Computer Science (arXiv)

High-dimensional feature representations are widely used in machine learning-based cyberattack detection systems. However, they increase computational complexity and may hinder deployment in resource-constrained environments. In this paper, we investigate feature compression techniques for cyberattack classification by comparing two dimensionality reduction approaches: Principal Component Analysis (PCA) and Linear Predictive Coding (LPC). Compressed feature representations with varying dimensionalities are generated and evaluated across several classification models. Experimental analysis demonstrates that PCA preserves classification performance even under aggressive compression. On the other hand, LPC provides competitive predictive representations with slightly larger performance degradation. The results show that substantial reductions in feature dimensionality can be achieved with minimal impact on classification accuracy, highlighting the potential of lightweight feature compression for efficient cybersecurity analytics.

Intrinsic methods fill the default toolbox for geometry processing on meshes. Intrinsic operators, in particular the Laplacian, underlie methods that require invariance to isometry and have hence been employed in many algorithms for shape analysis, learning, and editing. However, intrinsic methods are predicated on assumptions that quickly become brittle when working with in-the-wild geometry, where (i) mesh quality is not guaranteed, and (ii) many meshes are modeled with multiple connected components. In such settings, volumetric constructions are better-defined, since restrictions on surface topology can be relaxed. This paper presents a Monte Carlo method for estimating the Dirichlet-to-Neumann (DtN) operator -- a boundary-to-boundary volumetric operator -- and its associated Steklov eigenmodes. We build on recent developments in Monte Carlo geometry processing by casting this boundary operator itself as the subject of estimation. The DtN operator, defined through a volumetric stochastic process, is then generalized to the exterior domain, where it couples disconnected components through the surrounding ambient space. We show that our method is orders of magnitude faster than existing boundary-element approaches for computing Steklov spectra while remaining robust to poor triangulations, high-resolution meshes, and multi-component geometry. To demonstrate this scalability, we compute interior and exterior Steklov eigenspectra for approximately 450,000 shapes from the uncurated Objaverse dataset. We incorporate these operators into Steklov-CLIP, a mesh-based neural network that uses volumetric spectral operators for large-scale contrastive 3D representation learning. The resulting network learns semantically meaningful global and dense shape representations, illustrating that geometrically-principled volumetric operators can be made practical at the scale of modern 3D datasets.

We introduce Transition states (T states), denoted by $\ket{T_k^n}$, as a class of multipartite entangled states characterized by a fixed number of state transitions between adjacent qubits. These states form equal-amplitude superpositions over all states with a specified transition count. Unlike Bell states based on two-qubit correlations, GHZ states characterized by global correlations among all qubits, and W and Dicke states based on fixed numbers of qubit excitations, T states are defined by transition counts along an ordered sequence of qubits. We prove that T states are unitarily equivalent to Dicke states through a chain of CX (controlled-X) operations, thereby establishing a direct correspondence between transition-based and excitation-based representations of multipartite entanglement.

Vision-language models (VLMs) excel on visual question answering and multimodal reasoning benchmarks. Yet their capability on ultra-resolution images - where critical evidence is tiny, subtle, spatially distant, or distributed - remains unclear. Existing evaluations largely report final-answer accuracy, offering limited insight into whether models acquire and integrate the necessary visual evidence. We introduce UltraVR, a diagnostic benchmark for evidence-grounded visual reasoning over ultra-resolution images. UltraVR spans four high-value scenarios: CCTV surveillance, remote sensing (RS), whole-slide image (WSI) pathology, and industrial anomaly detection (AD). These domains pose complementary challenges: fine-grained object grounding in crowded CCTV scenes, long-range spatial comparison in RS, multi-scale evidence navigation in WSI, and subtle irregularity detection in repetitive industrial layouts. Beyond standard QA triples, each instance includes a structured ground-truth chain of thought with step-level questions, intermediate answers, and reasoning labels. These labels decompose reasoning into evidence grounding, local perception, quantification, evidence integration, and decision inference, enabling process-level diagnosis over black-box scoring. Using UltraVR, we evaluate frontier VLMs and show that current models remain far from reliable on ultra-resolution reasoning. Importantly, the structured annotations allow us to localize failures across the visual-to-decision pipeline: errors concentrate in evidence grounding and local perception, while downstream inference often recovers when intermediate visual facts are supplied. These findings demonstrate UltraVR as a diagnostic testbed for measuring not only whether VLMs answer correctly, but where their ultra-resolution reasoning process breaks.

Generative models have shown impressive results in speech enhancement but often suffer from multi-step inference. We propose SB-RF, a one-step generative framework integrating Rectified Flow (RF) with Schrödinger Bridge (SB) theory. SB-RF constructs a conditional bridge between clean and noisy speech distributions via entropy-regularized optimal transport. By aligning SB trajectories with the optimal transport geodesic through the velocity-matching objective of RF, SB-RF enables high-quality enhancement with one-step generation. Experiments demonstrate that SB-RF achieves leading performance among generative methods on the VoiceBank-DEMAND benchmark. Furthermore, to fully assess performance in challenging real-world scenarios, we evaluate SB-RF on a simulated low signal-to-noise ratio test set using an expanded training dataset. Under these conditions, SB-RF exhibits strong and competitive robustness with high efficiency, validating its potential for real-world applications.

Code Agents have achieved remarkable advances in recent years, exhibiting strong capabilities across a wide range of software engineering tasks. However, their misuse often produces bloated and disorganized code that impairing readability, extensibility, and robustness. Despite this risk, existing benchmarks largely evaluate functional correctness rather than long-term maintainability of code agents. In this paper, we propose SmellBench, an extensible code refactoring benchmark that proactively injects code smells into clean code snippets from real-world repositories. This design enables the generation of controlled, high-quality, and diverse refactoring cases with human-written ground truth. Specifically, it contains 294 cases spanning 7 popular smell types, 3 difficulty levels, 2 instruction settings across 7 real-world repositories. We further design 3 evaluation aspects covering functional correctness, localization ability, and refactoring quality assessment. Experiments with 2 popular agents and 6 large langauge models (LLMs) show that the best combination - Qwen Code + Claude Sonnet 4.5 - achieved only a 50.34 score of smell elimination. Further analysis reveals that this gap arises from a focus on local code smells and a lack of cross-file understanding, which hinders comprehensive smell elimination.

We study the problem of robust repair of a single erasure in Reed--Solomon codes under low communication bandwidth. Focusing on the Guruswami--Wootters trace repair framework, we investigate whether a failed node can be correctly repaired in the presence of erroneous responses from helper nodes. Equivalently, we view the collection of downloaded traces as a code, which we call the repair-trace code. By characterizing the zero coefficients of the associated polynomial in terms of cyclotomic cosets, we derive upper bounds on the dimension $k$ that allow correction of a given number of erroneous traces $e$, as well as lower bounds on the minimum distance as a function of $k$. For the case $q=2$, we exploit explicit formulas for cyclotomic coset representatives to obtain the exact optimal dimension bound for single-error correction. We also propose two efficient robust repair schemes. Our first scheme achieves the error-correction capability guaranteed by the BCH bound. To approach a stronger bound based on character sums, we develop a second scheme that tolerates more errors at the cost of an additional factor $n$ in computational complexity.

We address the challenge of engineering distributed haptic displays capable of reproducing multiple localized, independently addressable vibrations -- representing virtual tactile pixels -- at arbitrary locations on a surface. Our technique is based on the focusing of mechanical waves in a flexural plate using a sparse set of actuators. At tactile frequencies, wave diffraction prevents the formation of localized virtual tactile pixels at spatial scales relevant for multi-digit touch interactions. We overcome this limitation by augmenting the plate with a lattice of mechanical resonators, forming a locally resonant metamaterial plate. Coupling between the plate's dynamic modes and those of the resonators alters the dispersion relation governing wave transmission, introducing a slow-wave branch that enables focusing beyond the diffraction limit imposed by the unmodified plate. We use numerical simulations to engineer the dispersion relation of the metamaterial system for high-resolution focusing at tactile frequencies. We then fabricate a metamaterial tactile display and experimentally demonstrate virtual pixels that are far more localized than those generated on an otherwise identical plate without resonators, resulting in a tenfold reduction in virtual-pixel area. In behavioral experiments, we show that this system can deliver perceptually localized single- and multi-point tactile feedback and moving tactile sources while maintaining independent control over temporal waveforms at multiple display locations. The methods reported here can enable high-resolution haptic displays for widespread applications using a small number of actuated degrees of freedom.

Sound effects (SFX) datasets and libraries often employ distinct tagging schemes, taxonomies, and metadata structures. This creates challenges for research on SFX classification and generation because incompatible taxonomies lead to siloed datasets that might require individualized approaches, result in non-comparable outcomes, and prevent data merging strategies. We propose a modular dataset relabeling framework that adopts the Universal Category System (UCS), an industry-standard hierarchical taxonomy for sound effects, as a shared structural foundation. This open-source framework enables us (i) to convert tags of existing datasets to UCS with a rule-based multi-stage pipeline and conflict resolution to achieve high automatic conversion rates, (ii) to suggest a stratified dataset split for the new labels, and (iii) to combine multiple datasets. To showcase the practical utility, we introduce the EnvSound-UCS dataset, a publicly available unified UCS-compliant dataset of environmental sounds with 58,057 sound clips from three sources: AudioSet, FSD50K, and ESC-50.

Repository-level coding benchmarks face a trade-off between task difficulty and evaluation reliability: tasks that challenge frontier models often involve large codebases with incomplete test coverage, while human review does not scale. We introduce TensorBench, a benchmark of 199 feature-addition and refactoring tasks on an open-source compiler-based tensor framework that extends PyTorch with first-class support for dense and sparse tensors. Tasks cover new sparse formats, dense optimization passes, IR transformations, scheduler changes, runtime components, and high-level numerical operators. TensorBench grades each run by applying the agent's patch and running the framework's test suite, which includes the pre-existing randomized regression tests and any tests the agent adds. For feature-addition tasks, a pass means that the patched repository preserves the tested pre-existing behavior and satisfies the agent-added checks for the requested feature. We evaluate seven coding agents spanning three frontier model families and one open-weight model. Pass rates under this criterion range from $64.8\%$ for the strongest agent to $22.1\%$ for the weakest. Agents pass different subsets of tasks: pairwise Cohen's $κ$ ranges from $-0.07$ to $0.43$, with $κ= 0.05$ for the two strongest agents.

Mispronunciation Detection and Diagnosis (MDD) has gained increasing importance in computer-assisted language learning and speech technology in recent years. In this paper, we propose a method for constructing statistical graphs that enable models to learn phoneme confusion patterns represented as directed graphs. Furthermore, we introduce a language-specific strategy to capture systematic pronunciation differences across various native language (L1) backgrounds. The effectiveness of our approach is demonstrated through extensive experiments on the L2-ARCTIC benchmark, where it achieves an F1-score of 59.52%, outperforming several competitive baselines.

While ColBERT is an effective neural retrieval architecture, it requires a heavy index structure to support candidate set retrieval based on approximated token embeddings, gathering and decompressing document token embeddings, and applying the MaxSim operation. Indexes in PLAID and similar ColBERT implementations require five to ten times the disk storage of the original raw text, which limits their scalability. Furthermore, prior work has identified that the gathering and decompression stages are the primary inefficiencies at query time. Limiting the number of document tokens that must be gathered by thresholding and score approximation does not eliminate the need for the entire index to support ad hoc queries. In this work, we propose an embedding quantization approach that turns a ColBERT index into a true inverted index. We show that, theoretically, ColBERT with embedding quantization is equivalent to learned-sparse retrieval except for the scoring mechanism. Empirically, we demonstrate that our index is 50-70% smaller than a one-bit PLAID index while retaining retrieval effectiveness.

LLM-driven automated penetration testing agents are typically evaluated against static targets that neither detect nor respond to attacks, so their behavior under intelligent defense remains untested. The causal consistency of multi-step attack chains likewise hinges on unstable LLM reasoning, and agent decisions remain opaque to human analysts. These three shortcomings, in realism, consistency, and auditability, are usually patched in isolation. We present ZERO-APT, a turn-based attacker-defender-judge framework that addresses them within a single architecture. For realism, ZERO-APT embeds a configurable LLM Defender that consumes Sysmon telemetry and detects attacks in real time, exposing the attacker to a live opponent rather than a passive target. For consistency, three architectural mechanisms move causal consistency from unstable LLM reasoning into enforced system architecture: separation of planning from execution, multi-dimensional ReAct feedback, and a hard-constraint-filtered action library. For auditability, a dedicated Judge agent adjudicates each round, maintains global state, and emits structured post-hoc CTI reports that make every decision traceable. We evaluate a Windows Server 2022 post-exploitation prototype across five scenarios with three Defender configurations. ZERO-APT reaches 79\% attack success rate (Aurora 22\%, PentestGPT 39\%), a Causal Consistency Score of 0.860 (Aurora 0.930, Claude Code 0.520), and end-to-end decision auditability through structured CTI reports. We release the benchmark to support evaluation of penetration agents under intelligent defense.

Large Language Models (LLMs) have transformed natural language processing, but they remain vulnerable to Prompt Injection (PI) and Jailbreak (JB) attacks. In addition, benchmark evaluations may be affected by contamination and partial information leakage, compromising performance estimates. This work presents GuardNet, a guardrail system based on an ensemble of shallow neural networks (BiLSTMs) with approximately 47 million parameters. We investigate the hypothesis that robustness in adversarial scenarios depends more on the diversity of example coverage and threshold calibration than on model scale. The results indicate that GuardNet achieves competitive performance compared with lightweight detectors and high efficiency at low latency, although larger LLMs such as Mistral-7B and Llama-3.1-8B still achieve superior performance in terms of F1 score and AUROC on the blind JBB-Behaviors benchmark. Nevertheless, GuardNet achieves an AUROC of 0.747 on the blind dataset (n = 200) and an F1 score of 0.92 on a proprietary benchmark (n = 50), under threshold calibration and evaluation with declared partial information leakage. The system operates with an average latency of approximately 50 ms on CPU, making it suitable for deployment in production environments with cost and infrastructure constraints.

Undergraduate research programs such as the Summer Undergraduate Research Fellowship (SURF) at Purdue University receive thousands of applications every year, requiring significant time and effort for program staff to evaluate each submission consistently and within tight timelines. This work-in-progress paper describes the development and initial deployment of a large language model (LLM)-based tool to assist in the evaluation of approximately 1,200 student Statements of Purpose (SoPs) for the SURF 2026 cycle at Purdue University. The workflow utilizes OpenAI GPT models (GPT-4o, GPT-5-mini, and GPT-5.2) and uses a structured rubric across six subcategories, each scored on a 0-3 scale. A few SoPs, graded by program staff, were used to tune the model responses. The model prompt was designed to generate both numerical scores, rationales (including positive and negative aspects) and short excerpts from each submission. Using GPT-5.2, the full batch of 1,200 SoPs was processed in approximately 4.6 hours of compute time, averaging roughly 14 seconds per SoP (with per-SoP timing varying with SoP length, which ranged from 500 to 2,000 words). Notable differences in rubric adherence were observed across model versions, with GPT-5.2 adhering most closely. Disagreement in model scores was more pronounced for lower-scoring submissions. The LLM outputs replicated the role previously played by distributed human graders, providing the program coordinator with scored and rationale-annotated outputs for the entire applicant pool. The program coordinator then reviewed these outputs alongside each applicant's SoP, applying the same downstream office criteria used in prior SURF cycles, to produce a shortlist of strong candidates. This coordinator review was completed in approximately 4 hours, compared to the multi-week coordination effort required in prior program cycles.

Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and context. Existing testbeds rely on a few expert-authored domains, vary mainly strategic posture, and score every turn against every topic, introducing off-topic noise. We introduce SoCRATES, a benchmark for evaluating proactive LLM mediators in realistic, multi-domain testbeds. It constructs scenarios from real conflicts through an agentic pipeline across eight domains, probes five socio-cognitive adaptation axes (strategic posture, party composition, history length, emotional reactivity, and cultural identity), and scores each topic only on the turns that advance it via a topic-localized evaluator. The evaluator reaches 0.82 alignment with human experts, more than doubling a per-turn baseline. Benchmarking eight frontier LLMs, we find that even the strongest mediator closes only about a third of the unmediated consensus gap under diverse and realistic testbeds, with performance varying sharply by socio-cognitive axis, highlighting that progress lies in social adaptation to diverse conditions.

Speech-based mental health screening offers scalable depression detection, yet clinical deployment faces a significant barrier: users' privacy concerns about demographic information exposure. Current techniques struggle to resolve this conflict. Adversarial training often fails against unseen threats, whereas Differential Privacy tends to compromise diagnostic performance by injecting noise across all features. This paper presents InfoShield, which minimizes mutual information between speech representations and sensitive attributes while preserving depression classification accuracy. We identify that standard MINE estimators struggle with sequential speech due to temporal-static misalignment, and introduce TimeAwareMINE with cross-modal attention to align acoustic frames with attribute embeddings. Experiments on the Androids Corpus show InfoShield reduces gender inference from 92.6\% to 55.5\% and age inference from 55.7\% to 30.3\% with limited utility loss (6\% F1 reduction), achieving F1=0.784 compared to prior SOTA's 0.723.

Deployed large language model agents must adapt to distribution shift in dynamic environments. Ideally, adaptation can be performed from accumulated agent experiences and retain prior capabilities while transferring to future tasks. However, agent actions and environmental transitions can only be sampled once per scenario, as real-world environments cannot be trivially reset. To this end, we investigate an experiential and online continual learning setting in which agents learn from a stream of scenarios. We propose continual learning as-a-service (CLaaS), a system which enables agents to improve during deployment, abstracted behind a chat API. To increase sample efficiency, CLaaS stores rollouts in an experience replay buffer for gradient reuse during asynchronous training. We evaluate CLaaS on an adversarial task, demonstrating that parametric updates lead to superior forward transfer and less forgetting than in-context learning, with replay being a critical choice for sample efficiency.

Evaluating large language model (LLM) agents in multi-turn interactive environments is expensive and risky, as it requires online environment interaction. We propose ADWM (Autoregressive Diffusion World Model), an evaluation framework that estimates the performance of a new LLM agent policy purely from pre-collected trajectories. The core idea is to learn a latent diffusion world model that simulates how the environment responds to the evaluation policy, without ever executing it in the real environment. Existing diffusion-based OPE methods guide full trajectories in a single pass by jointly diffusing states and actions, an assumption that breaks down for LLM agents whose actions are discrete text that must be sampled from the policy after observing the environment. Unlike autoregressive world models that suffer from compounding errors, ADWM models each transition as an independent denoising process, enabling reliable step-by-step rollouts where the world model and agent alternate in causal order. Crucially, the LLM agent under evaluation directly guides the diffusion generation at each step via a policy-conditioned score function, ensuring that simulated trajectories accurately reflect its decision-making patterns. Empirically, ADWM achieves accurate value estimates and evaluation reliability across diverse multi-turn agent tasks, demonstrating its promise as a practical framework for offline LLM agent evaluation.

A situated query like "where is Lin Wei?" often encodes more than its literal content: the user may also want to know whether Lin Wei is free, in a good mood, or worth interrupting now. Standard tool-use agents answer the literal question and stop. AURA inserts an inference step between scene perception and tool use that produces an IntentFrame: a structured estimate of the implicit need with a scalar gap score that controls per-query probe budget and tool selection. On a 100-query four-scene implicit-intent benchmark, AURA improves implicit-need coverage over ReAct-style probing (Delta = +0.07, p < 10^-6); three of four scenes are individually significant, the gain reproduces on a second backbone, and a prompt ablation attributes the lift to gap calibration rather than answer memorisation. On factual lookup the controller trades raw accuracy for 82% fewer probes and zero forbidden-tool violations on a privacy-sensitive slice; scope conditions are detailed in Limitations. Code, simulator, and benchmark are released at https://github.com/innovation64/AURA.

This study presents a comprehensive field validation of a multi-resolution Convolutional Long Short-Term Memory (ConvLSTM) framework for predicting retaining wall deformation during staged excavation. The framework is trained on Gaussian noise-augmented numerical simulations and integrates ConvLSTM models operating at different temporal resolutions through a stacking ensemble strategy. The proposed framework is validated using field monitoring data from 34 inclinometers across 11 excavation sites in South Korea. Site-wise prediction performance is systematically evaluated using multiple evaluation metrics, with analyses of the influence of temporal deformation irregularity and spatiotemporal prediction characteristics on model performance. The results demonstrate that the framework predicts retaining wall deformation associated with up to 5.0 m of additional excavation with an average mean absolute error of 1.4 mm and a coefficient of determination of 0.93 across the excavation sites. These results indicate that the framework, although trained exclusively on numerically simulated and augmented database, can be effectively applied to diverse field excavation conditions and achieve a reliable level of prediction accuracy in practical retaining wall deformation prediction.

Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, making it unclear which components are essential for scalability. We revisit this question and argue that the primary driver of scalable multitask RL is not model-based control, but \emph{representation learning}. In particular, we show that combining predictive, model-based representations with high-capacity value function approximation is sufficient to achieve strong performance, even without planning. We evaluate a simple model-free algorithm, MR.Q, coupled with auxiliary predictive objectives into a scalable actor-critic architecture. This approach outperforms a recent world-model-based method and a range of deep RL baselines across a diverse suite of multitask continuous control tasks, while significantly reducing computational overhead and improving wall-clock efficiency. We observe consistent improvements with increased model capacity and show through ablations that predictive representation learning is critical for performance.

Role-playing language agents (RPLAs) should play characters whose values and behavior evolve as the story progresses, not maintain a fixed persona. Existing benchmarks measure factual recall at a given chapter, not whether responses align with the character's psychological trajectory, especially in scenarios the source text never explores. We introduce ArcANE (Arc-Aware Narrative Evaluation), an automatically constructed benchmark spanning 17 novels and 80 principal characters. A Character Arc segments the narrative into phases along a psychological axis, and each probe poses the same scenario across phases, spanning both situations within the source text and situations beyond it. Across six models and six context modes, conditioning on the Character Arc tops every other context strategy on every model, and the gap is largest on scenarios outside the source text where retrieval has nothing to find. We further fine-tune open-weight models on the same data to obtain ArcANE-8B/32B, which widen the Arc advantage even more on scenarios outside the source text.

Despite progress in image tokenization, standard methods encode redundant information by mixing all granularities within each token, thus redundancy persists between tokens. The mix of information of different granularity also complicates the training of generators. This paper introduces SelfBootTok, a method that resolves this by cleanly decomposing information into global and local token groups. Through self-bootstrapped learning, the model predicts local details exclusively from global tokens, shifting the burden of visual details from the generator to the tokenizer. Consequently, our generator is far more efficient, requiring only global tokens and reducing computation by approximately 40%, while delivering superior reconstruction and generation. Moreover, this paradigm scales elegantly: by leveraging more data or parameters to self-supervise local representation learning, SelfBootTok achieves a new state-of-the-art gFID score of 1.56 using only 64 tokens.

Reliable decision making pipelines powered by machine learning models require uncertainty quantification (UQ) methods that come with explicit safety guarantees. Conformal prediction provides such UQ by wrapping ML predictions into prediction sets, and recent work by Kiyani et al. (2025b) established that these sets can be translated into optimal risk-averse decision policies -- yet only inheriting marginal safety guarantees. We generalize and strengthen their results by (i) introducing action-conditional conformal prediction, which yields safety guarantees conditioned explicitly on each action taken by the decision maker, (ii) showing that action-conditional prediction sets serve as a proxy for the feasible decision space for risk-averse decision makers aiming to optimize action-conditional value-at-risk, and (iii) proposing a principled finite-sample algorithm based on pinball-loss minimization, connecting the framework of Gibbs et al. (2025) to action-conditional guarantees. Experiments on two real-world datasets confirm that our approach significantly improves action-conditional performance over conformal baselines.