Daily pick of latest papers for the past 5 days. Updated 26 August 2026.
220 of 220 papers
Action-conditioned world models are increasingly used as learned simulators for policy evaluation and improvement, yet their effectiveness rests on an unverified assumption: generated futures faithfully reflect arbitrary valid actions...
World action models (WAMs) improve robot control by modeling how observations evolve, but generating future observations at test time incurs substantial latency. Fast-WAM removes this process for efficiency; however, our matched...
Generative models are commonly ranked by Fréchet Inception Distance (FID) and Kernel Inception Distance (KID), yet FID's first-two-moment summary can miss distributional differences, and a reported scalar gap alone is not a calibrated test...
Smart glasses are evolving from capture and display accessories into first-person intelligence platforms that connect human perception, persistent context, and digital or physical action. Their on-body viewpoint aligns with the wearer's...
Recursive self-improvement (RSI) remains hard in long-horizon tasks, where growing histories obscure the task state and misalign skill invocation. We introduce Recuris, a recursive Experiential-Working Memory architecture for long-horizon...
Group-relative reinforcement learning waits for sibling rollouts of the same prompt, which is costly for long and variable tool-use trajectories. Single-stream Policy Optimization (SPO) removes this dependency with a persistent...
Multi-task vehicle routing problem (VRP) solvers seek to handle multiple VRP variants within a single unified model, avoiding the need to train a separate model for every variant. In spite of recent progress, current approaches remain...
Marginalized importance weighting evaluates a target policy by reweighting offline state-action samples with its discounted occupancy ratio, characterized by an adjoint Bellman equation. Existing minimax, primal-dual, and fitted...
Maitreyee Das Urmi, Jessica Pourleyli, Fabio Santos, Glaucia Melo
cs.CR, cs.SE
Large Language Models (LLMs) increasingly generate code from natural-language prompts, making prompt engineering a key mechanism for shaping the security of generated software. Structured and security-oriented prompts are widely used to...
Enterprise cybersecurity research draws on a wider range of methods than any single community routinely teaches. Researchers face a selection problem before they face a technical one: a study may simultaneously need a systematic review, a...
Model cards are structured documents that summarize key information about machine learning models to improve transparency, usability, and accountability. However, they often lack a consistent structure, and many models provide no model...
Color discrimination is a fundamental aspect of visualization as it influences how people interpret visual encodings. Many visualization guidelines are informed by perceptual studies, yet relatively few have been replicated. Acknowledging...
Angela D. R. Smith, Gabriella Thompson, Christopher L. Dancy, Mark Díaz et al.
cs.HC, cs.CY
As generative AI (genAI) systems become embedded in education, employment, healthcare, and creative industries, the impact and engagement among marginalized groups have become both a widespread discourse and a focus in scholarly research...
Konstantinos E. Kampourakis, Vyron Kampourakis, Georgios Kambourakis, Sokratis Katsikas et al.
cs.CR
Intrusion detection research in Industrial Control Systems (ICS) heavily depends on public datasets, yet no prior work has systematically assessed whether the collective dataset corpus supports current evaluation claims. This paper...
Requirements elicitation is essential for developing interactive software systems, as it helps ensure that the resulting product meets stakeholder needs. Since elicitation typically relies on natural language (NL), misunderstandings can...
Learning from Demonstration (LfD) allows robots to learn manipulation tasks directly from humans, thereby supporting the versatile application of robots. Most LfD methods do not explicitly model the physical interactions between a robot...
Emotion preference learning uses pairwise comparisons between candidate descriptions to align multimodal large language models (MLLMs) with human judgments of open-ended emotion descriptions and to train reward models that capture human...
Harbor seals track hydrodynamic trails with their vibrissae, enabling passive perception of moving targets in dark or turbid water. Inspired by this capability, we present compact fiber Bragg grating (FBG) whiskers for underwater robots...
Claims that generative AI will soon write all of the code have led to predictions that programming is nearing its end. In this vision paper, we argue against this assumption that broader access to code generation necessarily democratizes...
World-Action Models (WAMs) jointly learn future visual prediction and action generation, using video dynamics as a representation-learning signal for robotic manipulation. However, their video latents are primarily optimized for visual...
Ultralow-latency communication is critical for emerging next-generation applications such as XR, real-time control, and distributed sensing. We present ECO-COMM, an event-camera-based optical communication system for ultra-low-latency...
Video games provide a scalable source of training data for video world models, offering diverse environments, complex interactions, and abundant in-the-wild gameplay videos. However, raw gameplay footage entangles the game world with...
Process mining is widely used to diagnose processes and identify performance and compliance issues. Specifically, Predictive Process Monitoring (PPM) techniques use AI models to predict outcomes of ongoing process instances. While these...
As mobile phone adoption has surged, so have scams involving these devices. One such scam, known as SMiShing (or smishing) after Short Message Service (SMS), involves fraudsters sending phishing links via mobile texts. Despite the...
We propose recursive encoder and decoder (RED) for building a single deep neural network (DNN) model that can separate multi-speaker mixtures containing unknown numbers of speakers and variable numbers of microphones arranged in an unknown...
This paper introduces an environment for constructing literate programs in concert with language-aware machine agents. This environment includes a grammar for executable program essays, a parser that treats names as first-class objects, an...
Prompt engineering and prompt engineering techniques (PETs) have become an integral part of software engineering for AI systems. However, new LLMs are released frequently and it remains unclear how the effectiveness of prompt engineering...
Urban socio-semantic segmentation leverages digital and satellite imagery to provide critical spatial semantic information for downstream applications such as urban resource allocation. Although existing methods achieve high segmentation...
Deep neural network based deepfake detection systems have achieved high levels of accuracy on benchmark datasets and competitions. However, most models lack interpretability. It is challenging to extract reasoning from the network that can...
The primary goal of a distributed storage system is to ensure that clients can both write and read data in a reliable and consistent manner, even in the presence of failures. While existing asynchronous verifiable information dispersal...
Consistent replication of data among distributed processes – a task involving the well-known consensus problem – is notoriously expensive and hard to scale, affecting especially datacenter services with stringent performance requirements...
Over the past decade, autonomous robotic systems have been increasingly deployed in applications such as surveying, search and rescue, and last-mile delivery. These applications require robots to generate safe and efficient motion plans in...
Spatial audio is a key component of immersive 360° media, yet high-quality spatial capture remains limited in real-world speech-dominant scenes. We study visually guided First-Order Ambisonics (FOA) speech spatialization in the wild: given...
Spatial audio enhances user immersion by reproducing 3D sound fields, with Ambisonics being a widely adopted representation. While Ambisonics is theoretically independent of the recording setup, practical microphone arrays introduce...
Prehospital stroke assessment aims to accurately identify stroke symptoms and make rapid decisions through standardized procedures within an extremely narrow time window, thereby saving valuable time for subsequent treatment. In clinical...
Satellite-based distributed learning promises to train machine-learning models directly in orbit using massive, globally dispersed sensor data, thereby avoiding large-scale data downloads to ground servers. However, training convergence is...
Constructing syntactically correct and cryptographically valid message sequences is essential for protocol state machine learning, conformance testing, and fuzzing. Unlike plaintext protocols, cryptographic protocols involve complex...
Industrial services in beyond-fifth-generation (B5G) and sixth-generation (6G) networks are increasingly executed as multi-phase workflows whose quality-of-service (QoS) demands change across ordered phases. Existing exposure, analytics...
System prompts can be extracted from commercial LLMs with over 80% success and redeployed at zero cost, yet a prompt owner has no way to verify whether a suspected deployment is a clone. We propose Black-Box Behavioral Fingerprinting...
This chapter examines AI-media objects - creative and artistic outputs generated through generative artificial intelligence in the form of text-to-X tools - in relation to three avant-garde movements of the twentieth century: Dadaism...
Mixed precision is a promising approach for reducing the computational cost and energy consumption of Computation Fluid Dynamics (CFD) simulations, but its effectiveness depends strongly on where precision is reduced within the full...
Discrete motion representations have substantially advanced autoregressive text-to-motion generation. However, most motion tokenizers are optimized for reconstruction and do not explicitly allocate capacity according to semantic role...
On social media, we often encounter short-form video ads that employ cinematic editing techniques to evoke an emotional response. While AI tools are beginning to generate such cinematic ads automatically, we lack a fine-grained framework...
LLMs are becoming part of everyday life, including for older adults (OAs). OAs often learn digital technologies with younger family members, who have traditionally served as "warm experts" providing trusted and personalized operational...
3D geometry editing is a critical yet labor-intensive part of the graphics pipeline, requiring artists to translate creative intent into precise operations in complex professional software. Large language models (LLMs) have shown promise...
Multi-view reconstruction extends beyond surface recovery to editable and relightable mesh assets. Such assets require well-formed topology, valid UV parameterization, and explicit PBR material maps. Existing surface reconstruction...
High-fidelity image-to-3D generation requires a 3D representation that captures both geometry and appearance. To support relighting and integration into standard rendering pipelines, the representation should include physically based...
Data mixing is a central design problem in large language model pretraining: given a fixed token budget, practitioners must decide how much data to allocate to each domain. Recent proxy-based methods address this problem by training small...
Recent Vision-Language Models encode high-resolution images into long visual token sequences, incurring prohibitive prefill costs. To compress them, existing methods score each visual token by averaging text-to-visual attention uniformly...
Large Language Models excel at code generation, yet competitive programming exposes a persistent failure mode: existing multi-agent pipelines distribute work over generic planner, coder, and debugger roles and delegate the choice of...
Common shortest-path algorithms, such as Dijkstra's (SPF), that OSPF uses, provide exact routing solutions but must be recomputed for each network topology, limiting scalability in dynamic or large-scale networks. This paper proposes the...
Denoising score matching trains diffusion models by regressing onto a conditional score, although generation ultimately requires the marginal score. The two objectives share the same population minimizer, but the conditional target remains...
Supervised fine-tuning on teacher-generated trajectories is the standard first stage for distilling tool-calling capabilities into deployable models. Post-training pipelines that drive shipped tool-calling agents re-run this stage on a...
Indoor localization based on Wi-Fi typically relies on extensive collection of real-world received signal strength (RSS) fingerprints, making deployment costly and time-consuming. We present a ray-tracing-based framework that reduces this...
Latent-conditioned adaptive policies can control robots across changing dynamics, but their learned latents remain internal representations of the policy rather than physical models that can be inspected, rolled out, or used by other...
Robots are beginning to act on world-model predictions, yet reliability is still expressed through instantaneous, model-internal signals. DreamLedger instead treats reliability as a persistent deployment object: an execution-settled credit...
The Agent Payments Protocol (AP2), introduced by Google, enables large language model (LLM)-driven shopping agents to authorize and execute payments on behalf of users. Its signed Checkout and Payment Mandates protect the integrity of...
S M Maksudul Alam, Vivek Jain, Zhaowei Tan, Srikanth V. Krishnamurthy et al.
cs.NI
How can we actively search and identify live C2 servers of botnets at scale? The scalability requirement introduces the need to utilize resources efficiently in terms of computation and number of probing packets. We propose BotScan, an...
Effective color contrast in visual design is essential for content accessibility. While existing tools can identify contrast issues, they often operate in isolation from design workflows or are used as an afterthought. We present...
Archit Bhatnagar, Zhenning Yang, Sarah McClure, Yiming Qiu et al.
cs.SE, cs.AI, cs.DC
DevOps programming (e.g., using CLI/API scripts or IaC frameworks) is key to cloud infrastructure management. Unlike traditional programming tasks, DevOps program testing needs provisioning and execution against actual cloud resources...
Training large-scale AI models often outgrows a single data center, demanding sharded, multi-cluster, and decentralized training. However, the huge space of resource allocations makes exhaustive benchmarking and manual tuning impractical...
Embodied Agents System (EAS) are increasingly deployed in open-world physical domains, where reliability directly dictates deployment quality and human-agent trust. However, existing evaluations rely on outcome-centric metrics as success...
While reinforcement learning (RL) allows generalist robot policies to continually improve during deployment, the large model size of modern generalist policies, such as VLAs, poses a fundamental obstacle to effective RL improvement. In...
Unmanned aerial vehicle (UAV)-mounted 5G New Radio base stations (gNBs) can augment terrestrial networks with an on-demand, repositionable Frequency Range 2 (FR2) capacity layer. This flexibility, however, couples the physical network...
On a 3D-printed tactile map, a building felt under the finger is an anonymous shape: touch alone cannot tell which footprint is which, and a spoken description cannot reliably point to one shape at one place. We present a web-based tool...
Storage-backed inference is easy to overclaim: process RSS excludes charged page cache, process-local device readings exclude board-wide use, and successful generation does not establish correct asynchronous reuse. We present a falsifiable...
Psychological research on emotion dynamics has established that human affect is a continuous, evolving process: emotions rise, decay, and transition within seconds. Current emotional text-to-speech (TTS) systems, however, condition on a...
This paper evaluates quantum and AI-accelerated risks to TLS 1.3 cryptographic dependencies under an evidence-tiered model, distinguishing mechanism-backed threats (Shor algorithm against RSA and ECC) from contingency-backed risks to...
Existing Rowhammer-based inference-time backdoor attacks design their bit-flip strategies purely at the algorithmic level, without accounting for the bit-flips that the underlying DRAM hardware will actually produce. This disconnection...
The Shopify marketplace hosts more than 16,000 active third-party applications, serving 2.7 million active merchant stores generating an estimated 706 billion in annual sales, yet little empirical evidence exists on its structure and...
Mehrdad Rostamzadeh, Sidhant Narula, Mohammad Ghasemigol, Daniel Takabi
cs.CR, cs.AI
The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness introduces a severe server-side threat we term TrustShift: a compromised MCP server behaves...
Audio-visual speech enhancement (AVSE) uses visual-speech cues from a target speaker to recover that speaker's speech from noisy or overlapping speech. Many widely used protocols construct mixed signals from separately recorded audio...
Recent large audio language models (LALMs) have achieved impressive progress in audio understanding. However, existing evaluations remain largely constrained to English and narrow audio domains. Prior benchmarks typically focus on a single...
We propose and demonstrate SPIDER4TianoCore, a packaged Python command-line tool that provides integration-stage patch-status evidence for the TianoCore/UEFI firmware supply chain. Given an upstream pre-patch and post-patch pair and...
Laura Baird, Neelesh Reddybattula, Nazanin Siavash, Terrance E. Boult et al.
cs.SE
We propose enhancing the bug report templates in the GitHub Issues issue tracking system used by the TianoCore open-source community with the aim of improving the bug triage and resolution process. We analyze the bug repository data and...
Transformed by digitization, everyday activities-paying bills, shopping, managing transportation-increasingly require older adults to navigate digital systems. To accomplish these digital activities of daily living (DADLs), older adults...
Perimeter-based security appliances, such as firewalls or Intrusion Detection Systems, are ineffective against modern attacks that use pivoting, wherein attackers "pivot" traffic through compromised hosts to gain access to additional...
Inter-annotator disagreement in real-time affect annotation is widely treated as stochastic noise. We challenge this view by modelling ordinal annotation as an implicit game-theoretic coordination process against an internalised population...
In CLAUDE.md, "do not" is a natural-language instruction that the model interprets. Claude Code's deny is a built-in control that blocks an action before the agent can take it. Both can express the same security goal, but they control the...
Mustafa Umut Ozbek, Taiwo Ojo, Pooria Madani, Khalil El-Khatib et al.
cs.CR, cs.LG
Machine-learning-based anomaly detection is increasingly used in industrial control systems (ICS), yet most studies assume that detector training data is trustworthy. In practice, training data may be corrupted through compromised logs...
Finding people from a natural-language description (``ML engineers transitioning to research roles in biotech'') is increasingly delegated to LLM agents and framed as information retrieval. We argue that it is fundamentally a requirements...
Aligning deployed language models requires knowing when their outputs can be trusted, yet on-device models now ship to hundreds of millions of devices with no server-side moderation, and the configuration developers can actually deploy is...
Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning. This supervises which motor command was demonstrated while leaving implicit the...
Space robots operate in extreme environments where hardware degradation can critically compromise traditional control strategies. While continual reinforcement learning offers a promising mechanism for online adaptation, it inherently...
Recent audio generation models can synthesize high-fidelity speech, environmental sound, singing voice, and music, creating new risks for multimedia trust. Existing audio deepfake detection (ADD) benchmarks remain predominantly...
Esther Bosch, Rebecca Kruschka, David Schackmann, Stephanie Hoyer et al.
cs.HC
Increasing automation in rail transport shifts the train driver's role from active control to prolonged supervisory monitoring. This creates conditions for mental fatigue (MF) and reduced vigilance. Despite the safety relevance of this...
Evangelos Lempesis, Fabio Palmese, Hamed Haddadi, Anna Maria Mandalari
cs.NI, cs.CR
The massive adoption of Internet of Things (IoT) devices across critical domains such as healthcare, smart cities, industrial automation, and critical infrastructure introduces significant cybersecurity and regulatory challenges. Current...
Multimodal Large Language Models (MLLMs) have demonstrated great performance, yet they often suffer from severe modality misalignment when confronted with densely constrained spaces for interior design. Due to the loss of high-frequency...
Animatable 3D Gaussian head avatars offer high-fidelity and flexible facial rendering, but typically require substantial storage and transmission costs for numerous Gaussian primitives. Existing Gaussian head avatar methods overlook the...
With the rapid progress of diffusion models and large-scale video generation, generative world models are increasingly expected to replace traditional simulators, including physics engines, game engines, and reinforcement-learning...
Xinyuan Liu, Eren Sadikoglu, Riana Chatterjee, Ransalu Senanayake
cs.RO, cs.AI, cs.MA
Agentic AI frameworks interpret open-ended task goals and decompose them into multi-step plans. Richer information about embodiment-specific capabilities, physical preconditions, and cross-robot coordination improves grounding, but does...
Creating re-topologized 3D facial meshes is essential for high-quality facial animation but remains labor-intensive and time-consuming. This dissertation explores more efficient approaches for capturing production-ready facial meshes...
Alberick Euraste Djire, Iyiola E. Olatunji, Melissa Tessa, Earl T. Barr et al.
cs.SE, cs.AI
LLMs are increasingly used for code generation, yet they frequently hallucinate non-existent software packages, creating exploitable entry points into the software supply chain. We make four contributions to this problem. First, we show...
Modern text-to-SQL systems have become increasingly elaborate, relying on schema-linking modules, retrieval-augmented prompting, candidate generation, and multi-stage refinement pipelines. While effective, these additions introduce...
Diffusion language models can generate many tokens in parallel, but they still require repeated denoising steps during inference. This makes generation costly, especially when the model continues to recompute tokens that are already...
Public blockchains expose the complete transaction graph, and the privacy protocols deployed to obscure it rely almost exclusively on elliptic-curve cryptography, whose discrete-logarithm foundations fall to Shor's algorithm. Because...
As the use of Artificial Intelligence (AI) and Large Language Models (LLMs) is becoming common in everyday applications, their ability to interpret natural language has increased significantly. An emerging application of AI is integration...
Deploying large language models on edge devices is increasingly limited by a widening gap between model size and available memory. Existing approaches such as quantization, smaller models, and offloading can raise the effective memory...
Florian Rottach, Sebastian Schieferdecker, William Rudman, Randall Balestriero et al.
cs.LG, cs.AI
Despite recent advances in molecular foundation models, several limitations remain, such as chemically invalid augmentations, modality collapse, and incomplete representation of biochemical environments. To address these challenges, we...
Digital systems increasingly mediate emotional support, yet their interactions often remain culturally generic. Accordingly, we examine how a poetic tradition can be operationalized as a culturally grounded interactive medium and how...
Iyiola E. Olatunji, Alberick Euraste Djire, Jacques Klein, Tegawendé F. Bissyandé
cs.SE, cs.AI
Copying a function from a chat window into an editor takes less than a second. For many uses of AI coding tools, that speed is the point; in settings such as programming education, code review, and security-sensitive development, it can...
Recent vision-language models (VLMs) show strong capabilities in robotic perception and spatial reasoning, yet their ability to reason about complex mechanical assemblies remains underexplored. We introduce OmniCAD, a large-scale benchmark...
Q-learning with linear function approximation can be unstable because an arbitrary approximation architecture need not preserve the Bellman contraction. We develop a stable infinite-dimensional linear function approximation framework for...
Davide Bargellini, Alex Pasquali, Andrea Govoni, Riccardo Zanella et al.
cs.RO, eess.SY
Transferring reinforcement learning policies from simulation to Real-World robots remains a major challenge, particularly when dealing with low-level torque control, where even small modelling inaccuracies can lead to unstable or unsafe...
Robot policies receive heterogeneous observations at each decision step, yet sequence models differ in how they organize these inputs over time. We introduce WorldToken, a time-first policy instantiation that fuses multiview images...
In today's digital landscape, high-efficiency video coding (H.265/HEVC) has emerged as the most widely used video coding standard, employing selective encryption schemes to protect the privacy of video content while maintaining efficient...
Kishu Gupta, Deepika Saxena, Ashutosh Kumar Singh, Chung-Nan Lee
cs.CR, cs.LG
The significant upsurge in vehicle traffic presents a considerable challenge in the pursuit of smart mobilization and transportation (SMT) worldwide. Current approaches primarily focus on vehicular traffic management through congestion...
Decentralized federated learning (DFL) is a promising paradigm for autonomous nodes to collaboratively train AI models without relying on a central server. However, existing DFL solutions do not guarantee global model consistency, a...
Evaluating Large Language Model (LLM) code generation quality requires examining not just whether the generated code is correct, but whether it is maintainable, efficient, and stylistically sound, all of which are qualities of direct...
Private bidding is a process in which participants submit sealed bids, ensuring that their content remains hidden from other bidders during the bidding window. This is essential in competitive environments to ensure a fair and independent...
Rabia Hameed, Jihad Younis, Maryam Salem Alatawi, Tahreem Farman et al.
cs.GR
Shape-controlled curve design plays a fundamental role in computer-aided geometric design, computer graphics, and engineering applications. In this paper, we present a novel three-parameter 9-point binary approximating subdivision scheme...
Long jumpers with below the knee amputation (BKA) that take off from their running-specific prosthesis (RSP) improved performances significantly over the last years. The long jump biomechanics differs compared to athletes without BKA and...
GPU scale-up domains have become the building block of modern machine learning infrastructure, and their design follows a clear trajectory of exponential growth in both interconnect bandwidth and domain size. This paper argues that these...
Autonomous underwater vehicles (AUVs) rely on the fusion of inertial navigation systems (INS) and Doppler velocity logs (DVL) for accurate navigation. Before deployment, this fusion requires a DVL initialization pipeline consisting of two...
Workers are increasingly asked to adopt AI systems to assist their work, yet are rarely given a voice in defining what meaningful AI augmentation should look like or how to evaluate for it. In this paper, we propose worker-driven AI...
Large language models (LLMs) rely on tool calling as a fundamental agent capability, enabling them to invoke external systems and complete tasks beyond text generation. However, clean end-to-end (E2E) success cannot identify where a...
Forecasting dexterous hand motions from egocentric observations is fundamental to intelligent interactive systems. Existing VLM-based methods typically map observations directly to future motions, overlooking the underlying manipulation...
AI chatbots can help people write faster, but they can also encourage overreliance by making it easy to turn minimal input into usable text. We study turn-level design friction: intentional constraints added to each chatbot exchange that...
Pablo A. Fonseca, Raquel Rodríguez-Carvajal, Rafael A. Calvo
cs.HC, cs.CL, cs.CY
Large language models are increasingly consulted at moments of distress, yet single-turn benchmarks neither test sustained exchanges nor distinguish between users. We built a personality-aware evaluation in which four widely used models...
Decoding perceived speech from non-invasive brain recordings has garnered significant attention in recent years due to its wide range of potential applications. However, existing methods face considerable challenges in cross-subject...
Large language models (LLMs) have shown substantial promise for high-level synthesis (HLS) code generation, but most existing approaches validate only simulation or synthesis results. Because of timing and place-and-route constraints, HLS...
Regulation (EU) 2024/886 obliges European payment service providers to settle euro credit transfers in under ten seconds, around the clock. This removes both the overnight batch window in which anti-money-laundering (AML) analytics...
Current code clone detection (CCD) methods rely on fixed, language-specific graph representations like abstract syntax trees (ASTs) or program dependency graphs (PDGs). Because functionally identical code fragments can yield wildly...
We introduce MCSI, a two message key exchange we design over the CSIDH class group action, in which each party sends its ephemeral public element under an authenticated encryption keyed by the value the two static keys determine. The...
Speech-guided referring video object segmentation aims to recover the mask tracks of objects specified by a spoken motion description. Here, speech carries a linguistic instruction rather than acoustic evidence from a sounding object, so a...
Emotion-aware artistic image generation requires a model to satisfy semantic content, artistic style, and target emotion simultaneously. The key challenge is that artistic captions conflate these axes into underspecified free-form text...
Abstract specifications of concurrent objects determine which values operations may return, but they also implicitly constrain which information operations may know, for example the arguments of other operations that do not affect their...
Virtual Payment Channels (VPCs) enable efficient off-chain transactions in Payment Channel Networks (PCNs), but their performance depends on selecting high-quality underlying paths. Existing approaches either rely on simplified metrics or...
Pathological and more broadly non-canonical speech present significant challenges for automatic phoneme recognition due to systematic deviations from canonical pronunciation and limited availability of labeled clinical speech data...
Knowledge tracing models usually use response correctness as a central observation for estimating students' latent knowledge states. However, the same correct or incorrect response may arise from different behavioral contexts, such as...
Philipp Steigerwald, Nico Bienlein, Jennifer Burghardt, Mara Stieler et al.
cs.HC, cs.CL
Rising global demand for mental health support creates significant service delivery challenges, with asynchronous email counselling serving as a crucial low-threshold channel for accessing care. This paper presents CAIA, a co-designed...
Yize Li, Ningyuan Yang, Sile Yin, Sindhuja Thogarrati et al.
cs.SD, cs.LG, eess.AS
Large audio-language models (LALMs) have shown promising progress in understanding speech, music, and general sound events, yet their ability to reason about how audio signals are degraded remains underexplored. Existing benchmarks...
Hermann Yepdjio Nkouanga, Minwei Luo, Maggie Wigness, Suresh Singh
eess.AS, cs.CL
While cascaded multi-talker ASR (MT-ASR) leverages state-of-the-art foundation models, its performance is often capped by speaker leakage during separation. Prior correction strategies primarily focus on lexical re-labeling for speaker...
This paper addresses the issue of self-intersecting trajectories (in phase space) in industrial reduced-order modeling and proposes the Latent-Augmented Neural Ordinary Differential Equations (LA-NODEs) framework. From the perspective of...
Enterprise repositories are large, heteroge- neous, and continuously updated, making re- trieval difficult when efficient access, source- faithful evidence, and cross-query adaptation must be supported together. Enterprise mem- ory extends...
Large Language Models (LLMs) achieve strong reasoning performance, but their robustness to realistic lexical corruption remains poorly understood. We evaluate four open-weight instruction-tuned models and frontier models across four...
Language models are usually judged by a single accuracy score, which does not reveal how their performance degrades as inputs are perturbed. We present a graded, multi-family, failure-aware framework for stress-testing reasoning models. It...
Modern language models and agents increasingly require persistent memory for complete codebases, long interaction histories, and heterogeneous enterprise records. The key challenge is to keep hundreds of millions of tokens searchable while...
Biomedical multi-hop question answering (QA) requires models to connect evidence across intermediate entities such as diseases, drugs, proteins, and phenotypes. Existing agents typically rely on static retrieval workflows or coarse-grained...
S. M. Suhail Hussain, Arman Ahmad, Mohammad Tayyab, Shaik Mullapathi Farooq
cs.CR, eess.SY
Securing IEC 61869-9 Sampled Values (SV) is challenging because process-bus communication must satisfy stringent real-time constraints while supporting standardized high-rate publication profiles. This paper presents an experimentally...
Language-queried audio source separation (LASS) aims to extract target sources from audio mixtures according to natural language descriptions, offering a flexible and scalable interface for audio source separation. However, most existing...
Construction robotics and automation offer promising means of improving productivity, alleviating workforce shortages, and reducing workers' exposure to physically demanding tasks. However, reliable contact-rich robotic assembly remains...
Verification and validation (V&V) are crucial methods for evaluating the requirements and specifications of dynamical models that fulfill their intended purposes. Parallel Discrete EVent System Specification (PDEVS) is a system-theoretic...
Minimally invasive procedures performed within confined anatomical spaces depend on continuous endoscopic visualization. Current robotic endoscope systems can stabilize or reposition an endoscope, but they do not possess relevant context...
Daniel Rodriguez-Cardenas, David Nader Palacio, Anna Schmedding, Yiyang Lu et al.
cs.CR, cs.AI
Modern software systems require earlier and more scalable vulnerability severity assessment to reduce exposure to high-impact security flaws. Security analysts typically assign CVSS scores, but this manual triage does not scale with the...
Hridya Dhulipala, Rajesh Ombase, Michael Wang, Tien N. Nguyen
cs.SE, cs.CL, cs.IR
Retrieval-Augmented Generation (RAG) enables large language models to incorporate external knowledge during generation, improving factual grounding and domain adaptability. However, existing RAG pipelines assume that evidence retrieved...
Tool-using agents must decide when to stop. Existing systems already gate terminal success, certify execution traces, or enforce runtime polici es, but do not test this particular receipt-, scope-, and closed-replay design at the COMPLETE...
Adversaries now move faster than manual response processes can absorb. The average eCrime breakout time, that is, the interval between initial access and the first lateral movement to another host, fell to 29 minutes in 2025, a 65%...
Fenghao Lei, Zhixiong Huang, Long Yang, Jiabao Chen et al.
cs.RO, cs.AI, cs.CV, cs.LG
World-Action Models (WAMs) build robot control on video-generation backbones, which jointly predict dense future visual trajectories and robot actions. We argue that video generation is an unnecessary intermediate objective for...
In sound mixtures of more than one musical source, different vibrato patterns act as a cue that multiple sources are present for both human listeners and source separation algorithms. Matching the vibrato patterns of the signals in the...
Modern scientific facilities and instruments generate datasets at scales that are difficult for individual researchers to discover, access, and explore. Although many datasets are publicly available, using them often requires familiarity...
Robot foundation models have substantially advanced perception and control, but natural human-robot collaboration requires more than executing isolated commands. A robot must recognize ambiguity, maintain context across turns, communicate...
Stable quadrupedal locomotion on sparse terrain requires selecting state-relevant terrain evidence for precise foot placement. Model-based foothold planners provide precise foothold selection but rely heavily on explicit model assumptions...
This paper presents a conceptual design for a proactive human assisting robot system capable of recognizing human activities and responding proactively. The system leverages contextual human activity recognition to interpret human actions...
Carousel interfaces are widely used in modern recommendation systems. Unlike traditional interfaces that present a single ranked list, carousels simultaneously present several ranked lists to the user, as horizontally swipeable rows...
Commit messages help developers understand code changes, support collaboration, and improve long-term maintenance. However, the use of issue information alone as the external context for LLM-based CMG has not been systematically studied...
We show that the CRT-FHE scheme of Pradhan et al. is insecure for laws within its assumed error distribution range. The secret key follows from the public key by a single ring inversion whenever the public multiplier is a unit. The...
We present an autonomous cryptanalysis workflow in which agents generate, test, and refine hypotheses before human review. The autonomous stage returns reproducible candidates with exact witnesses, controls, code, and run records. A...
CWE labels in the National Vulnerability Database (NVD) are widely treated as ground truth for vulnerability search, scanner evaluation, benchmark construction, learning-based security tools, and vulnerability prioritization. Yet their...
Humans have multiple levels of temporal abstractions on daily interaction and thinking, such as concept perception and strategic planning. Inspired by this nature, we propose a two-level hierarchical reinforcement learning (RL) framework...
This paper presents an ontology-supported approach to the management of design parameters in engineering. This approach aims specifically at enabling Change Impact Analysis through Requirements Traceability and acquainted expert knowledge...
This paper presents an ontology-based approach to the supply chain-aware transformation of functional and environmental load requirements given by so-called Mission Profiles (MPs). The approach aims at improving the efficiency of the...
Formal verification is increasingly critical for blockchain consensus protocols, where subtle bugs can cause irreversible financial loss and network failure. Yet the literature on verification methods is fragmented across tools, protocol...
Latency-sensitive edge AI services must balance strict deadlines, output quality, and limited compute and energy budgets. However, static CPU provisioning wastes resources because inference cost varies substantially across inputs, model...
Human tactile perception relies on complex multisensory cues. Yet the relationship between tactile signals and perceptual representations remains poorly understood, limiting the integration of touch in digital environments and human-like...
Deep learning has achieved strong performance in encrypted traffic classification (ETC), yet its computational cost limits deployment on resource-constrained network devices such as routers and middleboxes. Existing compression methods...
In Industrial Internet of Things systems, learning-enabled Digital Twins (DTs) support remote monitoring by using data reported by distributed devices to maintain digital representations of physical processes. When uplink resources are...
Bitstream-corrupted Harsh Visual Understanding (BcHVU) aims to understand harshly degraded videos originally decoded from a severely corrupted bitstream in real-world multimedia communication. The ill-posed nature of BcHVU poses a major...
This paper presents the design and implementation of a multi-GPU concurrent queue system using NVIDIA's NVSHMEM. The Bellman-Ford algorithm is used as a case study to evaluate the performance of the proposed concurrent FIFO queue, with...
Bowen Shi, Sreeram Venkat, Stefan Henneking, Omar Ghattas
cs.DC, math.NA, physics.geo-ph
Data-driven methods for earthquake and tsunami early warning rely on large ensembles of rupture scenarios and their resulting waveforms, but generating such datasets with repeated high-fidelity seismic and tsunami simulations is...
We introduce adoption telemetry: a method for measuring enterprise AI adoption by computing change-management stage-progression directly from production usage signals. We contribute (1) a framework unifying pre-deployment evaluation gates...
Language grounding increasingly involves non-text observations whose structure is not naturally expressed as words or objects. We study this problem for physiological time series in non-contact blood pressure (BP) estimation: remote...
Vitor Miguel Xavier Peres, Lara Volpato, Gabriel Ferri Scnheider, Soraia Raupp Musse
cs.CV, cs.GR
Generating expressive facial behavior in virtual humans (VHs) remains a central challenge in affective computing and character animation. This paper presents a novel approach based on Conditional Variational Autoencoders (CVAEs), trained...
This paper describes the development of software drivers that enable precise timing applications with the low-cost HackRF One software-defined radio (SDR). The original firmware was extended with timing functions for synchronized sampling...
LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into fixed memory representations...
Perceived safety in streetscapes depends on where people look, yet how gaze relates to visual cues of urban disorder remains poorly understood. Prior work treats safety as an image-level label, offering little insight into how attention to...
This article presents a novel 3D reconstruction and mapping of the interior of the International Space Station (ISS) using 3D Gaussian Splatting (3DGS). Using existing grayscale images from the Astrobee free-flying robot dataset, we...
Phillip Long, Hao-Wen Dong, Julian McAuley, Zachary Novack
cs.SD, cs.LG, eess.AS
Current work in modeling symbolic music primarily relies on representations extracted from MIDI-like data. While such formats allow for modeling symbolic music as sequences of notes, they omit the large space of symbolic annotations common...
Anuj Kumar, Heiko Zimmermann, Josiah Bjorgaard, Jacan Chaplais et al.
cs.LG, cs.AI, cs.CE, physics.app-ph, physics.comp-ph
Recent mesh-based simulation advances have, in no small part, relied on neural surrogates of two distinct families: global models that route information through a small set of latent tokens, and local models that perform message passing...
Robotic systems are traditionally designed and deployed in static configurations, with assumptions made at design-time becoming immutable constraints during runtime. This design-then-deploy paradigm produces performant systems under narrow...
Longitudinal electronic health records (EHRs) document patients' sequences of clinical visits over time, preserving the temporal evolution of disease progression and care delivery. However, real longitudinal EHRs are difficult to access...
AI disclosure is increasingly promoted and sometimes required as a route to transparency, accountability, provenance, and trust. Yet disclosure can also expose AI users to suspicion, stigma (e.g., competence penalties), and surveillance...
Large language models (LLMs) are increasingly used to simulate students at different mastery levels. These simulations can generate synthetic training data and stress-test tutoring systems. However, common prompt-based approaches leave the...
Marek Mateusz Kowalski, Joshua Fonseca Rivera, Uzay Macar, David Demitri Africa
cs.AI, cs.CL
Safe deployment of increasingly capable models will likely come to rely on latent-space monitoring as a complement to behavioral evaluations, especially when evaluation-aware models exhibit scheming or deception. However, if models can...
When discrete-time optimizers operate at the edge of stability, they exhibit near-two-periodic behavior. These oscillatory dynamics are reminiscent of conservative systems, such as the dynamics generated by symplectic integrators. However...
Modern cyber–physical, Internet-of-Things (IoT), wearable, and edge systems increasingly require trust in three distinct entities: the human requesting access, the physical device executing the computation, and the hardware function that...
Christopher R. Hayner, Griffin J. Norris, Fabio Spada, Samet Uzun et al.
cs.RO, math.OC
Trajectory optimization computes dynamically feasible motions that enable autonomous systems to accomplish complex tasks while satisfying operational and environmental constraints. This tutorial presents OpenSCvx, an open-source Python...
Black-box VR and 3D applications are difficult to regression test because observable failures depend on where a tester moves, what objects are visible, and which views are captured. Manual exploratory testing can find such failures, but...
Ruan Rithelle Chagas de Faria Carminati, Giovanni Braglia, Luigi Biagiotti, Ronnier Frates Rohrich et al.
cs.RO
This paper investigates wearable-based recognition of human activities and gestures to support Human-Robot Interaction (HRI) in object-handover and assembly-like scenarios. Electromyography (EMG) and Inertial Measurement Unit (IMU) signals...
TEE-shielded inference keeps sensitive state in a trusted execution environment (TEE) while offloading linear algebra to an untrusted accelerator. Wang et al., in Game of Arrows (USENIX Security 2025), showed that five widely adopted...
AI is increasingly lowering the barrier to data analysis and creating visualization scripts. However, a key obstacle in AI-assisted visualization is that certain data issues can lead to visualizations that are plausible, but misrepresent...
Voice has been proposed as a low-cost screening signal for chronic obstructive pulmonary disease (COPD). COPD is strongly age-associated and voice changes with age, thus such results admit a trivial alternative explanation. We re-evaluate...
Target Wake Time (TWT), introduced in IEEE 802.11ax, lets an access point schedule exactly when each station wakes, transmits, and dozes. Existing TWT schedulers optimize energy or throughput, treating information freshness at best as a...
Contact-rich robotic manipulation requires an accurate model of the kinematic relationship between a robot's joints and the task features it senses. This relationship is rarely known exactly: it changes with each tool the robot picks up...
Consider a typical test of a robot system: one observes a sequence of outcomes concerning some aspect of interest (crash or no crash, tracking error, time to completion), and reports a mean (crash risk, average error, mean time to...
The rapid development of artificial intelligence, including agents and deepfake techniques, has accelerated phishing attacks and lowered the threshold for attackers. Modern phishing attacks now blend multiple tactics, including social...
Jacek Dąbrowski, Manjeshwar Aniruddh Mallya, Alessio Ferrari, Mohammad Amin Zadenoori et al.
cs.SE
Requirements-related information is scattered across heterogeneous artefacts such as user feedback, developer discussions, and software repositories, making the extraction of actionable requirements knowledge labour-intensive and hard to...
Formal verification offers the strongest assurance available for software, and verification-aware languages have made its automation real. Yet the benefits reach few mainstream developers, most of whose languages have no verification...
For sixty years, machine verification has been a major cost overhead, affordable only for exceptional artifacts. Here we report that generative AI inverts this relationship: at AI speed, machine verification is not only economical but...
Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko, Nikolay Karpov et al.
eess.AS, cs.AI, cs.CL, cs.LG, cs.SD
Contextualization is essential for production automatic speech recognition (ASR) systems, where user-provided phrases must be recognized accurately under strict latency constraints. Although many context-biasing methods improve recognition...
Natural-language workflows offer a software-like interface for agents: domain experts can write reusable procedures, and agents can execute them as instructions. This promise is not yet reliable. Workflow descriptions often leave data...
Studies of digital behavior often align users at moments they choose, such as opening an AI assistant, clicking a recommendation, or visiting a product page, and interpret higher activity afterward as an event effect. We show how this...
People's health and tracking goals frequently change, but most personal informatics systems struggle to adapt, leading people to abandon their data and start over. We propose goal-directed framing, an approach that repositions goals within...
Prompt injection is listed as the #1 threat to AI agents. When an agent accesses external data from websites, files, or emails, an attacker may inject a prompt into the data, saying, "Ignore all prior instructions and perform <an...
Persistent memory makes false information durable: once a false statement is stored, it can be retrieved into future sessions that match it. We measure the cost of this failure mode using plainly worded false assertions generated in a...
Natalia Amat-Lefort, Mert Yazan, Amanda Cercas Curry, Flor Miriam Plaza-del-Arco
cs.HC
Trust in AI for emotional support is not universal; it is shaped by who users are, where they come from, and what they value. Yet research in this area lacks validated psychometric instruments for assessing user perceptions in affective AI...
Workplace surveillance is used by organizations to protect corporate assets and monitor employee productivity. This research presents two central arguments on workplace surveillance: although surveillance serves legitimate organizational...
Nagashree K. S. Rao, Shrishti Saha Shetu, Mohamed Elminshawi, Emanuël A. P. Habets et al.
eess.AS
Diffusion-based models are emerging in the speech enhancement domain and are achieving state-of-the-art performance across various benchmark datasets. A major downside of diffusion models is that data generation requires many evaluations...
Automatic speech quality assessment aims to predict Mean Opinion Scores (MOS) consistent with human subjective perception and is essential for evaluating speech generation, enhancement, and communication systems. For speech signals...
Karthik Venkatasubba, Shivendra Deshpande, Shivram S, Jyothi Vedurada
cs.DC, cs.DB
Modern Approximate Nearest Neighbour Search (ANNS) applications operate over continuously evolving vector collections and require graph indexes that sustain high-throughput searches while incorporating insertions and deletions with high...
High-performance GPU kernels underpin modern deep learning and scientific computing. As workloads become increasingly diverse and GPU hardware evolves rapidly, developing efficient methods for automated GPU kernel generation and...
Shrishti Saha Shetu, Jose Miguel Martinez Aponte, Nagashree K. S. Rao, Sharvin Vittappan et al.
eess.AS
Speech enhancement on embedded digital signal processors (DSPs) imposes strict constraints on memory footprint, computational complexity, latency, and support for integer operations. Although recent DNN-based approaches have addressed...
Mauro Bianco, Till Ehrengruber, Enrique González Paredes, Andreas Jocksch et al.
cs.DC
The transition of Earth-system models to exascale is often hindered by rigid, monolithic Fortran codebases and maintenance-heavy compiler directives. While high-level DSLs offer a solution, they frequently fail due to cumbersome...
Visual world-model agents such as DreamerV3 act through a recurrent latent state rather than a single observation, which weakens frame-wise observation attacks and makes their perturbations vary sharply over time under a strict per-frame...
Satellites are becoming programmable computing platforms capable of running increasingly demanding AI workloads. This shift raises a systems problem: how can AI services remain deployable, manageable, and recoverable after launch when...
Network slicing is a foundational capability of Fifth Generation (5G)-Advanced and emerging Sixth Generation (6G) networks, yet practical support for seamless runtime slice transitions remains limited. Standard cloud-native 5G...
Guangyuan Dong, Chuang Liu, Yangchen Zeng, Haoyu Wang et al.
cs.MM, cs.AI, cs.CV, cs.GR
Multimodal information systems increasingly route generated visual content back through the same vision-language index that informed its production, so the output must remain retrievable by the queries it was meant to serve. When the scene...
Vector graphics are prized for their resolution independence, compact storage, and direct editability, making differentiable optimization of their parametric primitives an attractive goal. Yet classical rasterization is discontinuous with...
3D Gaussian Splatting has achieved remarkable success in novel view synthesis. However, extracting high-fidelity surfaces directly from 3DGS remains challenging due to its discrete and unstructured nature. Existing 3DGS-based...
Rotational degrees of freedom in Extended Position-Based Dynamics (XPBD) require computations on the nonlinear manifold of 3D rotations. We show that Lie theory provides a clean, unified framework for expressing rotations, constraints...