# Research Papers — 2026-02 · bundle page 32 of 210 > Full-text markdown of papers #1551–1600 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/32 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/31.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/33.md) ### How to Count AIs: Individuation and Liability for AI Agents Authors: Yonathan Arbel, Peter Salib, Simon Goldstein Published: 2026-02-24 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.10028v1 Very soon, millions of AI agents will proliferate across the economy, autonomously taking billions of actions. Inevitably, things will go wrong. Humans will be defrauded, injured, even killed. Law will somehow have to govern the coming wave. But when an AI causes harm, the first question to answer, before anyone can be held accountable is: Which AI Did It? Identifying AIs is unusually difficult. AIs lack bodies. They can copy, split, merge, swarm, and vanish at will. Even today, a "single" AI agent is often an ensemble of instances based on multiple models. The complexity will only multiply as AI capabilities improve. This Article is the first to comprehensively diagnose the legal problem of identifying AIs. Two kinds of identity are required: "thin" and "thick." Thin identification ties every AI action to some human principal, essential for holding accountable the humans who make and use AI agents. Thick identification distinguishes between AI agents, qua agents -- sorting millions of AI entities into discrete, persistent units with stable, coherent goals, essential where principal-agent problems prevent humans from perfectly controlling AIs. This Article also presents a solution: the "Algorithmic Corporation" or "A-corp" -- a legal-fictional entity that can hold property, make contracts, and litigate in its own name. Owned by humans but run by AIs, A-corps solve the thin identity problem by tying AI actions to a human owner, and the thick identity problem via emergent self-organization. A-corps own the resources -- including compute -- that AIs need to accomplish their goals, giving AI managers strong incentives to share control only with goal-aligned AIs. In equilibrium, incentive and selection mechanisms force A-corps to self-organize into persistent, legally legible entities with coherent goals that respond rationally to legal incentives, like liability. --- ### A Governance and Evaluation Framework for Deterministic, Rule-Based Clinical Decision Support in Empiric Antibiotic Prescribing Authors: Francisco José Gárate, Paloma Chausa, Diego Moreno, Judit López Luque, Vicens Díaz-Brito, Enrique Javier Gómez Published: 2026-02-24 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.10027v1 Empiric antibiotic prescribing in high-risk clinical contexts often requires decision making under conditions of incomplete information, where inappropriate coverage or unjustified escalation may compromise safety and antimicrobial stewardship. While clinical decision-support systems have been proposed to assist in this process, many approaches lack explicit governance and evaluation mechanisms defining scope, abstention conditions, recommendation permissibility, and expected system behavior. This work specifies a governance and evaluation framework for deterministic clinical decision-support systems operating under explicitly constrained scope. Deterministic behavior is adopted to ensure that identical inputs yield identical outputs, supporting transparency, auditability, and conservative decision support in high-risk prescribing contexts. The framework treats governance as a first-class design component, separating clinical decision logic from rule-based mechanisms that determine whether a recommendation may be issued. Explicit abstention, deterministic stewardship constraints, and exclusion rules are formalized as core constructs. The framework defines an evaluation methodology utilizing a fixed set of synthetic, mechanism-driven clinical cases with predefined expected behavior. This validation process focuses on behavioral alignment with specified rules rather than clinical effectiveness, predictive accuracy, or outcome optimization. Within this protocol, abstention is treated as a correct and intended outcome when governance conditions are not satisfied. The proposed framework provides a reproducible approach for specifying, governing, and inspecting deterministic clinical decision-support systems in empiric antibiotic prescribing contexts where transparency, auditability, and conservative behavior are prioritized. --- ### RedFuser: An Automatic Operator Fusion Framework for Cascaded Reductions on AI Accelerators Authors: Xinsheng Tang, Yangcheng Li, Nan Wang, Zhiyi Shu, Xingyu Ling, Junna Xing, Peng Zhou, Qiang Liu Published: 2026-02-24 Categories: cs.AR, cs.AI, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2603.10026v1 Operator fusion, as a key performance optimization technique in the deployment of AI models, significantly improves execution efficiency and has been widely adopted in modern AI compilers. However, for cascaded reduction operations involving multiple loops with inter-loop data dependencies, such as the safe softmax followed by GEMM within attention mechanisms, existing compilers lack effective automated fusion and kernel generation capabilities. Although some works have addressed specific instances through hand-crafted fusion strategies, their solutions are limited in generality and difficult to extend to other similar structures. Given the prevalence of such computational patterns in deep learning models, there remains significant untapped potential in achieving general and automated fusion optimization. In this paper, we present a formal theoretical methodology for analyzing cascaded reductions which can fuse them into a single loop and introduce an incremental computation form. Based on this methodology, we design Reduction Fuser (RedFuser), a framework that automatically identifies supported cascaded reduction patterns and generates optimized fused kernels. Experiments show that RedFuser successfully fuses diverse workloads, achieving up to 2$\times$ to 5$\times$ speedup over state-of-the-art AI compilers and matching the performance of highly optimized hand-written kernels. The code is available at https://github.com/alibaba/redfuser --- ### Sensitivity-Guided Framework for Pruned and Quantized Reservoir Computing Accelerators Authors: Atousa Jafari, Mahdi Taheri, Hassan Ghasemzadeh Mohammadi, Christian Herglotz, Marco Platzner Published: 2026-02-24 Categories: cs.AR, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2603.08737v1 This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model accuracy, and hardware efficiency. The proposed approach leverages a sensitivity-based pruning mechanism to identify and remove less critical quantized weights with minimal impact on model accuracy, thereby reducing computational overhead while preserving accuracy. We perform an extensive trade-off analysis to validate the effectiveness of the proposed framework and the impact of pruning and quantization on model performance and hardware parameters. For this evaluation, we employ three time-series datasets, including both classification and regression tasks. Experimental results across selected benchmarks demonstrate that our proposed approach maintains high accuracy while substantially improving computational and resource efficiency in FPGA-based implementations, with variations observed across different configurations and time series applications. For instance, for the MELBOEN dataset, an accelerator quantized to 4-bit at a 15\% pruning rate reduces resource utilization by 1.2\% and the Power Delay Product (PDP) by 50.8\% compared to an unpruned model, without any noticeable degradation in accuracy. --- ### Autonomous Edge-Deployed AI Agents for Electric Vehicle Charging Infrastructure Management Authors: Mohammed Cherifi Published: 2026-02-24 Categories: cs.DC, cs.AI, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.08736v1 Public EV charging infrastructure suffers from significant failure rates -- with field studies reporting up to 27.5% of DC fast chargers non-functional -- and multi-day mean time to resolution, imposing billions in annual economic burden. Cloud-centric architectures cannot achieve the latency, reliability, and bandwidth characteristics required for autonomous operation. We present Auralink SDC (Software-Defined Charging), an architecture deploying domain-specialized AI agents at the network edge for autonomous charging infrastructure management. Key contributions include: (1) Confidence-Calibrated Autonomous Resolution (CCAR), enabling autonomous remediation with formal false-positive bounds; (2) Adaptive Retrieval-Augmented Reasoning (ARA), combining dense and sparse retrieval with dynamic context allocation; (3) Auralink Edge Runtime, achieving sub-50ms TTFT on commodity hardware under PREEMPT_RT constraints; and (4) Hierarchical Multi-Agent Orchestration (HMAO). Implementation uses AuralinkLM models fine-tuned via QLoRA on a domain corpus spanning OCPP 1.6/2.0.1, ISO 15118, and operational incident histories. Evaluation on 18,000 labeled incidents in a controlled environment establishes 78% autonomous incident resolution, 87.6% diagnostic accuracy, and 28-48ms TTFT latency (P50). This work presents architecture and implementation patterns for edge-deployed industrial AI systems with safety-critical constraints. --- ### Benchmarking Federated Learning in Edge Computing Environments: A Systematic Review and Performance Evaluation Authors: Sales Aribe, Gil Nicholas Cagande Published: 2026-02-24 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2603.08735v1 Federated Learning (FL) has emerged as a transformative approach for distributed machine learning, particularly in edge computing environments where data privacy, low latency, and bandwidth efficiency are critical. This paper presents a systematic review and performance evaluation of FL techniques tailored for edge computing. It categorizes state-of-the-art methods into four dimensions: optimization strategies, communication efficiency, privacy-preserving mechanisms, and system architecture. Using benchmarking datasets such as MNIST, CIFAR-10, FEMNIST, and Shakespeare, it assesses five leading FL algorithms across key performance metrics including accuracy, convergence time, communication overhead, energy consumption, and robustness to non-Independent and Identically Distributed (IID) data. Results indicate that SCAFFOLD achieves the highest accuracy (0.90) and robustness, while Federated Averaging (FedAvg) excels in communication and energy efficiency. Visual insights are provided by a taxonomy diagram, dataset distribution chart, and a performance matrix. Problems including data heterogeneity, energy limitations, and repeatability still exist despite advancements. To enable the creation of more robust and scalable FL systems for edge-based intelligence, this analysis identifies existing gaps and provides an organized research agenda in the future. --- ### Measurement-Free Ancilla Recycling via Blind Reset: A Cross-Platform Study on Superconducting and Trapped-Ion Processors Authors: Sangkeum Lee Published: 2026-02-24 Categories: cs.AR, cs.AI, quant-ph arXiv: https://arxiv.org/abs/2603.08733v1 Ancilla reuse in repeated syndrome extraction couples reset quality to logical-cycle latency. We evaluate blind reset -- unitary-only recycling via scaled sequence replay -- on IQM Garnet, Rigetti Ankaa-3, and IonQ under matched seeds, sequence lengths, and shot budgets. Using ancilla cleanliness F_clean=P(|0>), per-cycle latency, and a distance-3 repetition-code logical-error proxy, platform-calibrated simulation identifies candidate regions where blind reset cuts cycle latency by up to 38x under NVQLink-class feedback overhead while maintaining F_clean >= 0.86 for L <= 6. Hardware experiments on IQM Garnet confirm blind-reset cleanliness >= 0.84 at L=8 (1024 shots, seed 42); platform-calibrated simulation for Rigetti Ankaa-3 predicts comparable performance. Architecture-dependent crossover lengths are L* ~ 12 (IQM), ~ 11 (Rigetti), ~ 1 (IonQ), and ~ 78 with GPU-linked external feedback. Two added analyses tighten deployment boundaries: a T1/T2 sensitivity map identifies coherence-ratio regimes, and error-bound validation confirms measured cleanliness remains consistent with the predicted diagnostic envelope. A deployment decision matrix translates these results into backend-specific policy selection. --- ### SmartBench: Evaluating LLMs in Smart Homes with Anomalous Device States and Behavioral Contexts Authors: Qingsong Zou, Zhi Yan, Zhiyao Xu, Kuofeng Gao, Jingyu Xiao, Yong Jiang Published: 2026-02-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06636v1 Due to the strong context-awareness capabilities demonstrated by large language models (LLMs), recent research has begun exploring their integration into smart home assistants to help users manage and adjust their living environments. While LLMs have been shown to effectively understand user needs and provide appropriate responses, most existing studies primarily focus on interpreting and executing user behaviors or instructions. However, a critical function of smart home assistants is the ability to detect when the home environment is in an anomalous state. This involves two key requirements: the LLM must accurately determine whether an anomalous condition is present, and provide either a clear explanation or actionable suggestions. To enhance the anomaly detection capabilities of next-generation LLM-based smart home assistants, we introduce SmartBench, which is the first smart home dataset designed for LLMs, containing both normal and anomalous device states as well as normal and anomalous device state transition contexts. We evaluate 13 mainstream LLMs on this benchmark. The experimental results show that most state-of-the-art models cannot achieve good anomaly detection performance. For example, Claude-Sonnet-4.5 achieves only 66.1% detection accuracy on context-independent anomaly categories, and performs even worse on context-dependent anomalies, with an accuracy of only 57.8%. More experimental results suggest that next-generation LLM-based smart home assistants are still far from being able to effectively detect and handle anomalous conditions in the smart home environment. Our dataset is publicly available at https://github.com/horizonsinzqs/SmartBench. --- ### Graph Property Inference in Small Language Models: Effects of Representation and Reasoning Strategy Authors: Michal Podstawski Published: 2026-02-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06635v2 Recent progress in language modeling has expanded the range of tasks that can be approached through natural language interfaces, including problems that require structured reasoning. However, it remains unclear how effectively limited-capacity language models can infer formal properties of relational structures when those structures are presented in textual form. We conduct a systematic study of graph-theoretic property inference in small instruction-tuned language models, isolating the roles of input representation and reasoning strategy. Across a diverse set of local and global graph metrics evaluated on three models, we find that small language models fail to achieve reliable graph property estimation: normalized errors consistently exceed the intrinsic dispersion of target properties, and rank correlations remain weak across all configurations. However, the failure is structured rather than uniform. Adjacency-list encodings consistently reduce error and improve ordinal consistency relative to edge-lists, and multi-branch reasoning yields measurable aggregate gains across configurations. These results show that without task-specific fine-tuning or architectural adaptation, graph property inference in pretrained small language models remains fundamentally unreliable, but that representational organization and inference design produce consistent differences. The findings characterize the conditions under which structured inference degrades and identify which design choices yield improvements even under constrained model capacity. --- ### A new Uncertainty Principle in Machine Learning Authors: V. Dolotin, A. Morozov Published: 2026-02-24 Categories: cs.LG, hep-th, math-ph arXiv: https://arxiv.org/abs/2603.06634v1 Many scientific problems in the context of machine learning can be reduced to the search of polynomial answers in appropriate variables. The Hevisidization of arbitrary polynomial is actually provided by one-and-the same two-layer expression. What prevents the use of this simple idea is the fatal degeneracy of the Heaviside and sigmoid expansions, which traps the steepest-descent evolution at the bottom of canyons, close to the starting point, but far from the desired true minimum. This problem is unavoidable and can be formulated as a peculiar uncertainty principle -- the sharper the minimum, the smoother the canyons. It is a direct analogue of the usual one, which is the pertinent property of the more familiar Fourier expansion. Standard machine learning software fights with this problem empirically, for example, by testing evolutions, originated at randomly distributed starting points and then selecting the best one. Surprisingly or not, phenomena and problems, encountered in ML application to science are pure scientific and belong to physics, not to computer science. On the other hand, they sound slightly different and shed new light on the well-known phenomena -- for example, extend the uncertainty principle from Fourier and, later, wavelet analysis to a new peculiar class of nearly singular sigmoid functions. --- ### Leakage Safe Graph Features for Interpretable Fraud Detection in Temporal Transaction Networks Authors: Hamideh Khaleghpour, Brett McKinney Published: 2026-02-24 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2603.06632v1 Illicit transaction detection is often driven by transaction level attributes however, fraudulent behavior may also manifest through network structure such as central hubs, high flow intermediaries, and coordinated neighborhoods. This paper presents a time respecting, leakage safe (causal) graph feature extraction protocol for temporal transaction networks and evaluates its utility for illicit entity classification. Using the Elliptic dataset, we construct directed transaction graphs and compute interpretable structural descriptors, including degree statistics, PageRank, HITS hub or authority scores, k-core indices, and neighborhood reachability measures. To prevent look ahead bias, we additionally compute causal variants of graph features using only edges observed up to each timestep. A Random Forest classifier trained with strict temporal splits achieves strong discrimination on a held out future test period (ROC-AUC about 0.85, Average Precision about 0.54). Although transaction attributes remain the dominant predictive signal, graph derived features provide complementary interpretability and enable risk context analysis for investigation workflows. We further assess operational utility using Precision at k and evaluate probability reliability via calibration curves and Brier scores, showing that calibrated models yield better aligned probabilities for triage. Overall, the results support causal graph feature extraction as a practical and interpretable augmentation for temporal fraud detection pipelines. --- ### Molecular Representations for AI in Chemistry and Materials Science: An NLP Perspective Authors: Sanjanasri JP, Pratiti Bhadra, N. Sukumar, Soman KP Published: 2026-02-24 Categories: physics.chem-ph, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2603.05525v1 Deep learning, a subfield of machine learning, has gained importance in various application areas in recent years. Its growing popularity has led it to enter the natural sciences as well. This has created the need for molecular representations that are both machine-readable and understandable to scientists from different fields. Over the years, many chemical molecular representations have been constructed, and new ones continue to be developed as computer technology advances and knowledge of molecular complexity increases. This paper presents some of the most popular digital molecular representations inspired by natural language processing (NLP) and used in chemical informatics. In addition, the paper discusses some notable AI-based applications that use these representations. This paper aims to provide a guide to structural representations that are important for the application of AI in chemistry and materials science from the perspective of an NLP researcher. This review is a reference tool for researchers with little experience working with chemical representations who wish to work on projects at the interface of these fields. --- ### Physics-constrained symbolic regression for discovering closed-form equations of multimodal water retention curves from experimental data Authors: Yejin Kim, Hyoung Suk Suh Published: 2026-02-24 Categories: physics.geo-ph, cs.AI, cs.SC arXiv: https://arxiv.org/abs/2603.03346v1 Modeling the unsaturated behavior of porous materials with multimodal pore size distributions presents significant challenges, as standard hydraulic models often fail to capture their complex, multi-scale characteristics. A common workaround involves superposing unimodal retention functions, each tailored to a specific pore size range; however, this approach requires separate parameter identification for each mode, which limits interpretability and generalizability, especially in data-sparse scenarios. In this work, we introduce a fundamentally different approach: a physics-constrained machine learning framework designed for meta-modeling, enabling the automatic discovery of closed-form mathematical expressions for multimodal water retention curves directly from experimental data. Mathematical expressions are represented as binary trees and evolved via genetic programming, while physical constraints are embedded into the loss function to guide the symbolic regressor toward solutions that are physically consistent and mathematically robust. Our results demonstrate that the proposed framework can discover closed-form equations that effectively represent the water retention characteristics of porous materials with varying pore structures. To support third-party validation, application, and extension, we make the full implementation publicly available in an open-source repository. --- ### LMU-Based Sequential Learning and Posterior Ensemble Fusion for Cross-Domain Infant Cry Classification Authors: Niloofar Jazaeri, Hilmi R. Dajani, Marco Janeczek, Martin Bouchard Published: 2026-02-24 Categories: eess.AS, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2603.02245v3 Decoding infant cry causes remains challenging for healthcare monitoring due to short nonstationary signals, limited annotations, and strong domain shifts across infants and datasets. We propose a compact acoustic framework that fuses mel-frequency cepstral coefficients (MFCCs), short-time Fourier transform (STFT) features, and fundamental-frequency (F0) contours within a multi-branch convolutional neural network (CNN) encoder, and models temporal dynamics using an enhanced Legendre Memory Unit (LMU). Compared to LSTMs, the LMU backbone provides stable sequence modeling with substantially fewer recurrent parameters, supporting efficient deployment. To improve cross-dataset generalization, we introduce calibrated posterior ensemble fusion with entropy-gated weighting to preserve domain-specific expertise while mitigating dataset bias. Experiments on Baby2020 and Baby Crying demonstrate improved macro-F1 under cross-domain evaluation, along with leakage aware splits and real-time feasibility for on-device monitoring. --- ### Mechanistically Guided LoRA Improves Paraphrase Consistency in Medical Vision-Language Models Authors: Binesh Sadanandan, Vahid Behzadan Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00148v1 Medical Vision-Language Models can give different yes or no answers to rephrasings of the same clinical question. We study this in MedGemma-4B using PSF-Med Sadanandan and Behzadan (2025), which provides paraphrase pairs for systematic consistency evaluation on medical VQA. On MIMIC-CXR binary questions (n = 158), the baseline flip rate is 14.6% and mean margin difference is 1.63 logits. We validate that Gemma Scope 2 Sparse Autoencoders (SAEs) transfer to MedGemma activations, achieving R2 ~= 0.997 on both medical and general text (n = 100 prompts each, p < 0.001 for exceeding a 0.95 threshold). We then fine-tune Low-Rank Adaptation (LoRA) adapters with a combined loss that balances paraphrase consistency with answer accuracy. This combined approach prevents mode collapse that occurs with pure consistency training while reducing flip rate from 14.6% to 4.4% (p = 0.002, two-proportion z-test) and margin difference from 1.63 to 0.33 (79.5% reduction). Accuracy remains stable at 84.2% baseline versus 82.3% after training (-1.9pp, not significant). On PadChest Balanced (n = 250), flip rate drops from 13.6% to 7.8%, mean margin difference drops from 1.08 to 0.35 (67.9% reduction), and accuracy increases from 66.4% to 69.4%. A layer-range ablation shows that early layers reduce margin differences more than mechanistically selected middle layers. --- ### Leveraging GenAI for Segmenting and Labeling Centuries-old Technical Documents Authors: Carlos Monroy, Benjamin Navarro Published: 2026-02-24 Categories: cs.CV, cs.IR, eess.IV arXiv: https://arxiv.org/abs/2603.00147v1 Image segmentation and image recognition are well established computational techniques in the broader discipline of image processing. Segmentation allows to locate areas in an image, while recognition identifies specific objects within an image. These techniques have shown remarkable accuracy with modern images, mainly because the amount of training data is vast. Achieving similar accuracy in digitized images of centuries-old documents is more challenging. This difficulty is due to two main reasons: first, the lack of sufficient training data, and second, because the degree of specialization in a given domain. Despite these limitations, the ability to segment and recognize objects in these collections is important for automating the curation, cataloging, and dissemination of knowledge, making the contents of priceless collections accessible to scholars and the general public. In this paper, we report on our ongoing work in segmenting and labeling images pertaining to shipbuilding treatises from the XVI and XVII centuries, a historical period known as the Age of Exploration. To this end, we leverage SAM2 for image segmentation; Florence2 and ChatGPT for labeling; and a specialized ontology ontoShip and glossary glosShip of nautical architecture for enhancing the labeling process. Preliminary results demonstrate the potential of marrying these technologies for improving curation and retrieval of priceless historical documents. We also discuss the challenges and limitations encountered in this approach and ideas on how to overcome them in the future. --- ### M-Gaussian: An Magnetic Gaussian Framework for Efficient Multi-Stack MRI Reconstruction Authors: Kangyuan Zheng, Xuan Cai, Jiangqi Wang, Guixing Fu, Zhuoshuo Li, Yazhou Chen, Xinting Ge, Liangqiong Qu, Mengting Liu Published: 2026-02-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00145v1 Magnetic Resonance Imaging (MRI) is a crucial non-invasive imaging modality. In routine clinical practice, multi-stack thick-slice acquisitions are widely used to reduce scan time and motion sensitivity, particularly in challenging scenarios such as fetal brain imaging. However, the resulting severe through-plane anisotropy compromises volumetric analysis and downstream quantitative assessment, necessitating robust reconstruction of isotropic high-resolution volumes. Implicit neural representation methods, while achieving high quality, suffer from computational inefficiency due to complex network structures. We present M-Gaussian, adapting 3D Gaussian Splatting to MRI reconstruction. Our contributions include: (1) Magnetic Gaussian primitives with physics-consistent volumetric rendering, (2) neural residual field for high-frequency detail refinement, and (3) multi-resolution progressive training. Our method achieves an optimal balance between quality and speed. On the FeTA dataset, M-Gaussian achieves 40.31 dB PSNR while being 14 times faster, representing the first successful adaptation of 3D Gaussian Splatting to multi-stack MRI reconstruction. --- ### Disentangled Hierarchical VAE for 3D Human-Human Interaction Generation Authors: Zichen Geng, Zeeshan Hayder, Bo Miao, Jian Liu, Wei Liu, Ajmal Mian Published: 2026-02-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00144v1 Generating realistic 3D Human-Human Interaction (HHI) requires coherent modeling of the physical plausibility of the agents and their interaction semantics. Existing methods compress all motion information into a single latent representation, limiting their ability to capture fine-grained actions and inter-agent interactions. This often leads to semantic misalignment and physically implausible artifacts, such as penetration or missed contact. We propose Disentangled Hierarchical Variational Autoencoder (DHVAE) based latent diffusion for structured and controllable HHI generation. DHVAE explicitly disentangles the global interaction context and individual motion patterns into a decoupled latent structure by employing a CoTransformer module. To mitigate implausible and physically inconsistent contacts in HHI, we incorporate contrastive learning constraints with our DHVAE to promote a more discriminative and physically plausible latent interaction space. For high-fidelity interaction synthesis, DHVAE employs a DDIM-based diffusion denoising process in the hierarchical latent space, enhanced by a skip-connected AdaLN-Transformer denoiser. Extensive evaluations show that DHVAE achieves superior motion fidelity, text alignment, and physical plausibility with greater computational efficiency. --- ### GrapHist: Graph Self-Supervised Learning for Histopathology Authors: Sevda Öğüt, Cédric Vincent-Cuaz, Natalia Dubljevic, Carlos Hurtado, Vaishnavi Subramanian, Pascal Frossard, Dorina Thanou Published: 2026-02-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.00143v1 Self-supervised vision models have achieved notable success in digital pathology. However, their domain-agnostic transformer architectures are not originally designed to account for fundamental biological elements of histopathology images, namely cells and their complex interactions. In this work, we hypothesize that a biologically-informed modeling of tissues as cell graphs offers a more efficient representation learning. Thus, we introduce GrapHist, a novel graph-based self-supervised learning framework for histopathology, which learns generalizable and structurally-informed embeddings that enable diverse downstream tasks. GrapHist integrates masked autoencoders and heterophilic graph neural networks that are explicitly designed to capture the heterogeneity of tumor microenvironments. We pre-train GrapHist on a large collection of 11 million cell graphs derived from breast tissues and evaluate its transferability across in- and out-of-domain benchmarks. Our results show that GrapHist achieves competitive performance compared to its vision-based counterparts in slide-, region-, and cell-level tasks, while requiring four times fewer parameters. It also drastically outperforms fully-supervised graph models on cancer subtyping tasks. Finally, we also release five graph-based digital pathology datasets used in our study at https://huggingface.co/ogutsevda/datasets , establishing the first large-scale graph benchmark in this field. Our code is available at https://github.com/ogutsevda/graphist . --- ### Evaluating Theory of Mind and Internal Beliefs in LLM-Based Multi-Agent Systems Authors: Adam Kostka, Jarosław A. Chudziak Published: 2026-02-24 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2603.00142v1 LLM-based MAS are gaining popularity due to their potential for collaborative problem-solving enhanced by advances in natural language comprehension, reasoning, and planning. Research in Theory of Mind (ToM) and Belief-Desire-Intention (BDI) models has the potential to further improve the agent's interaction and decision-making in such systems. However, collaborative intelligence in dynamic worlds remains difficult to accomplish since LLM performance in multi-agent worlds is extremely variable. Simply adding cognitive mechanisms like ToM and internal beliefs does not automatically result in improved coordination. The interplay between these mechanisms, particularly in relation to formal logic verification, remains largely underexplored in different LLMs. This work investigates: How do internal belief mechanisms, including symbolic solvers and Theory of Mind, influence collaborative decision-making in LLM-based multi-agent systems, and how does the interplay of those components influence system accuracy? We introduce a novel multi-agent architecture integrating ToM, BDI-style internal beliefs, and symbolic solvers for logical verification. We evaluate this architecture in a resource allocation problem with various LLMs and find an intricate interaction between LLM capabilities, cognitive mechanisms, and performance. This work contributes to the area of AI by proposing a novel multi-agent system with ToM, internal beliefs, and symbolic solvers for augmenting collaborative intelligence in multi-agent systems and evaluating its performance under different LLM settings. --- ### From Scale to Speed: Adaptive Test-Time Scaling for Image Editing Authors: Xiangyan Qu, Zhenlong Yuan, Jing Tang, Rui Chen, Datao Tang, Meng Yu, Lei Sun, Yancheng Bai, Xiangxiang Chu, Gaopeng Gou, Gang Xiong, Yujun Cai Published: 2026-02-24 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2603.00141v3 Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image and instruction. This mismatch causes three challenges when applying Image-CoT to editing: inefficient resource allocation with fixed sampling budgets, unreliable early-stage verification using general MLLM scores, and redundant edited results from large-scale sampling. To address this, we propose ADaptive Edit-CoT (ADE-CoT), an on-demand test-time scaling framework to enhance editing efficiency and performance. It incorporates three key strategies: (1) a difficulty-aware resource allocation that assigns dynamic budgets based on estimated edit difficulty; (2) edit-specific verification in early pruning that uses region localization and caption consistency to select promising candidates; and (3) depth-first opportunistic stopping, guided by an instance-specific verifier, that terminates when intent-aligned results are found. Extensive experiments on three SOTA editing models (Step1X-Edit, BAGEL, FLUX.1 Kontext) across three benchmarks show that ADE-CoT achieves superior performance-efficiency trade-offs. With comparable sampling budgets, ADE-CoT obtains better performance with more than 2x speedup over Best-of-N. --- ### Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion Authors: Sathwik Karnik, Juyeop Kim, Sanmi Koyejo, Jong-Seok Lee, Somil Bansal Published: 2026-02-24 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00140v1 Text-to-image diffusion models often memorize training data, revealing a fundamental failure to generalize beyond the training set. Current mitigation strategies typically sacrifice image quality or prompt alignment to reduce memorization. To address this, we propose Reachability-Aware Diffusion Steering (RADS), an inference-time framework that prevents memorization while preserving generation fidelity. RADS models the diffusion denoising process as a dynamical system and applies concepts from reachability analysis to approximate the "backward reachable tube"--the set of intermediate states that inevitably evolve into memorized samples. We then formulate mitigation as a constrained reinforcement learning (RL) problem, where a policy learns to steer the trajectory away from memorization via minimal perturbations in the caption embedding space. Empirical evaluations show that RADS achieves a superior Pareto frontier between generation diversity (SSCD), quality (FID), and alignment (CLIP) compared to state-of-the-art baselines. Crucially, RADS provides robust mitigation without modifying the diffusion backbone, offering a plug-and-play solution for safe generation. Our website is available at: https://s-karnik.github.io/rads-memorization-project-page/. --- ### Towards Data-driven Nitrogen Estimation in Wheat Fields using Multispectral Images Authors: Andreas Tritsarolis, Tomaž Bokan, Matej Brumen, Domen Mongus, Yannis Theodoridis Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00139v1 The modernization of agriculture has motivated the development of advanced analytics and decision-support systems to improve resource utilization and reduce environmental impacts. Targeted Spraying and Fertilization (TSF) is a critical operation that enables farmers to apply inputs more precisely, optimizing resource use and promoting environmental sustainability. However, accurate TSF is a challenging problem, due to external factors such as crop type, fertilization phase, soil conditions, and weather dynamics. In this paper, we present TerrAI, a Neural Network-based solution for TSF, which considers the spatio-temporal variability across different parcels. Our experimental study over a real-world remote sensing dataset validates the soundness of TerrAI on data-driven agricultural practices. --- ### Latent Replay Detection: Memory-Efficient Continual Object Detection on Microcontrollers via Task-Adaptive Compression Authors: Bibin Wilson Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00138v1 Deploying object detection on microcontrollers (MCUs) enables intelligent edge devices but current models cannot learn new object categories after deployment. Existing continual learning methods require storing raw images far exceeding MCU memory budgets of tens of kilobytes. We present Latent Replay Detection (LRD), the first framework for continual object detection under MCU memory constraints. Our key contributions are: 1. Task-Adaptive Compression: Unlike fixed PCA, we propose learnable compression with FiLM (Feature-wise Linear Modulation) conditioning, where task specific embeddings modulate the compression to preserve discriminative features for each task's distribution; 2. Spatial-Diverse Exemplar Selection: Traditional sampling ignores spatial information critical for detection - we select exemplars maximizing bounding box diversity via farthest-point sampling in IoU space, preventing localization bias in replay; 3. MCU-Deployable System: Our latent replay stores 150 bytes per sample versus >10KB for images, enabling a 64KB buffer to hold 400+ exemplars. Experiments on CORe50 (50 classes, 5 tasks) demonstrate that LRD achieves mAP@50 on the initial task and maintains strong performance across subsequent tasks - a significant improvement over naive fine-tuning while operating within strict MCU constraints. Our task-adaptive FiLM compression and spatial diverse exemplar selection work synergistically to preserve detection capabilities. Deployed on STM32H753ZI, ESP32-S3, and MAX78000 MCUs, LRD achieves 4.9-97.5ms latency per inference within a 64KB memory budget-enabling practical continual detection on edge devices for the first time. --- ### MAML-KT: Addressing Cold Start Problem in Knowledge Tracing for New Students via Few-Shot Model-Agnostic Meta Learning Authors: Indronil Bhattacharjee, Christabel Wayllace Published: 2026-02-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00137v2 Knowledge tracing (KT) models are commonly evaluated by training on early interactions from all students and testing on later responses. While effective for measuring average predictive performance, this evaluation design obscures a cold start scenario that arises in deployment, where models must infer the knowledge state of previously unseen students from only a few initial interactions. Prior studies have shown that under this setting, standard empirically risk-minimized KT models such as DKT, DKVMN and SAKT exhibit substantially lower early accuracy than previously reported. We frame new-student performance prediction as a few-shot learning problem and introduce MAML-KT, a model-agnostic meta learning approach that learns an initialization optimized for rapid adaptation to new students using one or two gradient updates. We evaluate MAML-KT on ASSIST2009, ASSIST2015 and ASSIST2017 using a controlled cold start protocol that trains on a subset of students and tests on held-out learners across early interaction windows (questions 3-10 and 11-15), scaling cohort sizes from 10 to 50 students. Across datasets, MAML-KT achieves higher early accuracy than prior KT models in nearly all cold start conditions, with gains persisting as cohort size increases. On ASSIST2017, we observe a transient drop in early performance that coincides with many students encountering previously unseen skills. Further analysis suggests that these drops coincide with skill novelty rather than model instability, consistent with prior work on skill-level cold start. Overall, optimizing KT models for rapid adaptation reduces early prediction error for new students and provides a clearer lens for interpreting early accuracy fluctuations, distinguishing model limitations from genuine learning and knowledge acquisition dynamics. --- ### TinyVLM: Zero-Shot Object Detection on Microcontrollers via Vision-Language Distillation with Matryoshka Embeddings Authors: Bibin Wilson Published: 2026-02-24 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00136v1 Zero-shot object detection enables recognising novel objects without task-specific training, but current approaches rely on large vision language models (VLMs) like CLIP that require hundreds of megabytes of memory - far exceeding the constraints of micro controller units (MCUs). We present TinyVLM, the first framework enabling zero-shot object detection on resource-constrained MCUs with less than 1MB of memory. Our approach introduces three key innovations: (1) a decoupled architecture that separates visual inference from text encoding, allowing precomputed class embeddings to be stored in flash memory; (2) Matryoshka distillation that trains nested embeddings at multiple dimensions (16-256), enabling flexible accuracy-memory trade-offs; and (3) quantized embedding storage that reduces class prototype memory by 4x with minimal accuracy loss. Trained on Conceptual Captions 3M (CC3M), TinyVLM achieves competitive zero-shot accuracy on COCO, Flowers102, and Food101 while requiring only 285KB of RAM and 892KB of flash memory for the deployed vision encoder. We demonstrate real-time inference at 26 FPS on STM32H7 and over 1,000 FPS on MAX78000 with its CNN accelerator, enabling practical zero-shot detection on edge devices for the first time. --- ### Detoxifying LLMs via Representation Erasure-Based Preference Optimization Authors: Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle, Doina Precup, Daniel M. Roy, Gintare Karolina Dziugaite Published: 2026-02-24 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.23391v1 Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and similar algorithms, reduce the likelihood of harmful continuations, but not robustly so: they are vulnerable to adversarial prompting and easily undone by fine-tuning-based relearning attacks. Indeed, research has shown that these edits to the model are superficial: linear probing reveals that harmful "directions" remain present in representations. To address this, we propose Representation Erasure-based Preference Optimization (REPO), reformulating detoxification as a token-level preference problem. Using a novel objective with preference data, we force the representations of toxic continuations to converge toward their benign counterparts. Our mechanistic analysis reveals that this granular approach is critical: unlike baselines, REPO induces deep, localized edits to toxicity-encoding neurons while preserving general model utility. Exhaustive evaluations show that REPO achieves state-of-the-art robustness, stopping sophisticated threats-including relearning attacks and enhanced GCG jailbreaks-where existing representation- and output-based methods fail. --- ### Deep Sequence Modeling with Quantum Dynamics: Language as a Wave Function Authors: Ahmed Nebli, Hadi Saadatdoorabi, Kevin Yam Published: 2026-02-24 Categories: cs.LG, cs.AI, quant-ph arXiv: https://arxiv.org/abs/2602.22255v1 We introduce a sequence modeling framework in which the latent state is a complex-valued wave function evolving on a finite-dimensional Hilbert space under a learned, time-dependent Hamiltonian. Unlike standard recurrent architectures that rely on gating mechanisms to suppress competing hypotheses, our framework utilizes quantum interference: the Hamiltonian steers the phases of complex amplitudes so that conflicting interpretations cancel while compatible ones reinforce. The dynamics are strictly unitary, ensuring that the state norm is preserved exactly at every time step via a Cayley (Crank--Nicolson) discretization. Token probabilities are extracted using the Born rule, a quadratic measurement operator that couples magnitudes and relative phases. Our primary theoretical contribution is a separation theorem characterizing the representational advantage of this readout: we define a family of disambiguation tasks that a complex unitary model of dimension $N$ solves exactly, but which requires a state dimension of $Ω(N^2)$ for any real-valued orthogonal model equipped with a standard affine-softmax readout. This quadratic gap arises because the Born rule implicitly lifts the $N$-dimensional state into the space of rank-one Hermitian matrices, accessing pairwise phase correlations that are inaccessible to linear projections. Finally, we derive a continuity equation for the latent probability mass, yielding conserved pairwise currents that serve as a built-in diagnostic for tracing information flow between dimensions. --- ### Causal Direction from Convergence Time: Faster Training in the True Causal Direction Authors: Abdulrahman Tamim Published: 2026-02-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.22254v1 We introduce Causal Computational Asymmetry (CCA), a principle for causal direction identification based on optimization dynamics in which one neural network is trained to predict $Y$ from $X$ and another to predict $X$ from $Y$, and the direction that converges faster is inferred to be causal. Under the additive noise model $Y = f(X) + \varepsilon$ with $\varepsilon \perp X$ and $f$ nonlinear and injective, we establish a formal asymmetry: in the reverse direction, residuals remain statistically dependent on the input regardless of approximation quality, inducing a strictly higher irreducible loss floor and non-separable gradient noise in the optimization dynamics, so that the reverse model requires strictly more gradient steps in expectation to reach any fixed loss threshold; consequently, the forward (causal) direction converges in fewer expected optimization steps. CCA operates in optimization-time space, distinguishing it from methods such as RESIT, IGCI, and SkewScore that rely on statistical independence or distributional asymmetries, and proper z-scoring of both variables is required for valid comparison of convergence rates. On synthetic benchmarks, CCA achieves 26/30 correct causal identifications across six neural architectures, including 30/30 on sine and exponential data-generating processes. We further embed CCA into a broader framework termed Causal Compression Learning (CCL), which integrates graph structure learning, causal information compression, and policy optimization, with all theoretical guarantees formally proved and empirically validated on synthetic datasets. --- ### Zatom-1: Towards a Multimodal Foundation Model for 3D Molecules and Materials Authors: Alex Morehead, Miruna Cretu, Antonia Panescu, Rishabh Anand, Maurice Weiler, Tynan Perez, Samuel Blau, Steven Farrell, Wahid Bhimji, Anubhav Jain, Hrushikesh Sahasrabuddhe, Pietro Lio et al. Published: 2026-02-24 Categories: cs.LG, cond-mat.mtrl-sci, cs.AI arXiv: https://arxiv.org/abs/2602.22251v4 General-purpose 3D modeling in chemistry encompasses molecules and materials, requiring both generative and predictive capabilities. However, most existing AI approaches are optimized for a single domain (molecules or materials) and a single task (generation or prediction), which limits representation sharing and transfer. We introduce Zatom-1, a cross-domain, general-purpose model architecture that unifies generative and predictive learning of 3D molecules and materials. Zatom-1 is a deliberately simplified Transformer trained with a multimodal flow matching objective that jointly models discrete atom types and continuous 3D geometries. This approach supports scalable pretraining with predictable gains as model capacity increases, while enabling fast and stable sampling. We use cross-domain generative pretraining as a universal initialization for downstream multi-task prediction of properties, energies, and forces. Empirically, Zatom-1 outperforms or competes with specialized baselines on both multi-task generative and predictive benchmarks in data-controlled settings, while improving generative inference speed by more than an order of magnitude. Our experiments demonstrate positive predictive transfer between data domains from joint generative pretraining: modeling materials during generative pretraining improves molecular property prediction accuracy. Open-source code and model weights are freely available at https://github.com/Zatom-AI/zatom. --- ### Improving Spatial Allocation for Energy System Coupling with Graph Neural Networks Authors: Xuanhao Mu, Jakob Geiges, Nan Liu, Thorsten Schlachter, Veit Hagenmeyer Published: 2026-02-24 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2602.22249v2 In energy system analysis, coupling models with mismatched spatial resolutions is a significant challenge. A common solution is assigning weights to high-resolution geographic units for aggregation, but traditional models are limited by using only a single geospatial attribute. This paper presents an innovative method employing a self-supervised Heterogeneous Graph Neural Network to address this issue. This method models high-resolution geographic units as graph nodes, integrating various geographical features to generate physically meaningful weights for each grid point. These weights enhance the conventional Voronoi-based allocation method, allowing it to go beyond simply geographic proximity by incorporating essential geographic information.In addition, the self-supervised learning paradigm overcomes the lack of accurate ground-truth data. Experimental results demonstrate that applying weights generated by this method to cluster-based Voronoi Diagrams significantly enhances scalability, accuracy, and physical plausibility, while increasing precision compared to traditional methods. --- ### Multi-Dimensional Spectral Geometry of Biological Knowledge in Single-Cell Transformer Representations Authors: Ihor Kendiukhov Published: 2026-02-24 Categories: q-bio.GN, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.22247v1 Single-cell foundation models such as scGPT learn high-dimensional gene representations, but what biological knowledge these representations encode remains unclear. We systematically decode the geometric structure of scGPT internal representations through 63 iterations of automated hypothesis screening (183 hypotheses tested), revealing that the model organizes genes into a structured biological coordinate system rather than an opaque feature space. The dominant spectral axis separates genes by subcellular localization, with secreted proteins at one pole and cytosolic proteins at the other. Intermediate transformer layers transiently encode mitochondrial and ER compartments in a sequence that mirrors the cellular secretory pathway. Orthogonal axes encode protein-protein interaction networks with graded fidelity to experimentally measured interaction strength (Spearman rho = 1.000 across n = 5 STRING confidence quintiles, p = 0.017). In a compact six-dimensional spectral subspace, the model distinguishes transcription factors from their target genes (AUROC = 0.744, all 12 layers significant). Early layers preserve which specific genes regulate which targets, while deeper layers compress this into a coarser regulator versus regulated distinction. Repression edges are geometrically more prominent than activation edges, and B-cell master regulators BATF and BACH2 show convergence toward the B-cell identity anchor PAX5 across transformer depth. Cell-type marker genes cluster with high fidelity (AUROC = 0.851). Residual-stream geometry encodes biological structure complementary to attention patterns. These results indicate that biological transformers learn an interpretable internal model of cellular organization, with implications for regulatory network inference, drug target prioritization, and model auditing. --- ### Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models Authors: Guangnian Wan, Qi Li, Gongfan Fang, Xinyin Ma, Xinchao Wang Published: 2026-02-24 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.22246v1 Multimodal Diffusion Language Models (MDLMs) have recently emerged as a competitive alternative to their autoregressive counterparts. Yet their vulnerability to backdoor attacks remains largely unexplored. In this work, we show that well-established data-poisoning pipelines can successfully implant backdoors into MDLMs, enabling attackers to manipulate model behavior via specific triggers while maintaining normal performance on clean inputs. However, defense strategies effective to these models are yet to emerge. To bridge this gap, we introduce a backdoor defense framework for MDLMs named DiSP (Diffusion Self-Purification). DiSP is driven by a key observation: selectively masking certain vision tokens at inference time can neutralize a backdoored model's trigger-induced behaviors and restore normal functionality. Building on this, we purify the poisoned dataset using the compromised model itself, then fine-tune the model on the purified data to recover it to a clean one. Given such a specific design, DiSP can remove backdoors without requiring any auxiliary models or clean reference data. Extensive experiments demonstrate that our approach effectively mitigates backdoor effects, reducing the attack success rate (ASR) from over 90% to typically under 5%, while maintaining model performance on benign tasks. --- ### Analysis of LLMs Against Prompt Injection and Jailbreak Attacks Authors: Piyush Jaiswal, Aaditya Pratap, Shreyansh Saraswati, Harsh Kasyap, Somanath Tripathy Published: 2026-02-24 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.22242v1 Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus, analyzing this risk has become a critical security requirement. This work evaluates prompt-injection and jailbreak vulnerability using a large, manually curated dataset across multiple open-source LLMs, including Phi, Mistral, DeepSeek-R1, Llama 3.2, Qwen, and Gemma variants. We observe significant behavioural variation across models, including refusal responses and complete silent non-responsiveness triggered by internal safety mechanisms. Furthermore, we evaluated several lightweight, inference-time defence mechanisms that operate as filters without any retraining or GPU-intensive fine-tuning. Although these defences mitigate straightforward attacks, they are consistently bypassed by long, reasoning-heavy prompts. --- ### Stochastic Neural Networks for Quantum Devices Authors: Bodo Rosenhahn, Tobias J. Osborne, Christoph Hirche Published: 2026-02-24 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2602.22241v2 This work presents a formulation to express and optimize stochastic neural networks as quantum circuits in gate-based quantum computing. Motivated by a classical perceptron, stochastic artificial neurons are introduced and combined into a quantum neural network. The Kiefer-Wolfowitz algorithm in combination with simulated annealing is used for training the network weights. Several topologies and models are presented, including shallow fully connected networks, Hopfield Networks, Restricted Boltzmann Machines, Autoencoders and convolutional neural networks. We also demonstrate the combination of our optimized neural networks as an oracle for the Grover algorithm to realize a quantum generative AI model. --- ### Stochastic Neural Networks for Quantum Devices Authors: Bodo Rosenhahn, Tobias J. Osborne, Christoph Hirche Published: 2026-02-24 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2602.22241v1 This work presents a formulation to express and optimize stochastic neural networks as quantum circuits in gate-based quantum computing. Motivated by a classical perceptron, stochastic neurons are introduced and combined into a quantum neural network. The Kiefer-Wolfowitz algorithm in combination with simulated annealing is used for training the network weights. Several topologies and models are presented, including shallow fully connected networks, Hopfield Networks, Restricted Boltzmann Machines, Autoencoders and convolutional neural networks. We also demonstrate the combination of our optimized neural networks as an oracle for the Grover algorithm to realize a quantum generative AI model. --- ### From Prompts to Performance: Evaluating LLMs for Task-based Parallel Code Generation Authors: Linus Bantel, Moritz Strack, Alexander Strack, Dirk Pflüger Published: 2026-02-24 Categories: cs.PL, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2602.22240v1 Large Language Models (LLM) show strong abilities in code generation, but their skill in creating efficient parallel programs is less studied. This paper explores how LLMs generate task-based parallel code from three kinds of input prompts: natural language problem descriptions, sequential reference implementations, and parallel pseudo code. We focus on three programming frameworks: OpenMP Tasking, C++ standard parallelism, and the asynchronous many-task runtime HPX. Each framework offers different levels of abstraction and control for task execution. We evaluate LLM-generated solutions for correctness and scalability. Our results reveal both strengths and weaknesses of LLMs with regard to problem complexity and framework. Finally, we discuss what these findings mean for future LLM-assisted development in high-performance and scientific computing. --- ### VAE-MS: An Asymmetric Variational Autoencoder for Mutational Signature Extraction Authors: Ida Egendal, Rasmus Froberg Brøndum, Dan J Woodcock, Christopher Yau, Martin Bøgsted Published: 2026-02-24 Categories: stat.AP, cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2602.22239v1 Mutational signature analysis has emerged as a powerful method for uncovering the underlying biological processes driving cancer development. However, the signature extraction process, typically performed using non-negative matrix factorization (NMF), often lacks reliability and clinical applicability. To address these limitations, several solutions have been introduced, including the use of neural networks to achieve more accurate estimates and probabilistic methods to better capture natural variation in the data. In this work, we introduce a Variational Autoencoder for Mutational Signatures (VAE-MS), a novel model that leverages both an asymmetric architecture and probabilistic methods for the extraction of mutational signatures. VAE-MS is compared to with three state-of-the-art models for mutational signature extraction: SigProfilerExtractor, the NMF-based gold standard; MUSE-XAE, an autoencoder that employs an asymmetric design without probabilistic components; and SigneR, a Bayesian NMF model, to illustrate the strength in combining a nonlinear extraction with a probabilistic model. In the ability to reconstruct input data and generalize to unseen data, models with probabilistic components (VAE-MS, SigneR) dramatically outperformed models without (SigProfilerExtractor, MUSE-XAE). The NMF-baed models (SigneR, SigProfilerExtractor) had the most accurate reconstructions in simulated data, while VAE-MS reconstructed more accurately on real cancer data. Upon evaluating the ability to extract signatures consistently, no model exhibited a clear advantage over the others. Software for VAE-MS is available at https://github.com/CLINDA-AAU/VAE-MS. --- ### TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI Authors: Kyeongpil Min, Sangmin Jeon, Jae-Jin Lee, Woojoo Lee Published: 2026-02-24 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.22238v1 Cloud-edge AI must jointly satisfy model compression and security under tight device budgets. While Tensor-Train Decomposition (TTD) shrinks on-device models, prior selective-encryption studies largely assume dense weights, leaving its practicality under TTD compression unclear. We present TT-SEAL, a selective-encryption framework for TT-decomposed networks. TT-SEAL ranks TT cores with a sensitivity-based importance metric, calibrates a one-time robustness threshold, and uses a value-DP optimizer to encrypt the minimum set of critical cores with AES. Under TTD-aware, transfer-based threat models (and on an FPGA-prototyped edge processor) TT-SEAL matches the robustness of full (black-box) encryption while encrypting as little as 4.89-15.92% of parameters across ResNet-18, MobileNetV2, and VGG-16, and drives the share of AES decryption in end-to-end latency to low single digits (e.g., 58% -> 2.76% on ResNet-18), enabling secure, low-latency edge AI. --- ### Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environments Authors: Shuang Song, Debao Huang, Deyan Deng, Haolin Xiong, Yang Tang, Yajie Zhao, Rongjun Qin Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.22025v2 Intrinsic image decomposition (IID) of outdoor scenes is crucial for relighting, editing, and understanding large-scale environments, but progress has been limited by the lack of real-world datasets with reliable albedo and shading supervision. We introduce Olbedo, a large-scale aerial dataset for outdoor albedo--shading decomposition in the wild. Olbedo contains 5,664 UAV images captured across four landscape types, multiple years, and diverse illumination conditions. Each view is accompanied by multi-view consistent albedo and shading maps, metric depth, surface normals, sun and sky shading components, camera poses, and, for recent flights, measured HDR sky domes. These annotations are derived from an inverse-rendering refinement pipeline over multi-view stereo reconstructions and calibrated sky illumination, together with per-pixel confidence masks. We demonstrate that Olbedo enables state-of-the-art diffusion-based IID models, originally trained on synthetic indoor data, to generalize to real outdoor imagery: fine-tuning on Olbedo significantly improves single-view outdoor albedo prediction on the MatrixCity benchmark. We further illustrate applications of Olbedo-trained models to multi-view consistent relighting of 3D assets, material editing, and scene change analysis for urban digital twins. We release the dataset, baseline models, and an evaluation protocol to support future research in outdoor intrinsic decomposition and illumination-aware aerial vision. --- ### MERRY: Semantically Decoupled Evaluation of Multimodal Emotional and Role Consistencies of Role-Playing Agents Authors: Zhenyu Wang, Xiaofen Xing, Yirong Chen, Xiangmin Xu Published: 2026-02-24 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.21941v1 Multimodal Role-Playing Agents (MRPAs) are attracting increasing attention due to their ability to deliver more immersive multimodal emotional interactions. However, existing studies still rely on pure textual benchmarks to evaluate the text responses of MRPAs, while delegating the assessment of their multimodal expressions solely to modality-synthesis metrics. This evaluation paradigm, on the one hand, entangles semantic assessment with modality generation, leading to ambiguous error attribution, and on the other hand remains constrained by the heavy reliance on human judgment. To this end, we propose MERRY, a semantically decoupled evaluation framework for assessing Multimodal Emotional and Role consistencies of Role-playing agents. This framework introduce five refined metrics for EC and three for RC. Notably, we transform the traditional subjective scoring approach into a novel bidirectional-evidence-finding task, significantly improving the human agreement of LLM-as-Judge evaluations. Based on MERRY, we conduct extensive evaluations. Our empirical results primarily reveal that: (1) Training on synthetic datasets tends to reduce emotional consistency, whereas training on real-world datasets improves it; (2) Existing models suffer from emotional templatization and simplification, exhibiting positive-bias and performance bottleneck in fine-grained negative emotions; (3) Simple prompting method strengthens the weak models but constrains the strong ones, while simple fine-tuning method suffers from poor role generalization. Codes and dataset are available. --- ### Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG Authors: Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy, Chiara Picardi, Amit Giloni, Roman Vainshtein, Andrés Murillo, Hisashi Kojima, Motoyoshi Sekiya, Yuki Unno, Junichi Suga Published: 2026-02-24 Categories: cs.CR, cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2602.21447v1 Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval, planning, and generation components. We formulate this security challenge as a Partially Observable Markov Decision Process (POMDP), where adversarial intent is a latent variable inferred from noisy multi-stage observations. We introduce MMA-RAG^T, an inference-time control framework governed by a Modular Trust Agent (MTA) that maintains an approximate belief state via structured LLM reasoning. Operating as a model-agnostic overlay, MMA-RAGT mediates a configurable set of internal checkpoints to enforce stateful defence-in-depth. Extensive evaluation on 43,774 instances demonstrates a 6.50x average reduction factor in Attack Success Rate relative to undefended baselines, with negligible utility cost. Crucially, a factorial ablation validates our theoretical bounds: while statefulness and spatial coverage are individually necessary (26.4 pp and 13.6 pp gains respectively), stateless multi-point intervention can yield zero marginal benefit under homogeneous stateless filtering when checkpoint detections are perfectly correlated. --- ### ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decoding Authors: Ziyi Liang, Hamed Poursiami, Zhishun Yang, Keiland Cooper, Akhilesh Jaiswal, Maryam Parsa, Norbert Fortin, Babak Shahbaba Published: 2026-02-24 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.21446v1 Hyperdimensional Computing (HDC) offers a computationally efficient paradigm for neuromorphic learning. Yet, it lacks rigorous uncertainty quantification, leading to open decision boundaries and, consequently, vulnerability to outliers, adversarial perturbations, and out-of-distribution inputs. To address these limitations, we introduce ConformalHDC, a unified framework that combines the statistical guarantees of conformal prediction with the computational efficiency of HDC. For this framework, we propose two complementary variations. First, the set-valued formulation provides finite-sample, distribution-free coverage guarantees. Using carefully designed conformity scores, it forms enclosed decision boundaries that improve robustness to non-conforming inputs. Second, the point-valued formulation leverages the same conformity scores to produce a single prediction when desired, potentially improving accuracy over traditional HDC by accounting for class interactions. We demonstrate the broad applicability of the proposed framework through evaluations on multiple real-world datasets. In particular, we apply our method to the challenging problem of decoding non-spatial stimulus information from the spiking activity of hippocampal neurons recorded as subjects performed a sequence memory task. Our results show that ConformalHDC not only accurately decodes the stimulus information represented in the neural activity data, but also provides rigorous uncertainty estimates and correctly abstains when presented with data from other behavioral states. Overall, these capabilities position the framework as a reliable, uncertainty-aware foundation for neuromorphic computing. --- ### MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning Authors: Jesse He, Helen Jenne, Max Vargas, Davis Brown, Gal Mishne, Yusu Wang, Henry Kvinge Published: 2026-02-24 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.21442v1 The recent field of neural algorithmic reasoning (NAR) studies the ability of graph neural networks (GNNs) to emulate classical algorithms like Bellman-Ford, a phenomenon known as algorithmic alignment. At the same time, recent advances in large language models (LLMs) have spawned the study of mechanistic interpretability, which aims to identify granular model components like circuits that perform specific computations. In this work, we introduce Mechanistic Interpretability for Neural Algorithmic Reasoning (MINAR), an efficient circuit discovery toolbox that adapts attribution patching methods from mechanistic interpretability to the GNN setting. We show through two case studies that MINAR recovers faithful neuron-level circuits from GNNs trained on algorithmic tasks. Our study sheds new light on the process of circuit formation and pruning during training, as well as giving new insight into how GNNs trained to perform multiple tasks in parallel reuse circuit components for related tasks. Our code is available at https://github.com/pnnl/MINAR. --- ### Causal Decoding for Hallucination-Resistant Multimodal Large Language Models Authors: Shiwei Tan, Hengyi Wang, Weiyi Qin, Qi Xu, Zhigang Hua, Hao Wang Published: 2026-02-24 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.21441v1 Multimodal Large Language Models (MLLMs) deliver detailed responses on vision-language tasks, yet remain susceptible to object hallucination (introducing objects not present in the image), undermining reliability in practice. Prior efforts often rely on heuristic penalties, post-hoc correction, or generic decoding tweaks, which do not directly intervene in the mechanisms that trigger object hallucination and thus yield limited gains. To address this challenge, we propose a causal decoding framework that applies targeted causal interventions during generation to curb spurious object mentions. By reshaping the decoding dynamics to attenuate spurious dependencies, our approach reduces false object tokens while maintaining descriptive quality. Across captioning and QA benchmarks, our framework substantially lowers object-hallucination rates and achieves state-of-the-art faithfulness without degrading overall output quality. --- ### Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback Authors: Arnab Maiti, Claire Jie Zhang, Kevin Jamieson, Jamie Heather Morgenstern, Ioannis Panageas, Lillian J. Ratliff Published: 2026-02-24 Categories: stat.ML, cs.GT, cs.LG arXiv: https://arxiv.org/abs/2602.21436v2 In this paper, we study last-iterate convergence of learning algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the day-to-day behavior of learning dynamics. We focus on the challenging setting where players select actions from compact convex sets and receive only bandit feedback. Our main contribution is the design of an uncoupled learning algorithm that guarantees last-iterate convergence to the Nash equilibrium with high probability. We establish a convergence rate of $\tilde{O}(T^{-1/4})$ up to polynomial factors in problem parameters. Crucially, our proposed algorithm is computationally efficient, requiring only an efficient linear optimization oracle over the players' compact action sets. The algorithm is obtained by combining techniques from experimental design and the classic Follow-The-Regularized-Leader (FTRL) framework, with a carefully chosen regularizer function tailored to the geometry of the action set of each learner. --- ### Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback Authors: Arnab Maiti, Claire Jie Zhang, Kevin Jamieson, Jamie Heather Morgenstern, Ioannis Panageas, Lillian J. Ratliff Published: 2026-02-24 Categories: stat.ML, cs.GT, cs.LG arXiv: https://arxiv.org/abs/2602.21436v1 In this paper, we study last-iterate convergence of learning algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the day-to-day behavior of learning dynamics. We focus on the challenging setting where players select actions from compact convex sets and receive only bandit feedback. Our main contribution is the design of an uncoupled learning algorithm that guarantees last-iterate convergence to the Nash equilibrium with high probability. We establish a convergence rate of $\tilde{O}(T^{-1/4})$ up to polynomial factors in problem parameters. Crucially, our proposed algorithm is computationally efficient, requiring only an efficient linear optimization oracle over the players' compact action sets. The algorithm is obtained by combining techniques from experimental design and the classic Follow-The-Regularized-Leader (FTRL) framework, with a carefully chosen regularizer function tailored to the geometry of the action set of each learner. --- ### Synergizing Understanding and Generation with Interleaved Analyzing-Drafting Thinking Authors: Shengqiong Wu, Bobo Li, Xinkai Wang, Xiangtai Li, Lei Cui, Furu Wei, Shuicheng Yan, Hao Fei, Tat-seng Chua Published: 2026-02-24 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.21435v2 Unified Vision-Language Models (UVLMs) aim to advance multimodal learning by supporting both understanding and generation within a single framework. However, existing approaches largely focus on architectural unification while overlooking the need for explicit interaction between the two capabilities during task solving. As a result, current models treat understanding and generation as parallel skills rather than synergistic processes. To achieve real synergy, we introduce the interleaved Analyzing-Drafting problem-solving loop (AD-Loop), a new think paradigm that dynamically alternates between analytic and drafting operations. By interleaving textual thoughts with visual thoughts, AD-Loop enables models to iteratively refine both comprehension and outputs, fostering genuine synergy. To train this mechanism, we design a two-stage strategy: supervised learning on interleaved thought data to initialize alternation, followed by reinforcement learning to promote adaptive and autonomous control. Extensive experiments demonstrate that AD-Loop consistently improves performance across standard benchmarks for both understanding and generation, with strong transferability to various UVLMs architectures. Visual analyses further validate the effectiveness of implicit visual thoughts. These results highlight AD-Loop as a principled and broadly applicable strategy for synergizing comprehension and creation. The project page is at https://sqwu.top/AD-Loop. --- ### Provably Safe Generative Sampling with Constricting Barrier Functions Authors: Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti Published: 2026-02-24 Categories: cs.LG, cs.AI, eess.SY, math.OC arXiv: https://arxiv.org/abs/2602.21429v3 Flow-based generative models, such as diffusion models and flow matching models, have achieved remarkable success in learning complex data distributions. However, a critical gap remains for their deployment in safety-critical domains: the lack of formal guarantees that generated samples will satisfy hard constraints. We propose a safety filtering framework that acts as an online shield for any pre-trained generative model. Our key insight is to cooperate with the generative process rather than override it. We define a constricting safety tube that is relaxed at the initial noise distribution and progressively tightens to the target safe set at the final data distribution, mirroring the coarse-to-fine structure of the generative process itself. By characterizing this tube via Control Barrier Functions (CBFs), we synthesize a feedback control input through a convex Quadratic Program (QP) at each sampling step. As the tube is loosest when noise is high and intervention is cheapest in terms of control energy, most constraint enforcement occurs when it least disrupts the model's learned structure. We prove that this mechanism guarantees safe sampling in discrete-time. The minimum-norm control synthesized at each step minimizes the per-step contribution to the KL divergence between the safe and original distributions. Across all experiments, we observe 100% constraint satisfaction. Our framework applies to any pre-trained flow-based sampling scheme requiring no retraining or architectural modifications. We validate the approach across constrained image generation, physically-consistent trajectory sampling, and safe robotic manipulation policies, achieving 100% constraint satisfaction while preserving semantic fidelity. --- ### PSF-Med: Measuring and Explaining Paraphrase Sensitivity in Medical Vision Language Models Authors: Binesh Sadanandan, Vahid Behzadan Published: 2026-02-24 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.21428v2 Medical Vision Language Models (VLMs) can change their answers when clinicians rephrase the same question, a failure mode that threatens deployment safety. We introduce PSF-Med, a benchmark of 26,850 chest X-ray questions paired with 92,856 meaning-preserving paraphrases across MIMIC-CXR, PadChest, and VinDr-CXR, spanning clinical populations in the US, Spain, and Vietnam. Every paraphrase is validated by an LLM judge using a bidirectional clinical entailment rubric, with 91.6% cross-family agreement. Across nine VLMs, including general-purpose models, we find flip rates from 3% to 37%. However, low flip rate does not imply visual grounding: text-only baselines show that some models stay consistent even when the image is removed, suggesting they rely on language priors. To study mechanisms in one model, we apply GemmaScope 2 Sparse Autoencoders (SAEs) to MedGemma 4B and analyze FlipBank, a curated set of 158 flip cases. We identify a sparse feature at layer 17 that correlates with prompt framing and predicts decision margin shifts. In causal patching, removing this feature's contribution recovers 45% of the yes-minus-no logit margin on average and fully reverses 15% of flips. Acting on this finding, we show that clamping the identified feature at inference reduces flip rates by 31% relative with only a 1.3 percentage-point accuracy cost, while also decreasing text-prior reliance. These results suggest that flip rate alone is not enough; robustness evaluations should test both paraphrase stability and image reliance. ---