% and 76% (shown in Fig. 1). Code and models are available at https://github.com/ZijunLi7/ZIL.

Agentic AI systems built on large language models can plan over multiple steps, use external tools, retain information in memory, and coordinate with other agents. These capabilities make them more useful than static language models, but they also introduce new security and operational risks. Untrusted content from websites, emails, documents, and databases can enter the same context as system instructions; persistent memory can carry compromised information across sessions; and access to external tools can turn an incorrect model response into a consequential real-world action. This article reviews the trustworthiness of agentic AI across five interconnected dimensions: safety and robustness, alignment and human oversight, transparency and auditability, privacy and data governance, and regulatory compliance. It organizes key failure modes, including indirect prompt injection, backdoor triggers, goal misgeneralization, memory contamination, and cross-session data leakage, into a unified taxonomy. It also examines major mitigation approaches, such as instruction hierarchies, context isolation, spotlighting, process-based supervision, constrained tool use, and privacy-preserving memory, while distinguishing techniques supported by empirical evidence from those that remain largely conceptual. Building on this analysis, we introduce the Trustworthy Agent Development Lifecycle (TADL), a six-phase framework covering specification, design, training, evaluation, deployment, and monitoring. For each phase, TADL identifies relevant trust activities, expected evidence, and risk-based decision gates. Although TADL has not yet been empirically validated, it provides a structured foundation for developing and evaluating more secure and accountable agentic systems. The article concludes by identifying gaps in current benchmarks and outlining priorities for future research.

Offline reinforcement learning (offline RL) enables policy learning from pre-collected static datasets without online exploration, and is increasingly deployed not only in safety-critical domains such as autonomous driving and robotic control but also in data-mining applications such as recommendation and behavior analysis. While compliance-driven data removal enhances privacy, it also opens a previously unrecognized attack surface. We introduce UBA-ORL (Unlearning-activated Backdoor Attack on Offline Reinforcement Learning), the first unlearning-activated backdoor attack for offline RL: in the evaluated settings, the attack is substantially suppressed after normal training and becomes pronounced after a compliance-driven deletion (unlearning) request. UBA-ORL employs a dual-sample mechanism: alongside backdoor trajectories (BD) that link a trigger to malicious actions under inflated rewards, the attacker injects camouflage trajectories (CM) sharing the same trigger pattern but preserving benign actions with equally high rewards. During training, BD and CM provide competing supervisory signals; upon a legitimate deletion request on the CM subset, the residual BD signal can re-dominate, reactivating the backdoor on demand. Empirical results show that UBA-ORL achieves controllable activation under the evaluated offline-RL configurations, while no-trigger return changes vary by configuration, exposing a previously overlooked security risk in compliance-driven offline RL platforms. We urge the community to develop joint pre-/post-unlearning auditing mechanisms for compliant unlearning services.

Monitoring lower airspace over critical infrastructure using cellular signals of opportunity is highly practical because transmitters are pre-deployed, licensed, and continuously active. Digital twins can evaluate the feasibility of such integrated sensing and communication (ISAC) architectures, but their predictive accuracy must be validated against real-world data. This paper reports validation results for TiamiTwin, a digital twin developed for bistatic ISAC drone sensing, using empirical measurements from an operational 5G deployment featuring a commercial band n41 gNB and a receiver separated by 572.8 m over a non-line-of-sight (NLOS) channel. TiamiTwin incorporates three parallel channel representations evaluated on a 240-subcarrier grid: the 3GPP TR 38.901 (Release 19) bistatic ISAC model, a ray-traced site model, and the captured field measurements. Empirical results demonstrate that both statistical and ray-tracing models under-predict the measured root-mean-square (RMS) delay spread by approximately a factor of three. Furthermore, target reflections sit 68 dB below static clutter in power, making target detection entirely dependent on Doppler separation to isolate the drone from zero-Doppler background returns. Despite this severe clutter environment, the target remains separable along 88% of the flight path in the delay, Doppler, or joint delay-Doppler domains.

As explanations of artificial intelligence systems proliferate, their recipients must grasp not only what they convey but also recognise what they cannot. We conducted an interview study with nine participants to examine how explainees reason when their information needs exceed the scope of available explanations. Participants often unwittingly confabulated explanatory insights when relevant information was missing from the explanations, not recognising the inherent limitations thereof. We characterise such explanations as leaky explanations – simplifications that strive to hide complexity yet whose correct interpretation hinges on understanding of the concealed details. To address out-of-scope interpretations we propose Explanation Navigator: a conversational interaction framework that detects mismatches between users' information needs and explanations' content, elucidating pertinent yet implicit details and providing complementary explanations for unmet information needs. An online study with 316 participants showed that our approach allowed explainees to recognise and rectify confabulated explanatory insights, guiding them towards developing correct understanding.

Identity association in multi-object tracking (MOT) is vulnerable to partial occlusion, truncated detections, and fluctuating confidence scores. Existing motion-dominant trackers commonly represent occlusion as a scalar penalty. This treatment misses the directional observation bias caused by occlusion: left, right, top, and bottom occlusions distort the location and shape of a detection in different ways. We propose \ours{} (Directional Occlusion-Aware SORT), an online and training-free tracker that models these biases explicitly. First, it infers a soft front–back ordering from box overlap and relative bottom positions, and estimates directional occlusion coverage and depth. It then constructs a mixture of one clean and four directional occlusion observation components. The model uses a five-dimensional observation comprising box center, area, confidence, and aspect ratio, and adapts observation noise to predicted occlusion and detection confidence. The directional mixture likelihood is used in high-confidence association, low-confidence association, and track recovery; ambiguity penalties and local order-consistency swaps further reduce identity errors among nearby objects. On the DanceTrack validation split, \ours{} improves HOTA from 63.00 to 66.34, AssA from 45.10 to 49.57, and IDF1 from 62.19 to 65.28 over OA-SORT with the same detector and evaluation protocol. The gains are concentrated in association quality while detection accuracy remains stable. Additional local evaluations on MOT17 and MOT20 train splits characterize cross-dataset behavior under the same no-ReID tracking protocol.

Online discourse about urban issues - walkability, cycling infrastructure, public transit, housing density, and street safety - is voluminous but unstructured, and existing city-evaluation tools capture none of it. We present a pipeline and conversational system that combines geographic entity resolution, topic modeling, sentiment analysis, and Retrieval-Augmented Generation (RAG) over 22,788 chunks of YouTube transcripts and comments spanning 309 North American cities. Beyond the system itself, our contribution is a set of measurements about what happens when standard NLP components meet short, informal, geographically ambiguous text. A Twitter-tuned RoBERTa classifier outperforms a VADER lexicon baseline by 12.6 macro-F1 points (0.589 vs. 0.464; McNemar p = 0.0001), but both models collapse on the neutral class, which dominates urbanist comment traffic; annotators disagree on the same class (Cohen's kappa = 0.53). Dense retrieval beats a TF-IDF baseline at every cutoff (P@5 0.790 vs. 0.560), and video-level relevance proxies understate chunk-level precision by a wide margin (0.660 vs. 0.94 under human rating). For groundedness evaluation, we find BERTScore unusable when a multi-sentence generated summary is compared against a single short comment - scores are nearly flat regardless of relevance - and show that ROUGE-1-based groundedness is a paraphrase-driven lower bound rather than a hallucination rate. These findings generalize beyond the urbanist domain to any RAG system built over short user-generated documents.