# Research Papers — 2026-02 · bundle page 14 of 210 > Full-text markdown of papers #651–700 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-02/page/14 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/13.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/15.md) ### Generative Active Testing: Efficient LLM Evaluation via Proxy Task Adaptation Authors: Aashish Anantha Ramakrishnan, Ardavan Saeedi, Hamid Reza Hassanzadeh, Fazlolah Mohaghegh, Dongwon Lee Published: 2026-02-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19264v1 With the widespread adoption of pre-trained Large Language Models (LLM), there exists a high demand for task-specific test sets to benchmark their performance in domains such as healthcare and biomedicine. However, the cost of labeling test samples while developing new benchmarks poses a significant challenge, especially when expert annotators are required. Existing frameworks for active sample selection offer limited support for generative Question Answering tasks, where option dynamics can affect model decision boundaries. In this paper, we present Generative Active Testing (GAT), an uncertainty-aware acquisition framework leveraging LLMs as surrogates for informing the sample selection process. Using a novel Statement Adaptation Module, we modify generative tasks into a pseudo-classification format, enabling the capture of sample-level uncertainties across unlabeled candidates. Our zero-shot acquisition functions reduce estimation error by ~40% compared to traditional sampling baselines, offering a scalable solution for cost-effective model benchmarking. --- ### How Motivation Relates to Generative AI Use: A Large-Scale Survey of Mexican High School Students Authors: Echo Zexuan Pan, Danny Glick, Ying Xu Published: 2026-02-26 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.19263v2 This study examined how high school students with different motivational profiles use generative AI tools in math and writing. Through K-means clustering analysis of survey data from 6,793 Mexican high school students, we identified three distinct motivational profiles based on self-concept and perceived subject value. Results revealed distinct domain-specific AI usage patterns across students with different motivational profiles. Our findings challenge one-size-fits-all AI integration approaches and advocate for motivationally-informed educational interventions. --- ### Empirical Characterization of Inference-Time Elicited Probability Transformations in Large Language Models Authors: Mike Farmer, Abhinav Kochar, Yugyung Lee Published: 2026-02-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19262v2 Large language models increasingly rely on inference-time procedures such as chain-of-thought reasoning, self-refinement, retrieval augmentation, and verifier-guided revision, yet the structure of elicited probability transformations under these procedures remains poorly understood. We study externally elicited probability assignments over candidate answers and observe recurring approximate log-ratio relationships: \( \log \tilde q_t(i) = α_t \left( \log q_t(i) + \log b_t(i) \right) + c_t, \) where $q_t$ and $\tilde q_t$ are pre- and post-elicitation probabilities, $b_t$ is an externally constructed evidence signal, and $α_t$ is an empirical descriptor of the prompting configuration. Across 4,975 reasoning problems from GPQA Diamond, TheoremQA, MMLU-Pro, and ARC-Challenge, evaluated on multiple instruction-tuned model families, we observe approximate log-ratio relationships with mean $R^2 \approx 0.76$ over about $1.3 \times 10^5$ candidate-level observations. Coefficients vary across elicitation settings, but qualitatively similar relationships persist across evaluated conditions. Robustness analyses using alternative statistical representations, prompting configurations, held-out evaluation, and token-level log-probabilities suggest that the observed structure is not tied to one prompting procedure or probability estimation method. The main contribution is not the algebraic form itself, which is related to generalized Bayesian updating and probability-transformation frameworks, but the empirical observation that diverse inference-time prompting pipelines repeatedly exhibit reproducible log-ratio structure under controlled conditions. The framework provides a protocol-sensitive perspective for analyzing calibration, evidence amplification, uncertainty propagation, and interaction sensitivity in inference-time LLM pipelines. --- ### Significance-Gain Pair Encoding for LLMs: A Statistical Alternative to Frequency-Based Subword Merging Authors: Azam Nouri Published: 2026-02-26 Categories: cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.19261v1 Subword tokenization is a key design choice for modern language models, including large language models (LLMs), with byte- and character-level BPE serving as a widely used baseline. Standard BPE selects merges by raw pair frequency, which favors compression but can conflate true adjacency cohesion with pairs that are frequent due to high marginal counts. This paper introduces Significance-Gain BPE, a drop-in alternative merge criterion that measures cohesion via a z-statistic under an independence null model and combines it with an explicit compression-aware gain term. Significance-Gain BPE is evaluated on WikiText-103 (raw) character slices using a small causal Transformer language model, reporting both token-dependent perplexity and the tokenizer-invariant metric bits per character (BPC). At a representative operating point, Significance-Gain BPE reduces validation and test perplexity by 13% and 12%, respectively, and improves validation and test BPC by about 0.9 to 1.0%. A vocabulary-size sweep further shows lower BPC in most closest-compression comparisons, suggesting that statistically grounded merge selection can improve predictive efficiency per unit of raw text across a range of compression regimes. --- ### HATL: Hierarchical Adaptive-Transfer Learning Framework for Sign Language Machine Translation Authors: Nada Shahin, Leila Ismail Published: 2026-02-26 Categories: cs.CL, cs.AI, cs.CV, cs.CY, cs.ET arXiv: https://arxiv.org/abs/2603.19260v1 Sign Language Machine Translation (SLMT) aims to bridge communication between Deaf and hearing individuals. However, its progress is constrained by scarce datasets, limited signer diversity, and large domain gaps between sign motion patterns and pretrained representations. Existing transfer learning approaches in SLMT are static and often lead to overfitting. These challenges call for the development of an adaptive framework that preserves pretrained structure while remaining robust across linguistic and signing variations. To fill this void, we propose a Hierarchical Adaptive Transfer Learning (HATL) framework, where pretrained layers are progressively and dynamically unfrozen based on training performance behavior. HATL combines dynamic unfreezing, layer-wise learning rate decay, and stability mechanisms to preserve generic representations while adapting to sign characteristics. We evaluate HATL on Sign2Text and Sign2Gloss2Text translation tasks using a pretrained ST-GCN++ backbone for feature extraction and the Transformer and an adaptive transformer (ADAT)for translation. To ensure robust multilingual generalization, we evaluate the proposed approach across three datasets: RWTH-PHOENIXWeather-2014 (PHOENIX14T), Isharah, and MedASL. Experimental results show that HATL consistently outperforms traditional transfer learning approaches across tasks and models, with ADAT achieving BLEU-4 improvements of 15.0% on PHOENIX14T and Isharah and 37.6% on MedASL. --- ### Breeze Taigi: Benchmarks and Models for Taiwanese Hokkien Speech Recognition and Synthesis Authors: Yu-Siang Lan, Chia-Sheng Liu, Yi-Chang Chen, Po-Chun Hsu, Allyson Chiu, Shun-Wen Lin, Da-shan Shiu, Yuan-Fu Liao Published: 2026-02-26 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.19259v1 Taiwanese Hokkien (Taigi) presents unique opportunities for advancing speech technology methodologies that can generalize to diverse linguistic contexts. We introduce Breeze Taigi, a comprehensive framework centered on standardized benchmarks for evaluating Taigi speech recognition and synthesis systems. Our primary contribution is a reproducible evaluation methodology that leverages parallel Taiwanese Mandarin resources. We provide 30 carefully curated Mandarin-Taigi audio pairs from Taiwan's Executive Yuan public service announcements with normalized ground truth transcriptions. We establish Character Error Rate (CER) as the standard metric and implement normalization procedures to enable fair cross-system comparisons. To demonstrate the benchmark's utility and provide reference implementations, we develop speech recognition and synthesis models through a methodology that leverages existing Taiwanese Mandarin resources and large-scale synthetic data generation. In particular, we fine-tune a Whisper model on approximately 10,000 hours of Taigi synthetic speech data. Our ASR model achieves 30.13% average CER on the benchmark, outperforming existing commercial and research systems. By providing standardized evaluation protocols, diverse training datasets, and open baseline models, we offer a replicable framework with methodologies applicable to various linguistic contexts. --- ### MAPLE: Metadata Augmented Private Language Evolution Authors: Eli Chien, Yuzheng Hu, Ryan McKenna, Shanshan Wu, Zheng Xu, Peter Kairouz Published: 2026-02-26 Categories: cs.CL, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.19258v3 Differentially private (DP) fine-tuning of large language models (LLMs) requires massive compute and full model access, which rules out state-of-the-art proprietary APIs for general users. Generating DP synthetic data offers a practical workaround. This approach also allows for transparent exploratory data analysis and arbitrary reuse across downstream tasks, sidestepping the rigid constraints of a model's parameter space. Private Evolution (PE) provides a promising API-based framework for generating this data, but its success relies heavily on initialization. If the private data distribution falls too far outside the foundation model's pre-training priors -- a common issue in highly specialized domain -- PE struggles to align with the target data. This misalignment causes poor convergence, degraded utility, and wasted API calls. To solve this initialization bottleneck, we introduce Metadata Augmented Private Language Evolution (MAPLE). MAPLE extracts DP tabular metadata and uses in-context learning to firmly ground the initial synthetic distribution in the target domain. Our evaluations on domain-specific text generation tasks show that MAPLE yields a strictly better privacy-utility trade-off, converges significantly faster, and sharply reduces API costs compared to baseline PE methods. --- ### MAPLE: Metadata Augmented Private Language Evolution Authors: Eli Chien, Yuzheng Hu, Ryan McKenna, Shanshan Wu, Zheng Xu, Peter Kairouz Published: 2026-02-26 Categories: cs.CL, cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.19258v2 Differentially private (DP) fine-tuning of large language models (LLMs) requires massive compute and full model access, which rules out state-of-the-art proprietary APIs for general users. Generating DP synthetic data offers a practical workaround. This approach also allows for transparent exploratory data analysis and arbitrary reuse across downstream tasks, sidestepping the rigid constraints of a model's parameter space. Private Evolution (PE) provides a promising API-based framework for generating this data, but its success relies heavily on initialization. If the private data distribution falls too far outside the foundation model's pre-training priors -- a common issue in highly specialized domain -- PE struggles to align with the target data. This misalignment causes poor convergence, degraded utility, and wasted API calls. To solve this initialization bottleneck, we introduce Metadata Augmented Private Language Evolution (MAPLE). MAPLE extracts DP tabular metadata and uses in-context learning to firmly ground the initial synthetic distribution in the target domain. Our evaluations on domain-specific text generation tasks show that MAPLE yields a strictly better privacy-utility trade-off, converges significantly faster, and sharply reduces API costs compared to baseline PE methods. --- ### Constraint-aware Path Planning from Natural Language Instructions Using Large Language Models Authors: Dylan Shim, Minghan Wei Published: 2026-02-26 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.19257v1 Real-world path planning tasks typically involve multiple constraints beyond simple route optimization, such as the number of routes, maximum route length, depot locations, and task-specific requirements. Traditional approaches rely on dedicated formulations and algorithms for each problem variant, making them difficult to scale across diverse scenarios. In this work, we propose a flexible framework that leverages large language models (LLMs) to solve constrained path planning problems directly from natural language input. The core idea is to allow users to describe routing tasks conversationally, while enabling the LLM to interpret and solve the problem through solution verification and iterative refinement. The proposed method consists of two integrated components. For problem types that have been previously formulated and studied, the LLM first matches the input request to a known problem formulation in a library of pre-defined templates. For novel or unseen problem instances, the LLM autonomously infers a problem representation from the natural language description and constructs a suitable formulation in an in-context learning manner. In both cases, an iterative solution generation and verification process guides the LLM toward producing feasible and increasingly optimal solutions. Candidate solutions are compared and refined through multiple rounds of self-correction, inspired by genetic-algorithm-style refinement. We present the design, implementation, and evaluation of this LLM-based framework, demonstrating its capability to handle a variety of constrained path planning problems. This method provides a scalable and generalizable approach for solving real-world routing tasks with minimal human intervention, while enabling flexible problem specification through natural language. --- ### NextMem: Towards Latent Factual Memory for LLM-based Agents Authors: Zeyu Zhang, Rui Li, Xiaoyan Zhao, Yang Zhang, Wenjie Wang, Xu Chen, Tat-Seng Chua Published: 2026-02-26 Categories: cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.15634v1 Memory is critical for LLM-based agents to preserve past observations for future decision-making, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations. Textual methods impose heavy context and indexing burdens, while parametric methods suffer from catastrophic forgetting and high costs. To address these challenges, we introduce NextMem, a latent factual memory framework that utilizes an autoregressive autoencoder to efficiently construct latent memory while ensuring accurate reconstruction. For better optimization, we propose a two-stage training process, including autoregressive reconstruction alignment and progressive latent substitution. We also incorporate quantization to reduce storage overhead. Extensive experiments demonstrate that NextMem achieves superior performance, and excels in retrieval, robustness, and extensibility properties. We release our code and model checkpoints at https://github.com/nuster1128/NextMem. --- ### Quality Assessment of Public Summary of Training Content for GPAI models required by AI Act Article 53(1)(d) Authors: Dick A. H. Blankvoort, Harshvardhan J. Pandit, Maximilian Gahntz Published: 2026-02-26 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.13270v1 The AI Act's Article 53(1)(d) requires providers of general-purpose AI (GPAI) models to publish a sufficiently detailed public summary about the content used for training based on a template provided by the AI Office. The stated goal of this obligation is to increase transparency regarding the data used for training GPAI models, and to enable relevant stakeholders to exercise their rights, especially regarding IP, copyright, and data protection. This paper provides a quality assessment framework to assess the public summary across two key dimensions: \textit{transparency} regarding information being provided in a clear, comprehensive, and sufficiently detailed manner; and \textit{usefulness} regarding whether the provision of the document and the contents can be effectively utilised by stakeholders to carry out rights related actions. This framework enables identification of key issues in public summaries, and provides a structured and research-based method to compare practices across public summaries and providers. It also enables authorities such as the AI Office to identify potential issues that could emerge and provides actionable recommendations and guidelines for providers to develop public summaries with high quality. The paper provides an assessment of 5 public summaries published as of 12th January 2026 which were found through an exhaustive search process. To disseminate these findings as a public resource, the paper also describes the development of a website where the assessments, outcomes, and methodologies will be shared. --- ### GenAI Integration into Engineering Education: A Case Study of an Introductory Undergraduate Engineering Course Authors: Kadir Kozan, Ozgur Keles, Sihan Jian, Serkan Ayvaz, Krzysztof Sierszecki, Sewon Joo Published: 2026-02-26 Categories: cs.CY, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.13269v1 GenAI has a potential to enhance the learning and teaching processes in engineering education. For instance, GenAI feedback on students' task performance can be effective depending on when such feedback is provided. However, little is known about how engineering faculty and instructors discover such potential within the scope of their instruction when they try out the technology for the first time. To this end, this study purported to describe an engineering instructor's and seven teaching assistants' initial experiences of integrating GenAI into their undergraduate engineering course and the corresponding changes in students' formative exercise performance. An embedded descriptive single case study design was employed. The corresponding research data included four interviews conducted at the beginning, middle and end of an academic semester, and students' formative exercise performance. Overall, after GenAI integration, students' formative exercise performance increased, and a critical and reflective practice of learning about how to integrate GenAI into instruction provided informative insights. Still, technology integration stayed at the level of replacing other instructional methods or increasing the efficiency of solving coding problems. It turned out to be exciting and surprising for students to be able to use GenAI in course work even though their use of the technology weakened over time. Our findings suggest that engineering teaching staff's initial experimental experiences with GenAI integration can be informative and provide context-specific practical insights. Therefore, it is reasonable for higher education institutions to encourage such experiences especially when there is a lot of unknown regarding an emerging technology. --- ### A Survey on Quantitative Modeling of Trust in Online Social Networks Authors: Wenting Song, K. Suzanne Barber Published: 2026-02-26 Categories: cs.SI, cs.AI, cs.CR, cs.CY, cs.GT arXiv: https://arxiv.org/abs/2603.11054v1 Online social networks facilitate user engagement and information sharing but are also rife with misinformation and deception. Research on trust modeling in online social networks focuses on developing computational models or algorithms to measure trust relationships, assess the reliability of shared content, and detect spam or malicious activities. However, most existing review papers either briefly mention the concept of trust or focus on a single category of trust models. In this paper, we offer a comprehensive categorization and review of state-of-the-art trust models developed for online social networks. First, we explore theories and models related to trust in psychology and identify several factors that influence the formation and evolution of online trust. Next, state-of-the-art trust models are categorized based on their algorithmic foundations. For each category, the modeling mechanisms are investigated, and their unique contributions to quantitative trust modeling are highlighted. Subsequently, we provide an implementation-centric trust modeling handbook, which summarizes available datasets, trust-related features, promising modeling techniques, and feasible application scenarios. Finally, the findings of the literature review are summarized, and unresolved challenges are discussed. --- ### The DMA Streaming Framework: Kernel-Level Buffer Orchestration for High-Performance AI Data Paths Authors: Marco Graziano Published: 2026-02-26 Categories: cs.AR, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2603.10030v2 AI transport libraries move bytes efficiently, but they commonly assume that buffers are already correctly allocated, placed, shared, registered, and safe under completion and teardown pressure. This paper presents dmaplane, a Linux kernel module that makes this missing layer explicit as buffer orchestration. dmaplane exposes a stable kernel UAPI via /dev/dmaplane and composes ring-based command channels, DMA buffer lifecycle management, dma-buf export for cross-device sharing, a kernel-space RDMA engine, NUMA-aware allocation and verification, credit-based flow control, low-overhead observability, and GPU memory integration via PCIe BAR pinning. We evaluate orchestration sensitivity with measurements of NUMA cross-node penalties at DRAM scale, completion-safe flow control under sustained RDMA load, and GPU BAR mapping tiers versus cudaMemcpy. We also demonstrate end-to-end disaggregated inference by transferring KV-cache chunks between two machines using RDMA WRITE WITH IMMEDIATE and reconstructing tensor views on the receiver. RDMA measurements use Soft-RoCE; we distinguish measured results from provider-independent properties by construction. --- ### The AetherFloat Family: Block-Scale-Free Quad-Radix Floating-Point Architectures for AI Accelerators Authors: Keita Morisaki Published: 2026-02-26 Categories: cs.AR, cs.LG arXiv: https://arxiv.org/abs/2603.08741v1 The IEEE 754 floating-point standard is the bedrock of modern computing, but its structural requirements -- a hidden leading bit, Base-2 bit-level normalization, and Sign-Magnitude encoding -- impose significant silicon area and power overhead in massively parallel Neural Processing Units (NPUs). Furthermore, the industry's recent shift to 8-bit formats (e.g., FP8 E4M3, OCP MX formats) has introduced a new hardware penalty: the strict necessity of Block-Scaling (AMAX) logic to prevent out-of-bound Large Language Model (LLM) activations from overflowing and degrading accuracy. The AetherFloat Family is a parameterizable architectural replacement designed from first principles for Hardware/Software Co-Design in AI acceleration. By synthesizing Lexicographic One's Complement Unpacking, Quad-Radix (Base-4) Scaling, and an Explicit Mantissa, AetherFloat achieves zero-cycle native integer comparability, branchless subnormal handling, and a verified 33.17% area, 21.99% total power, and 11.73% critical path delay reduction across the multiply-accumulate (MAC) unit. Instantiated as AetherFloat-8 (AF8), the architecture relies on a purely explicit 3-bit mantissa. Combined with Base-4 scaling, AF8 delivers a substantially wider dynamic range, acting as a ``Block-Scale-Free'' format for inference that circumvents dynamic scaling microarchitecture. Finally, a novel Vector-Shared 32-bit Galois Stochastic Rounding topology bounds precision variance while neutralizing the vanishing gradients that plague legacy formats. While AF16 serves as a near-lossless bfloat16 replacement via post-training quantization, AF8 is designed as a QAT-first inference format: its Block-Scale-Free property eliminates dynamic AMAX hardware at the cost of requiring quantization-aware fine-tuning for deployment. --- ### Quantum Deep Learning: A Comprehensive Review Authors: Yanjun Ji, Zhao-Yun Chen, Marco Roth, David A. Kreplin, Christian Schiffer, Martin King, Oliver Anton, M. Sahnawaz Alam, Markus Krutzik, Dennis Willsch, Ludwig Mathey, Frank K. Wilhelm et al. Published: 2026-02-26 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2603.06644v1 Quantum deep learning (QDL) explores the use of both quantum and quantum-inspired resources to determine when deep learning's core capabilities, such as expressivity, generalization, and scalability, can be enhanced based on specific resource constraints. Distinct from broader quantum machine learning, QDL emphasizes compositional depth at the pipeline level and the integration of quantum or quantum-inspired components within end-to-end workflows. This review provides an operational definition of QDL and introduces a taxonomy comprising four primary paradigms: hybrid quantum-classical models, quantum deep neural networks, quantum algorithms for deep learning primitives, and quantum-inspired classical algorithms. Theoretical principles are connected to advanced architectures, software toolchains, and experimental demonstrations across superconducting, trapped-ion, photonic, semiconductor spin, and neutral-atom systems, as well as quantum annealers. Claims of quantum advantage are critically assessed by distinguishing provable complexity-theoretic separations from empirical observations. The analysis characterizes trade-offs between model expressivity, trainability, and classical simulability, while systematically detailing the bottlenecks imposed by optimization landscapes, input-output access models, and hardware constraints. Applications are surveyed in domains encompassing image classification, natural language processing, scientific discovery, quantum data processing, and quantum optimal control, underscoring fair benchmarking against optimized classical counterparts and a comprehensive assessment of resource requirements. This review serves as a tutorial entry point for graduate students while guiding readers to specialized literature. It concludes with a verification-aware roadmap to transition QDL from near-term demonstrations to scalable and fault-tolerant implementations. --- ### SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aware Residual Test-Time Training Authors: Swamynathan V P Published: 2026-02-26 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.06642v2 Test-Time Training (TTT) language models replace the KV-cache with fast weights updated during inference, achieving O(1) memory but suffering catastrophic failure on exact-recall tasks. Version 1 of this work proposed SR-TTT, which routes high-surprisal tokens to a sparse exact-attention Residual Cache, and reported large Needle-in-a-Haystack gains. We show those gains were evaluation artifacts: the loss and metric read logits at the answer positions rather than one position earlier, training both models to copy an answer already visible in their input (a model trained on retrieval-impossible data reaches 100% accuracy under the flawed metric); additionally, the cache attended non-causally over future tokens, including the answer itself. We release a corrected implementation with startup causality self-tests, then ask whether the SR-TTT hypothesis survives correction. It does not, and the failure decomposes into two independent, separately measured bottlenecks. Storage: surprisal gating is systematically position-biased - the TTT reconstruction loss requires burn-in before a needle becomes relatively surprising, so early-context needles are stored at near-zero rates (0-1% containment at depth 0.1) exactly where long-context memory matters most. Addressing: with storage solved by an oracle and with new trainable read-time projections, per-slot attention supervision raises addressing mass 2.5x (0.06 -> 0.15) yet token accuracy is statistically unchanged, and retrieval extracts only approx. 0.06 nats of the 2.30-nat needle; position-free content addressing cannot resolve ordered slots whose contents are near-interchangeable. Exact match remains 0% in all 2,250 paired trials across all corrected conditions. We retract the claims of v1 and offer the corrected codebase, diagnostic protocol, and negative results as a cautionary reference for surprise-gated memory architectures. --- ### MPBMC: Multi-Property Bounded Model Checking with GNN-guided Clustering Authors: Soumik Guha Roy, Sumana Ghosh, Ansuman Banerjee, Raj Kumar Gajavelly, Sudhakar Surendran Published: 2026-02-26 Categories: cs.LO, cs.AI, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2603.04450v1 Formal verification of designs with multiple properties has been a long-standing challenge for the verification research community. The task of coming up with an effective strategy that can efficiently cluster properties to be solved together has inspired a number of proposals, ranging from structural clustering based on the property cone of influence (COI) to leverage runtime design and verification statistics. In this paper, we present an attempt towards functional clustering of properties utilizing graph neural network (GNN) embeddings for creating effective property clusters. We propose a hybrid approach that can exploit neural functional representations of hardware circuits and runtime design statistics to speed up the performance of Bounded Model Checking (BMC) in the context of multi-property verification (MPV). Our method intelligently groups properties based on their functional embedding and design statistics, resulting in speedup in verification results. Experimental results on the HWMCC benchmarks show the efficacy of our proposal with respect to the state-of-the-art. --- ### An Explainable Ensemble Framework for Alzheimer's Disease Prediction Using Structured Clinical and Cognitive Data Authors: Nishan Mitra Published: 2026-02-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.04449v1 Early and accurate detection of Alzheimer's disease (AD) remains a major challenge in medical diagnosis due to its subtle onset and progressive nature. This research introduces an explainable ensemble learning Framework designed to classify individuals as Alzheimer's or Non-Alzheimer's using structured clinical, lifestyle, metabolic, and lifestyle features. The workflow incorporates rigorous preprocessing, advanced feature engineering, SMOTE-Tomek hybrid class balancing, and optimized modeling using five ensemble algorithms-Random Forest, XGBoost, LightGBM, CatBoost, and Extra Trees-alongside a deep artificial neural network. Model selection was performed using stratified validation to prevent leakage, and the best-performing model was evaluated on a fully unseen test set. Ensemble methods achieved superior performance over deep learning, with XGBoost, Random Forest, and Soft Voting showing the strongest accuracy, sensitivity, and F1-score profiles. Explainability techniques, including SHAP and feature importance analysis, highlighted MMSE, Functional Assessment Age, and several engineered interaction features as the most influential determinants. The results demonstrate that the proposed framework provides a reliable and transparent approach to Alzheimer's disease prediction, offering strong potential for clinical decision support applications. --- ### SkillNet: Create, Evaluate, and Connect AI Skills Authors: Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Yida Xue et al. Published: 2026-02-26 Categories: cs.AI, cs.CL, cs.CV, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2603.04448v3 Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To address this challenge, we introduce SkillNet, an open infrastructure for creating, evaluating, and organizing AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 600,000 skills, an interactive platform, and a versatile Python toolkit. Experiments on ALFWorld, WebShop, and ScienceWorld show 40% higher average rewards and 30% fewer execution steps across multiple backbone models. Furthermore, SkillNet-Gym benchmarks skill retrieval, utilization, and composition, while SkillNet-Fabric enables task-specific skill routing through lightweight Wikis. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery. --- ### SkillNet: Create, Evaluate, and Connect AI Skills Authors: Yuan Liang, Ruobin Zhong, Haoming Xu, Chen Jiang, Yi Zhong, Runnan Fang, Jia-Chen Gu, Shumin Deng, Yunzhi Yao, Mengru Wang, Shuofei Qiao, Xin Xu et al. Published: 2026-02-26 Categories: cs.AI, cs.CL, cs.CV, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2603.04448v1 Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To overcome this limitation, we introduce SkillNet, an open infrastructure designed to create, evaluate, and organize AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 200,000 skills, an interactive platform, and a versatile Python toolkit. Experimental evaluations on ALFWorld, WebShop, and ScienceWorld demonstrate that SkillNet significantly enhances agent performance, improving average rewards by 40% and reducing execution steps by 30% across multiple backbone models. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery. --- ### Perfect score on IPhO 2025 theory by Gemini agent Authors: Yichen Huang Published: 2026-02-26 Categories: physics.ed-ph, cs.AI arXiv: https://arxiv.org/abs/2603.03352v1 The International Physics Olympiad (IPhO) is the world's most prestigious and renowned physics competition for pre-university students. IPhO problems require complex reasoning based on deep understanding of physical principles in a standard general physics curriculum. On IPhO 2025 theory problems, while gold medal performance by AI models was reported previously, it falls behind the best human contestant. Here we build a simple agent with Gemini 3.1 Pro Preview. We run it five times and it achieved a perfect score every time. However, data contamination could occur because Gemini 3.1 Pro Preview was released after the competition. --- ### Automated Measurement of Geniohyoid Muscle Thickness During Speech Using Deep Learning and Ultrasound Authors: Alisher Myrgyyassov, Bruce Xiao Wang, Yu Sun, Shuming Huang, Zhen Song, Min Ney Wong, Yongping Zheng Published: 2026-02-26 Categories: q-bio.QM, cs.LG, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2603.03350v1 Manual measurement of muscle morphology from ultrasound during speech is time-consuming and limits large-scale studies. We present SMMA, a fully automated framework that combines deep-learning segmentation with skeleton-based thickness quantification to analyze geniohyoid (GH) muscle dynamics. Validation demonstrates near-human-level accuracy (Dice = 0.9037, MAE = 0.53 mm, r = 0.901). Application to Cantonese vowel production (N = 11) reveals systematic patterns: /a:/ shows significantly greater GH thickness (7.29 mm) than /i:/ (5.95 mm, p < 0.001, Cohen's d > 1.3), suggesting greater GH activation during production of /a:/ than /i:/, consistent with its role in mandibular depression. Sex differences (5-8% greater in males) reflect anatomical scaling. SMMA achieves expert-validated accuracy while eliminating the need for manual annotation, enabling scalable investigations of speech motor control and objective assessment of speech and swallowing disorders. --- ### RLShield: Practical Multi-Agent RL for Financial Cyber Defense with Attack-Surface MDPs and Real-Time Response Orchestration Authors: Srikumar Nayak Published: 2026-02-26 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.00186v1 Financial systems run nonstop and must stay reliable even during cyber incidents. Modern attacks move across many services (apps, APIs, identity, payment rails), so defenders must make a sequence of actions under time pressure. Most security tools still use fixed rules or static playbooks, which can be slow to adapt when the attacker changes behavior. Reinforcement learning (RL) is a good fit for sequential decisions, but much of the RL-in-finance literature targets trading and does not model real cyber response limits such as action cost, service disruption, and defender coordination across many assets. This paper proposes RLShield, a practical multi-agent RL pipeline for financial cyber defense. We model the enterprise attack surface as a Markov decision process (MDP) where states summarize alerts, asset exposure, and service health, and actions represent real response steps (e.g., isolate a host, rotate credentials, ratelimit an API, block an account, or trigger recovery). RLShield learns coordinated policies across multiple agents (assets or service groups) and optimizes a risk-sensitive objective that balances containment speed, business disruption, and response cost. We also include a game-aware evaluation that tests policies against adaptive attackers and reports operational outcomes, not only reward. Experiments show that RLShield reduces time-to-containment and residual exposure while keeping disruption within a fixed response budget, outperforming static rule baselines and single-agent RL under the same constraints. These results suggest that multi-agent, cost-aware RL can provide a deployable layer for automated response in financial security operations. --- ### ThreatFormer-IDS: Robust Transformer Intrusion Detection with Zero-Day Generalization and Explainable Attribution Authors: Srikumar Nayak Published: 2026-02-26 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.00185v1 Intrusion detection in IoT and industrial networks requires models that can detect rare attacks at low false-positive rates while remaining reliable under evolving traffic and limited labels. Existing IDS solutions often report strong in-distribution accuracy, but they may degrade when evaluated on future traffic, unseen (zero-day) attack families, or adversarial feature manipulations, and many systems provide limited evidence to support analyst triage. To address these gaps, we propose ThreatFormer- IDS, a Transformer-based sequence modeling framework that converts flow records into time-ordered windows and learns contextual representations for robust intrusion screening. The method combines (i) weighted supervised learning for imbalanced detection, (ii) masked self-supervised learning to improve representation stability under drift and sparse labels, (iii) PGDbased adversarial training with scale-normalized perturbations to strengthen resilience against feature-level evasion, and (iv) Integrated Gradients attribution to highlight influential time steps and features for each alert. On the ToN IoT benchmark with chronological evaluation, ThreatFormer-IDS achieves AUCROC 0.994, AUC-PR 0.956, and Recall@1%FPR 0.910, outperforming strong tree-based and sequence baselines. Under a zero-day protocol with held-out attack families, it maintains superior generalization (AUC-PR 0.721, Recall@1%FPR 0.783). Robustness tests further show slower degradation in AUCPR as the adversarial budget increases, confirming improved stability under bounded perturbations. Overall, ThreatFormer- IDS provides a unified, deployment-oriented IDS pipeline that balances detection quality, zero-day behavior, robustness, and explainability. --- ### Zero-Shot and Supervised Bird Image Segmentation Using Foundation Models: A Dual-Pipeline Approach with Grounding DINO~1.5, YOLOv11, and SAM~2.1 Authors: Abhinav Munagala Published: 2026-02-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00184v2 Bird image segmentation remains a challenging task in computer vision due to extreme pose diversity, complex plumage patterns, and variable lighting conditions. This paper presents a dual-pipeline framework for binary bird image segmentation leveraging 2025 foundation models. We introduce two operating modes built upon Segment Anything Model 2.1 (SAM 2.1) as a shared frozen backbone: (1) a zero-shot pipeline using Grounding DINO 1.5 to detect birds via the text prompt "bird" before prompting SAM 2.1 with bounding boxes requiring no labelled bird data; and (2) a supervised pipeline that fine-tunes YOLOv11 on the CUB-200-2011 dataset for high-precision detection, again prompting SAM 2.1 for pixel-level masks. The segmentation model is never retrained for new species or domains. On CUB-200-2011 (11,788 images, 200 species), the supervised pipeline achieves IoU 0.912, Dice 0.954, and F1 0.953 outperforming all prior baselines including SegFormer-B2 (IoU 0.842) by +7.0 percentage points. The zero-shot pipeline achieves IoU 0.831 using only a text prompt, the first such result reported on this benchmark. We demonstrate that prompt-based foundation model pipelines outperform task specific end-to-end trained segmentation networks, while requiring only lightweight detector fine-tuning (~1 hour) for domain adaptation. Complete PyTorch implementation, dataset preparation scripts, and trained weights are publicly available. --- ### Test Case Prioritization: A Snowballing Literature Review and TCPFramework with Approach Combinators Authors: Tomasz Chojnacki, Lech Madeyski Published: 2026-02-26 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.00183v2 Context: Test case prioritization (TCP) is a technique widely used by software development organizations to accelerate regression testing. Objectives: We aim to systematize existing TCP knowledge and to propose and empirically evaluate a new TCP approach. Methods: We conduct a snowballing review (SR) on TCP, implement a~comprehensive platform for TCP research (TCPFramework), analyze existing evaluation metrics and propose two new ones (\rAPFDc{} and ATR), and develop a~family of ensemble TCP methods called approach combinators. Results: The SR helped identify 324 studies related to TCP. The techniques proposed in our study were evaluated on the RTPTorrent dataset, consistently outperforming their base approaches across the majority of subject programs, and achieving performance comparable to the current state of the art for heuristical algorithms (in terms of \rAPFDc{}, NTR, and ATR), while using a distinct approach. Conclusions: The proposed methods can be used efficiently for TCP, reducing the time spent on regression testing by up to 2.7\%. Approach combinators offer significant potential for improvements in future TCP research, due to their composability. --- ### Embedding Morphology into Transformers for Cross-Robot Policy Learning Authors: Kei Suzuki, Jing Liu, Ye Wang, Chiori Hori, Matthew Brand, Diego Romeres, Toshiaki Koike-Akino Published: 2026-02-26 Categories: cs.RO, cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.00182v1 Cross-robot policy learning -- training a single policy to perform well across multiple embodiments -- remains a central challenge in robot learning. Transformer-based policies, such as vision-language-action (VLA) models, are typically embodiment-agnostic and must infer kinematic structure purely from observations, which can reduce robustness across embodiments and even limit performance within a single embodiment. We propose an embodiment-aware transformer policy that injects morphology via three mechanisms: (1) kinematic tokens that factorize actions across joints and compress time through per-joint temporal chunking; (2) a topology-aware attention bias that encodes kinematic topology as an inductive bias in self-attention, encouraging message passing along kinematic edges; and (3) joint-attribute conditioning that augments topology with per-joint descriptors to capture semantics beyond connectivity. Across a range of embodiments, this structured integration consistently improves performance over a vanilla pi0.5 VLA baseline, indicating improved robustness both within an embodiment and across embodiments. --- ### Engineering FAIR Privacy-preserving Applications that Learn Histories of Disease Authors: Ines N. Duarte, Praphulla M. S. Bhawsar, Lee K. Mason, Jeya Balaji Balasubramanian, Daniel E. Russ, Arlindo L. Oliveira, Jonas S. Almeida Published: 2026-02-26 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.00181v1 A recent report on "Learning the natural history of human disease with generative transformers" created an opportunity to assess the engineering challenge of delivering user-facing Generative AI applications in privacy-sensitive domains. The application of these models, particularly for personalized healthcare tasks like predicting individual morbidity risk, is typically constrained by data privacy concerns. This project was accordingly designed as an in-browser model deployment exercise (an "App") testing the architectural boundaries of client-side inference generation (no downloads or installations). We relied exclusively on the documentation provided in the reference report to develop the model, specifically testing the "R" component of the FAIR data principles: Findability, Accessibility, Interoperability, and Reusability. The successful model deployment, leveraging ONNX and a custom JavaScript SDK, establishes a secure, high-performance architectural blueprint for the future of private generative AI in medicine. --- ### NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces Authors: Jiwoo Kim, Swarajh Mehta, Hao-Lun Hsu, Hyunwoo Ryu, Yudong Liu, Miroslav Pajic Published: 2026-02-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00180v2 Generative modeling of neural network parameters is often tied to architectures because standard parameter representations rely on known weight-matrix dimensions. Generation is further complicated by permutation symmetries that allow networks to model similar input-output functions while having widely different, unaligned parameterizations. In this work, we introduce Neural Network Diffusion Transformers (NNiTs), which generate weights in a width-agnostic manner by tokenizing weight matrices into patches and modeling them as locally structured fields. We establish that Graph HyperNetworks (GHNs) with a convolutional neural network (CNN) decoder structurally align the weight space, creating the local correlation necessary for patch-based processing. Focusing on Multilayer Perceptrons (MLPs), where permutation symmetry is especially apparent, NNiTs generate fully functional networks across a range of architectures. Our approach jointly models discrete architecture tokens and continuous weight patches within a single sequence model. On ManiSkill3 robotics tasks, NNiT achieves $>85\%$ success on architecture topologies unseen during training, while baseline approaches fail to generalize; the same pipeline also generalizes to MNIST classification beyond the robotic control setting. --- ### Detecting Cognitive Signatures in Typing Behavior for Non-Intrusive Authorship Verification Authors: David Condrey Published: 2026-02-26 Categories: cs.CR, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2603.00177v3 The proliferation of AI-generated text has intensified the need for reliable authorship verification, yet current output-based methods are increasingly unreliable. We observe that the ordinary typing interface captures rich cognitive signatures, measurable patterns in keystroke timing that reflect the planning, translating, and revising stages of genuine composition. Drawing on large-scale keystroke datasets comprising over 136 million events, we define the Cognitive Load Correlation (CLC) and show it distinguishes genuine composition from mechanical transcription. We present a non-intrusive verification framework that operates within existing writing interfaces, collecting only timing metadata to preserve privacy. Our analytical evaluation estimates 85 to 95 percent discrimination accuracy under stated assumptions, while limiting biometric leakage via evidence quantization. We analyze the adversarial robustness of cognitive signatures, showing they resist timing-forgery attacks that defeat motor-level authentication because the cognitive channel is entangled with semantic content. We conclude that reframing authorship verification as a human-computer interaction problem provides a privacy-preserving alternative to invasive surveillance. --- ### Bridging Policy and Real-World Dynamics: LLM-Augmented Rebalancing for Shared Micromobility Systems Authors: Heng Tan, Hua Yan, Yu Yang Published: 2026-02-26 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00176v1 Shared micromobility services such as e-scooters and bikes have become an integral part of urban transportation, yet their efficiency critically depends on effective vehicle rebalancing. Existing methods either optimize for average demand patterns or employ robust optimization and reinforcement learning to handle predefined uncertainties. However, these approaches overlook emergent events (e.g., demand surges, vehicle outages, regulatory interventions) or sacrifice performance in normal conditions. We introduce AMPLIFY, an LLM-augmented policy adaptation framework for shared micromobility rebalancing. The framework combines a baseline rebalancing module with an LLM-based adaptation module that adjusts strategies in real time under emergent scenarios. The adaptation module ingests system context, demand predictions, and baseline strategies, and refines adjustments through self-reflection. Evaluations on real-world e-scooter data from Chicago show that our approach improves demand satisfaction and system revenue compared to baseline policies, highlighting the potential of LLM-driven adaptation as a flexible solution for managing uncertainty in micromobility systems. --- ### Self-Attention And Beyond the Infinite: Towards Linear Transformers with Infinite Self-Attention Authors: Giorgio Roffo, Hazem Abdelkawy, Nilli Lavie, Luke Palmer Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00175v5 The quadratic cost of softmax attention limits Transformer scalability in high-resolution vision. We introduce Infinite Self-Attention (InfSA), a spectral reformulation that treats each attention layer as a diffusion step on a content-adaptive token graph, accumulating multi-hop interactions through a discounted Neumann series over attention matrices. This links self-attention to classical graph centrality (Katz, PageRank, eigenvector centrality) for interpretable token weighting. We also show the Neumann kernel equals the fundamental matrix of an absorbing Markov chain, so a token's centrality is its expected number of random-walk visits before absorption. We then propose Linear-InfSA, a linear-time variant that approximates the principal eigenvector of the implicit attention operator without forming the full attention matrix. It keeps an auxiliary state of fixed size proportional to per-head dimension dh (independent of sequence length N), is drop-in compatible with Vision Transformers, and supports stable training at 4096 by 4096 and inference at 9216 by 9216 (about 332k tokens). In a 4-layer ViT (53.5M parameters, 59 GFLOPs at 224 by 224), Linear-InfSA reaches 84.7% top-1 on ImageNet-1K, a +3.2 point architectural gain over an equal-depth softmax ViT trained with the same recipe. On ImageNet-V2, InfViT variants outperform all compared baselines (up to 79.8% vs 76.8%), indicating robustness under distribution shift. On an A100 40GB GPU, Linear-InfViT runs at 231 images/s and 0.87 J/image (13x better throughput and energy than equal-depth ViT) and is the only tested model to complete 9216 by 9216 inference without out-of-memory. The linear approximation closely matches the dominant eigenvector of the quadratic operator (cosine 0.985). --- ### Automated Discovery of Improved Constant Weight Binary Codes Authors: Christopher D. Rosin Published: 2026-02-26 Categories: cs.IT, cs.AI, cs.DM, math.CO arXiv: https://arxiv.org/abs/2603.00174v1 A constant weight binary code consists of $n$-bit binary codewords, each with exactly $w$ bits equal to 1, such that any two codewords are at least Hamming distance $d$ apart. $A(n,d,w)$ is the maximum size of a constant weight binary code with parameters $n,d,w$. We establish improved lower bounds on $A(n,d,w)$ by constructing new larger codes, for 24 values of $(n,d,w)$ with $6 \leq d \leq 18$ and $18 \leq n \leq 35$. The improved lower bounds come from two strategies. The first is a tabu search that operates at the level of bit swaps. The second is a novel greedy heuristic that repeatedly chooses the candidate codeword that maximizes a randomly-scored histogram of distances to previously-added codewords. These strategies were proposed by CPro1, an automated protocol that generates, implements, and tests diverse strategies for combinatorial constructions. --- ### Summer-22B: A Systematic Approach to Dataset Engineering and Training at Scale for Video Foundation Model Authors: Simo Ryu, Chunghwan Han Published: 2026-02-26 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00173v1 We describe our experience training Summer-22B, a video foundation model developed from scratch. This report documents the engineering challenges, design decisions, and lessons learned while scaling from raw footage collection to a functional model trained on approximately 50 million clips. We outline our approach combining metadata-driven dataset curation, multi-stage filtering, $μ$P parameterization, and hypersphere-constrained optimization. We developed the Lavender Data system for dataset management and adopted inference-aware architectural choices. We share observations on what worked in our setting: dataset engineering consumed the majority of effort, architectural variants showed smaller differences than we expected, and $μ$P hyperparameter transfer appeared effective even under geometric constraints. We hope this account proves useful to others undertaking similar projects. --- ### Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation Authors: Kennedy Edemacu, Mohammad Mahdi Shokri Published: 2026-02-26 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.00172v1 Retrieval-augmented generation (RAG) has emerged as a powerful paradigm for enhancing multimodal large language models by grounding their responses in external, factual knowledge and thus mitigating hallucinations. However, the integration of externally sourced knowledge bases introduces a critical attack surface. Adversaries can inject malicious multimodal content capable of influencing both retrieval and downstream generation. In this work, we present MM-MEPA, a multimodal poisoning attack that targets the metadata components of image-text entries while leaving the associated visual content unaltered. By only manipulating the metadata, MM-MEPA can still steer multimodal retrieval and induce attacker-desired model responses. We evaluate the attack across multiple benchmark settings and demonstrate its severity. MM-MEPA achieves an attack success rate of up to 91\% consistently disrupting system behaviors across four retrievers and two multimodal generators. Additionally, we assess representative defense strategies and find them largely ineffective against this form of metadata-only poisoning. Our findings expose a critical vulnerability in multimodal RAG and underscore the urgent need for more robust, defense-aware retrieval and knowledge integration methods. --- ### LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models Authors: Yuxiang Shen, Hailong Huang, Zhenkun Gao, Xueheng Li, Man Zhou, Chengjun Xie, Haoxuan Che, Xuanhua He, Jie Zhang Published: 2026-02-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00171v3 Multimodal Large Language Models (MLLMs) are shifting towards "Thinking with Images" by actively exploring image details. While effective, large-scale training is computationally expensive, which has spurred growing interest in lightweight, training-free solutions. However, existing training-free methods suffer from two flaws: perceptual redundancy from indiscriminate cropping, which increases computational cost and introduces noise; and a drift between semantic intent and spatial attention, which prevents accurate localization of user-focused regions. To address these challenges, we propose LookWise, a framework for adaptive visual reasoning. LookWise follows a two-stage pipeline: a confidence-based module decides when to look more carefully, and a semantic-guided localization module determines where to look. This design enables MLLMs to adaptively acquire fine-grained visual evidence without additional training. Experiments on fine-grained and high-resolution visual reasoning benchmarks show that LookWise consistently improves accuracy over strong baselines while achieving an approximately $4.0\times$ inference speedup over the search-based method ZoomEye, demonstrating robust cross-model generalization. --- ### A Novel Evolutionary Method for Automated Skull-Face Overlay in Computer-Aided Craniofacial Superimposition Authors: Práxedes Martínez-Moreno, Andrea Valsecchi, Pablo Mesejo, Pilar Navarro-Ramírez, Valentino Lugli, Sergio Damas Published: 2026-02-26 Categories: cs.CV, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2603.00170v3 Craniofacial Superimposition is a forensic technique for identifying skeletal remains by comparing a post-mortem skull with ante-mortem facial photographs. A critical step in this process is Skull-Face Overlay (SFO). This stage involves aligning a 3D skull model with a 2D facial image, typically guided by cranial and facial landmarks' correspondence. However, its accuracy is undermined by individual variability in soft-tissue thickness, introducing significant uncertainty into the overlay. This paper introduces Lilium, an automated evolutionary method to enhance the accuracy and robustness of SFO. Lilium explicitly models soft-tissue variability using a 3D cone-based representation whose parameters are optimized via a Differential Evolution algorithm. The method enforces anatomical, morphological, and photographic plausibility through a combination of constraints: landmark matching, camera parameter consistency, head pose alignment, skull containment within facial boundaries, and region parallelism. This emulation of the usual forensic practitioners' approach leads Lilium to outperform the state-of-the-art method in terms of both accuracy and robustness. --- ### Image-Based Classification of Olive Species Specific to Turkiye with Deep Neural Networks Authors: Irfan Atabas, Hatice Karatas Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00168v1 In this study, image processing and deep learning methodologies were employed to automatically classify local olive species cultivated in Turkiye. A stereo camera was utilized to capture images of five distinct olive species, which were then preprocessed to ensure their suitability for analysis. Convolutional Neural Network (CNN) architectures, specifically MobileNetV2 and EfficientNetB0, were employed for image classification. These models were optimized through a transfer learning approach. The training and testing results indicated that the EfficientNetB0 model exhibited the optimal performance, with an accuracy of 94.5%. The findings demonstrate that deep learning-based systems offer an effective solution for classifying olive species with high accuracy. The developed method has significant potential for application in areas such as automatic identification and quality control of agricultural products. --- ### Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk? Authors: Hongyu Li, Kuan Liu, Yuan Chen, Juntao Hu, Huimin Lu, Guanjie Chen, Xue Liu, Guangming Lu, Hong Huang Published: 2026-02-26 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00166v2 Recent advances in generative AI have shown human-level performance in complex content creation. However, we identify a "Paradox of Simplicity": models that can render complex scenes often fail at trivial, low-entropy tasks, such as generating a uniform pure color image. We argue this is a systemic failure related to uncontrollable emergent abilities. As models scale, strong priors for aesthetics and complexity override deterministic simplicity, creating an "aesthetic bias" that hinders the model's transition from data simulation to true intellectual abstraction. To better investigate this problem, we formalize the concept of AI Obedience, a hierarchical framework that grades a model's ability to transition from probabilistic approximation to pixel-level determinism (Levels 1 to 5). We introduce Violin, the first systematic benchmark designed to evaluate Level 4 Obedience through three deterministic tasks: color purity, image masking, and geometric shape generation. Using Violin, we evaluate several state-of-the-art models and reveal that closed-source models generally outperform open-source ones in deterministic precision. Interestingly, performance on our benchmark correlates with the benchmark in natural image generation. Our work provides a foundational framework and tools for achieving better alignment between human instructions and model outputs. --- ### ConFoThinking: Consolidated Focused Attention Driven Thinking for Visual Question Answering Authors: Zhaodong Wu, Haochen Xue, Qi Cao, Wenqi Mo, Yu Pei, Wenqi Xu, Jionglong Su, Yang Liu Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00165v1 Thinking with Images improves fine-grained VQA for MLLMs by emphasizing visual cues. However, tool-augmented methods depend on the capacity of grounding, which remains unreliable for MLLMs. In parallel, attention-driven methods to crop the Region of Interest (ROIs) are proposed but they are constrained by (1) fragmented attention signals scattered across layers, leading to suboptimal localization and (2) relying on question- or redundant-text-conditioned attention extraction. Our analysis reveals three patterns: MLLMs may attend to the correct region yet generate incorrect coordinates, where-to-look attention is often fragmented across layers, and attention extraction is query-sensitive. Motivated by these, We propose ConFoThinking, a Consolidated-Focused-Attention-Driven Thinking framework that learns to aggregate attention into a designated intermediate layer, from which we mine and zoom in salient regions for downstream visual understanding. Moreover, we extract attention using concise semantic cues of what to look into, which mitigates the semantic noise introduced by question- or redundant-text-based attention extraction. Experiments across five VQA benchmarks demonstrate ConFoThinking significantly improves perception performance. The code, checkpoints, and dataset will be released after being accepted. --- ### Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection Authors: Marcus Graves Published: 2026-02-26 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.00164v1 We introduce Reverse CAPTCHA, an evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in otherwise normal-looking text. Unlike traditional CAPTCHAs that distinguish humans from machines, our benchmark exploits a capability gap: models can perceive Unicode control characters that are invisible to human readers. We evaluate five models from two providers across two encoding schemes (zero-width binary and Unicode Tags), four hint levels, two payload framings, and with tool use enabled or disabled. Across 8,308 model outputs, we find that tool use dramatically amplifies compliance (Cohen's h up to 1.37, a large effect), that models exhibit provider-specific encoding preferences (OpenAI models decode zero-width binary; Anthropic models prefer Unicode Tags), and that explicit decoding instructions increase compliance by up to 95 percentage points within a single model and encoding. All pairwise model differences are statistically significant (p < 0.05, Bonferroni-corrected). These results highlight an underexplored attack surface for prompt injection via invisible Unicode payloads. --- ### A Boundary-Metric Evaluation Protocol for Whiteboard Stroke Segmentation Under Extreme Imbalance Authors: Nicholas Korcynski Published: 2026-02-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.00163v1 The binary segmentation of whiteboard strokes is hindered by extreme class imbalance, caused by stroke pixels that constitute only $1.79%$ of the image on average, and in addition, the thin-stroke subset averages $1.14% \pm 0.41%$ in the foreground. Standard region metrics (F1, IoU) can mask thin-stroke failures because the vast majority of the background dominates the score. In contrast, adding boundary-aware metrics and a thin-subset equity analysis changes how loss functions rank and exposes hidden trade-offs. We contribute an evaluation protocol that jointly examines region metrics, boundary metrics (BF1, B-IoU), a core/thin-subset equity analysis, and per-image robustness statistics (median, IQR, worst-case) under seeded, multi-run training with non-parametric significance testing. Five losses -- cross-entropy, focal, Dice, Dice+focal, and Tversky -- are trained three times each on a DeepLabV3-MobileNetV3 model and evaluated on 12 held-out images split into core and thin subsets. Overlap-based losses improve F1 by more than 20 points over cross-entropy ($0.663$ vs $0.438$, $p < 0.001$). In addition, the boundary metrics confirm that the gain extends to the precision of the contour. Adaptive thresholding and Sauvola binarization at native resolution achieve a higher mean F1 ($0.787$ for Sauvola) but with substantially worse worst-case performance (F1 $= 0.452$ vs $0.565$ for Tversky), exposing a consistency-accuracy trade-off: classical baselines lead on mean F1 while the learned model delivers higher worst-case reliability. Doubling training resolution further increases F1 by 12.7 points. --- ### GazeXPErT: An Expert Eye-tracking Dataset for Interpretable and Explainable AI in Oncologic FDG-PET/CT Scans Authors: Joy T Wu, Daniel Beckmann, Sarah Miller, Alexander Lee, Elizabeth Theng, Stephan Altmayer, Ken Chang, David Kersting, Tomoaki Otani, Brittany Z Dashevsky, Hye Lim Park, Matteo Novello et al. Published: 2026-02-26 Categories: eess.IV, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2603.00162v2 (18F)FDG-PET/CT is a cornerstone imaging modality for guiding oncology therapies, yet human expert shortages necessitate more efficient diagnostic aids. While standalone AI models for automatic lesion detection exist, clinical translation remains hindered by AI explainability, reliability, and workflow integration. Meanwhile, human-computer-interaction in radiology remain limited to keyboard, mouse and voice, ignoring experts' faster, natural gaze signal. We present GazeXPErT, a 4D eye-tracking dataset with annotated expert decision windows for tumor detection and measurement on 346 dual-read FDG-PET/CTs. The dataset contributes 9,030 gaze-to-lesion trajectories derived from 3,948 minutes of 60 Hz eye-tracking data, rendered in COCO-style format. GazeXPErT captures experts' visual reasoning patterns when adjudicating suspicious lesions. It aims to facilitate development of trusted, explainable and interactive AI models through understanding expert gaze patterns. Baseline feasibility experiments suggest salient signal is extractable from routinely collected expert gaze (3D nnU-Net Dice: 0.6819 versus 0.6008 without), that gaze-trained vision transformers may aid dynamic lesion localization (74.95% predicted gaze closer to tumor), and that experts' intent may be predictable from raw gaze (Accuracy 67.53%, AUROC 0.747). --- ### GazeXPErT: An Expert Eye-tracking Dataset for Interpretable and Explainable AI in Oncologic FDG-PET/CT Scans Authors: Joy T Wu, Daniel Beckmann, Sarah Miller, Alexander Lee, Elizabeth Theng, Stephan Altmayer, Ken Chang, David Kersting, Tomoaki Otani, Brittany Z Dashevsky, Hye Lim Park, Matteo Novello et al. Published: 2026-02-26 Categories: eess.IV, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2603.00162v1 (18F)FDG-PET/CT is a cornerstone imaging modality for tumor staging and treatment response assessment across many cancer types, yet expert reader shortages necessitate more efficient diagnostic aids. While standalone AI models for automatic lesion segmentation exist, clinical translation remains hindered by concerns about interpretability, explainability, reliability, and workflow integration. We present GazeXPErT, a 4D eye-tracking dataset capturing expert search patterns during tumor detection and measurement on 346 FDG-PET/CT scans. Each study was read by a trainee and a board-certified nuclear medicine or radiology specialist using an eye-tracking-enabled annotation platform that simulates routine clinical reads. From 3,948 minutes of raw 60Hz eye-tracking data, 9,030 unique gaze-to-lesion trajectories were extracted, synchronized with PET/CT image slices, and rendered in COCO-style format for multiple machine learning applications. Baseline validation experiments demonstrate that a 3D nnUNet tumor segmentation model achieved superior performance when incorporating expert gaze patterns versus without (DICE score 0.6819 versus 0.6008), and that vision transformers trained on sequential gaze and PET/CT images can improve dynamic lesion localization (74.95% predicted gaze point closer to tumor) and expert intention prediction (Accuracy 67.53% and AUROC 0.747). GazeXPErT is a valuable resource designed to explore multiple machine learning problems beyond these baseline experiments, which include and are not limited to, visual grounding or causal reasoning, clinically explainable feature augmentation, human-computer interaction, human intention prediction or understanding, and expert gaze-rewarded modeling approaches to AI in oncologic FDG-PET/CT imaging. --- ### SKINOPATHY AI: Smartphone-Based Ophthalmic Screening and Longitudinal Tracking Using Lightweight Computer Vision Authors: S. Kalaycioglu, C. Hong, M. Zhu, H. Xie Published: 2026-02-26 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.00161v1 Early ophthalmic screening in low-resource and remote settings is constrained by access to specialized equipment and trained practitioners. We present SKINOPATHY AI, a smartphone-first web application that delivers five complementary, explainable screening modules entirely through commodity mobile hardware: (1) redness quantification via LAB a* color-space normalization; (2) blink-rate estimation using MediaPipe FaceMesh Eye Aspect Ratio (EAR) with adaptive thresholding; (3) pupil light reflex characterization through Pupil-to-Iris Ratio (PIR) time-series analysis; (4) scleral color indexing foricterus and anemia proxies via LAB/HSV statistics; and (5) iris-landmark-calibrated lesion encroachment measurement with millimeter-scale estimates and longitudinal trend tracking. The system is implemented as a React/FastAPI stack with OpenCV and MediaPipe, MongoDB-backed session persistence, and PDF report generation. All algorithms are fully deterministic, privacy-preserving, and designed for non-diagnostic consumer triage. We detail system architecture, algorithm design, evaluation methodology, clinical context, and ethical boundaries of the platform. SKINOPATHY AI demonstrates that multi-signal ophthalmic screening is feasible on unmodified smartphones without cloud-based AI inference, providing a foundation for future clinically validated mobile ophthalmoscopy tools. --- ### Hierarchical Multi-Scale Graph Learning with Knowledge-Guided Attention for Whole-Slide Image Survival Analysis Authors: Bin Xu, Yufei Zhou, Boling Song, Jingwen Sun, Yang Bian, Cheng Lu, Ye Wu, Jianfei Tu, Xiangxue Wang Published: 2026-02-26 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.23557v2 We propose a Hierarchical Multi-scale Knowledge-aware Graph Network (HMKGN) that models multi-scale interactions and spatially hierarchical relationships within whole-slide images (WSIs) for cancer prognostication. Unlike conventional attention-based MIL, which ignores spatial organization, or graph-based MIL, which relies on static handcrafted graphs, HMKGN enforces a hierarchical structure with spatial locality constraints, wherein local cellular-level dynamic graphs aggregate spatially proximate patches within each region of interest (ROI) and a global slide-level dynamic graph integrates ROI-level features into WSI-level representations. Moreover, multi-scale integration at the ROI level combines coarse contextual features from broader views with fine-grained structural representations from local patch-graph aggregation. We evaluate HMKGN on four TCGA cohorts (KIRC, LGG, PAAD, and STAD; N=513, 487, 138, and 370) for survival prediction. It consistently outperforms existing MIL-based models, yielding improved concordance indices (10.85% better) and statistically significant stratification of patient survival risk (log-rank p < 0.05). --- ### Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents Authors: Aishwarya Sarkar, Sayan Ghosh, Nathan Tallent, Aman Chadha, Tanya Roosta, Ali Jannesari Published: 2026-02-26 Categories: cs.LG, cs.AI, cs.DC, cs.MA, cs.PF arXiv: https://arxiv.org/abs/2602.23556v1 Large-scale Graph Neural Networks (GNNs) are typically trained by sampling a vertex's neighbors to a fixed distance. Because large input graphs are distributed, training requires frequent irregular communication that stalls forward progress. Moreover, fetched data changes with graph, graph distribution, sample and batch parameters, and caching polices. Consequently, any static prefetching method will miss crucial opportunities to adapt to different dynamic conditions. In this paper, we introduce Rudder, a software module embedded in the state-of-the-art AWS DistDGL framework, to autonomously prefetch remote nodes and minimize communication. Rudder's adaptation contrasts with both standard heuristics and traditional ML classifiers. We observe that the generative AI found in contemporary Large Language Models (LLMs) exhibits emergent properties like In-Context Learning (ICL) for zero-shot tasks, with logical multi-step reasoning. We find this behavior well-suited for adaptive control even with substantial undertraining. Evaluations using standard datasets and unseen configurations on the NERSC Perlmutter supercomputer show up to 91% improvement in end-to-end training performance over baseline DistDGL (no prefetching), and an 82% improvement over static prefetching, reducing communication by over 50%. Our code is available at https://github.com/aishwaryyasarkar/rudder-llm-agent. --- ### RT-NeuS: Towards Real-Time Neuro-Symbolic Video Understanding via Adaptive Temporal Verification Authors: Shawn Liang, Sahil Shah, Chengwei Zhou, S P Sharan, Harsh Goel, Arnab Sanyal, Sandeep Chinchali, Gourav Datta Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23553v2 Long-form video question answering (LVQA) requires answering natural-language queries about videos spanning minutes to hours, demanding temporal reasoning across thousands of frames. Standard vision-language models (VLMs) struggle with this task: their fixed frame budgets force aggressive downsampling that misses the temporal structure that complex queries depend on. Neuro-symbolic approaches address this by decomposing queries into atomic propositions, translating them into temporal logic specifications, and applying formal model checking to retrieve segments satisfying the specification. This yields up to 10% higher accuracy on temporally complex benchmarks, with interpretability and formal guarantees. However, constructing the video automaton requires grounding every proposition at every frame window via VLM calls, resulting in up to 130x slower inference than standard VLM prompting. We present RT-NeuS, a framework that preserves the accuracy and formal guarantees of temporal-logic-guided LVQA while closing this latency gap. RT-NeuS introduces coarse-to-fine adaptive sampling to identify the small set of query-relevant, visually distinct frames, and batched proposition detection with KV-cache reuse to evaluate all propositions per window in a single forward pass. We derive latency upper bounds as a function of video length, proposition count, and sampling density. Experiments on LongVideoBench, Video-MME, and MLVU reduce inference latency by up to 13x on a single NVIDIA H200 GPU, while matching or exceeding prior neuro-symbolic accuracy. --- ### LE-NeuS: Latency-Efficient Neuro-Symbolic Video Understanding via Adaptive Temporal Verification Authors: Shawn Liang, Sahil Shah, Chengwei Zhou, SP Sharan, Harsh Goel, Arnab Sanyal, Sandeep Chinchali, Gourav Datta Published: 2026-02-26 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.23553v1 Neuro-symbolic approaches to long-form video question answering (LVQA) have demonstrated significant accuracy improvements by grounding temporal reasoning in formal verification. However, existing methods incur prohibitive latency overheads, up to 90x slower than base VLM prompting, rendering them impractical for latency-sensitive edge deployments. We present LE-NeuS, a latency-efficient neuro-symbolic framework that preserves the accuracy benefits of temporal logic-guided video understanding while drastically reducing inference latency. Our key insight is that the dominant computational bottleneck arises from sequential and dense proposition detection across video frames during automaton construction. We address this through two principled optimizations: (1) CLIP guided two-stage adaptive sampling that exploits visual redundancy to skip semantically similar frames while preserving temporal boundaries, and (2) batched proposition detection that parallelizes VLM inference across temporal windows. Theoretically, we derive latency bounds as a function of video length, proposition complexity, and sampling density, establishing conditions under which latency efficiency is achievable. Empirically, on LongVideoBench and Video-MME benchmarks deployed on NVIDIA H100 GPUs, LE-NeuS reduces the latency gap from 90x to approximately 10x while maintaining >10% accuracy gains on temporally complex queries. ---