# Research Papers — 2026-02 · bundle page 7 of 210 > Full-text markdown of papers #301–350 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/7 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/6.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/8.md) ### Policy Compliance of User Requests in Natural Language for AI Systems Authors: Pedro Cisneros-Velarde Published: 2026-02-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00369v1 Consider an organization whose users send requests in natural language to an AI system that fulfills them by carrying out specific tasks. In this paper, we consider the problem of ensuring such user requests comply with a list of diverse policies determined by the organization with the purpose of guaranteeing the safe and reliable use of the AI system. We propose, to the best of our knowledge, the first benchmark consisting of annotated user requests of diverse compliance with respect to a list of policies. Our benchmark is related to industrial applications in the technology sector. We then use our benchmark to evaluate the performance of various LLM models on policy compliance assessment under different solution methods. We analyze the differences on performance metrics across the models and solution methods, showcasing the challenging nature of our problem. --- ### Deep Learning-Based Meat Freshness Detection with Segmentation and OOD-Aware Classification Authors: Hutama Arif Bramantyo, Mukarram Ali Faridi, Rui Chen, Clarissa Harris, Yin Sun Published: 2026-02-27 Categories: cs.LG, cs.CV, eess.IV arXiv: https://arxiv.org/abs/2603.00368v1 In this study, we present a meat freshness classification framework from Red-Green-Blue (RGB) images that supports both packaged and unpackaged meat datasets. The system classifies four in-distribution (ID) meat classes and uses an out-of-distribution (OOD)-aware abstention mechanism that flags low-confidence samples as No Result. The pipeline combines U-Net-based segmentation with deep feature classifiers. Segmentation is used as a preprocessing step to isolate the meat region and reduce background, producing more consistent inputs for classification. The segmentation module achieved an Intersection over Union (IoU) of 75% and a Dice coefficient of 82%, producing standardized inputs for the classification stage. For classification, we benchmark five backbones: Residual Network-50 (ResNet-50), Vision Transformer-Base/16 (ViT-B/16), Swin Transformer-Tiny (Swin-T), EfficientNet-B0, and MobileNetV3-Small. We use nested 5x3 cross-validation (CV) for model selection and hyperparameter tuning. On the held-out ID test set, EfficientNet-B0 achieves the highest accuracy (98.10%), followed by ResNet-50 and MobileNetV3-Small (both 97.63%) and Swin-T (97.51%), while ViT-B/16 is lower (94.42%). We additionally evaluate OOD scoring and thresholding using standard OOD metrics and sensitivity analysis over the abstention threshold. Finally, we report on-device latency using TensorFlow Lite (TFLite) on a smartphone, highlighting practical accuracy-latency trade-offs for future deployment. --- ### Distribution-Aware Companding Quantization of Large Language Models Authors: Athul Radhakrishnan, Siddhant Mohan, Mahima Sachdeva Published: 2026-02-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00364v1 Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More specifically, at each position in the training corpus, we ask the model to predict the following n tokens using n independent output heads, operating on top of a shared model trunk. Considering multi-token prediction as an auxiliary training task, we measure improved downstream capabilities with no overhead in training time for both code and natural language models. The method is increasingly useful for larger model sizes and keeps its appeal when training for multiple epochs. Gains are especially pronounced on generative benchmarks like coding, where our models consistently outperform strong baselines by several percentage points. Our 13B parameter models solves 12 % more problems on HumanEval and 17 % more on MBPP than comparable next-token models. Experiments on small algorithmic tasks demonstrate that multi-token prediction is favorable for the development of induction heads and algorithmic reasoning capabilities. As an additional benefit, models trained with 4-token prediction are up to 3X times faster at inference, even with large batch sizes. --- ### Quantifying Catastrophic Forgetting in IoT Intrusion Detection Systems Authors: Sourasekhar Banerjee, David Bergqvist, Salman Toor, Christian Rohner, Andreas Johnsson Published: 2026-02-27 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00363v1 Distribution shifts in attack patterns within RPL-based IoT networks pose a critical threat to the reliability and security of large-scale connected systems. Intrusion Detection Systems (IDS) trained on static datasets often fail to generalize to unseen threats and suffer from catastrophic forgetting when updated with new attacks. Ensuring continual adaptability of IDS is therefore essential for maintaining robust IoT network defence. In this focused study, we formulate intrusion detection as a domain continual learning problem and propose a method-agnostic IDS framework that can integrate diverse continual learning strategies. We systematically benchmark five representative approaches across multiple domain-ordering sequences using a comprehensive multi-attack dataset comprising 48 domains. Results show that continual learning mitigates catastrophic forgetting while maintaining a balance between plasticity, stability, and efficiency, a crucial aspect for resource-constrained IoT environments. Among the methods, Replay-based approaches achieve the best overall performance, while Synaptic Intelligence (SI) delivers near-zero forgetting with high training efficiency, demonstrating strong potential for stable and sustainable IDS deployment in dynamic IoT networks. --- ### Percept-Aware Surgical Planning for Visual Cortical Prostheses with Vascular Avoidance Authors: Galen Pogoncheff, Alvin Wang, Jacob Granley, Michael Beyeler Published: 2026-02-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00362v1 Cortical visual prostheses aim to restore sight by electrically stimulating neurons in early visual cortex (V1). With the emergence of high-density and flexible neural interfaces, electrode placement within three-dimensional cortex has become a critical surgical planning problem. Existing strategies emphasize visual field coverage and anatomical heuristics but do not directly optimize predicted perceptual outcomes under safety constraints. We present a percept-aware framework for surgical planning of cortical visual prostheses that formulates electrode placement as a constrained optimization problem in anatomical space. Electrode coordinates are treated as learnable parameters and optimized end-to-end using a differentiable forward model of prosthetic vision. The objective minimizes task-level perceptual error while incorporating vascular avoidance and gray matter feasibility constraints. Evaluated on simulated reading and natural image tasks using realistic folded cortical geometry (FreeSurfer fsaverage), percept-aware optimization consistently improves reconstruction fidelity relative to coverage-based placement strategies. Importantly, vascular safety constraints eliminate margin violations while preserving perceptual performance. The framework further enables co-optimization of multi-electrode thread configurations under fixed insertion budgets. These results demonstrate how differentiable percept models can inform anatomically grounded, safety-aware computer-assisted planning for cortical neural interfaces and provide a foundation for optimizing next-generation visual prostheses. --- ### KROM: Kernelized Reduced Order Modeling Authors: Aras Bacho, Jonghyeon Lee, Houman Owhadi Published: 2026-02-27 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2603.00360v1 We propose KROM, a kernel-based reduced-order framework for fast solution of nonlinear partial differential equations. KROM formulates PDE solution as a minimum-norm (Gaussian-process) recovery problem in an RKHS, and accelerates the resulting kernel solves by sparsifying the precision matrix via sparse Cholesky factorization. A central ingredient is an empirical kernel constructed from a snapshot library of PDE solutions (generated under varying forcings, initial data, boundary data, or parameters). This snapshot-driven kernel adapts to problem-specific structure -- boundary behavior, oscillations, nonsmooth features, linear constraints, conservation and dissipation laws -- thereby reducing the dependence on hand-tuned stationary kernels. The resulting method yields an implicit reduced model: after sparsification, only a localized subset of effective degrees of freedom is used online. We report numerical results for semilinear elliptic equations, discontinuous-coefficient Darcy flow, viscous Burgers, Allen--Cahn, and two-dimensional Navier--Stokes, showing that empirical kernels can match or outperform Matérn baselines, especially in nonsmooth regimes. We also provide error bounds that separate discretization effects, snapshot-space approximation error, and sparse-Cholesky approximation error. --- ### How Large Language Models Get Stuck: Early structure with persistent errors Authors: Alokesh Manna, William Snyder, Whitney Tabor Published: 2026-02-27 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.00359v2 Linguistic insights may help make Large Language Model (LLM) training more efficient. We trained Meta's OPT model on the 100M word BabyLM dataset, and evaluated it on the BLiMP benchmark, which consists of 67 classes, each defined by sentence pairs that differ in a targeted syntactic or semantic rule violation. We tested the model's preference for grammatical over ungrammatical sentences across training iterations and grammatical types. In nearly one-third of the BLiMP classes, OPT fails to consistently assign a higher likelihood to grammatical sentences, even after extensive training. When it fails, it often establishes a clear (erroneous) separation of the likelihoods at an early stage of processing and sustains this to the end of our training phase. We hypothesize that this mis-categorization is costly because it creates entrenched biases that must, eventually, be reversed in order for the model to perform well. We probe this phenomenon using a mixture of qualitative (based on linguistic theory and the theory of Deep Learning) and quantitative (based on numerical testing) assessments. Our qualitative assessments indicate that only some BLiMP tests are meaningful guides. We conclude by articulating a hypothesis, the Bigram Hypothesis, which claims that the learning process will exhibit erroneous entrenchment if bigram statistics bias the model toward wrong distinctions early in training, and we describe a method of testing the hypothesis on appropriately selected BLiMP classes. --- ### Token Management in Multi-Tenant AI Inference Platforms Authors: William J. Cunningham Published: 2026-02-27 Categories: cs.DC, cs.LG, cs.OS arXiv: https://arxiv.org/abs/2603.00356v1 Multi-tenant AI inference platforms must balance resource utilization against service-level guarantees under variable demand. Conventional approaches fail to achieve this balance: dedicated endpoints strand capacity on idle models, while rate limits ignore the heterogeneous cost of inference requests. We introduce \emph{token pools}, a control-plane abstraction that represents inference capacity as explicit entitlements expressed in inference-native units (token throughput, KV cache, concurrency). Unlike rate limits, which govern request admission without regard to execution cost, token pools authorize both admission and autoscaling from the same capacity model, ensuring consistency between what is promised and what is provisioned. The abstraction captures burst modes across multiple dimensions invisible to conventional throttling. Dynamic per-entitlement limits on each burst dimension enable fine-grained control over resource consumption while permitting work-conserving backfill by low-priority traffic. The design supports priority-aware allocation, service tiers with differentiated guarantees, and debt-based fairness mechanisms, all without modifying the underlying inference runtime or cluster scheduler. In experiments on a Kubernetes cluster with vLLM backends, token pools maintain a bounded P99 latency for guaranteed workloads during overload by selectively throttling spot traffic, while a baseline without admission control experiences unbounded latency degradation across all workloads. A second experiment demonstrates debt-based fair-share convergence among elastic workloads with heterogeneous SLO requirements during capacity scarcity. --- ### StethoLM: Audio Language Model for Cardiopulmonary Analysis Across Clinical Tasks Authors: Yishan Wang, Tsai-Ning Wang, Mathias Funk, Aaqib Saeed Published: 2026-02-27 Categories: cs.LG, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2603.00355v1 Listening to heart and lung sounds - auscultation - is one of the first and most fundamental steps in a clinical examination. Despite being fast and non-invasive, it demands years of experience to interpret subtle audio cues. Recent deep learning methods have made progress in automating cardiopulmonary sound analysis, yet most are restricted to simple classification and offer little clinical interpretability or decision support. We present StethoLM, the first audio-language model specialized for cardiopulmonary auscultation, capable of performing instruction-driven clinical tasks across the full spectrum of auscultation analysis. StethoLM integrates audio encoding with a medical language model backbone and is trained on StethoBench, a comprehensive benchmark comprising 77,027 instruction-response pairs synthesized from 16,125 labeled cardiopulmonary recordings spanning seven clinical task categories: binary classification, detection, reporting, reasoning, differential diagnosis, comparison, and location-based analysis. Through multi-stage training that combines supervised fine-tuning and direct preference optimization, StethoLM achieves substantial gains in performance and robustness on out-of-distribution data. Our work establishes a foundation for instruction-following AI systems in clinical auscultation. --- ### Acoustic Sensing for Universal Jamming Grippers Authors: Lion Weber, Theodor Wienert, Martin Splettstößer, Alexander Koenig, Oliver Brock Published: 2026-02-27 Categories: cs.RO, cs.AI, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2603.00351v1 Universal jamming grippers excel at grasping unknown objects due to their compliant bodies. Traditional tactile sensors can compromise this compliance, reducing grasping performance. We present acoustic sensing as a form of morphological sensing, where the gripper's soft body itself becomes the sensor. A speaker and microphone are placed inside the gripper cavity, away from the deformable membrane, fully preserving compliance. Sound propagates through the gripper and object, encoding object properties, which are then reconstructed via machine learning. Our sensor achieves high spatial resolution in sensing object size (2.6 mm error) and orientation (0.6 deg error), remains robust to external noise levels of 80 dBA, and discriminates object materials (up to 100% accuracy) and 16 everyday objects (85.6% accuracy). We validate the sensor in a realistic tactile object sorting task, achieving 53 minutes of uninterrupted grasping and sensing, confirming the preserved grasping performance. Finally, we demonstrate that disentangled acoustic representations can be learned, improving robustness to irrelevant acoustic variations. --- ### Monotropic Artificial Intelligence: Toward a Cognitive Taxonomy of Domain-Specialized Language Models Authors: Antonio de Sousa Leitão Filho, Allan Kardec Duailibe Barros Filho, Fabrício Saul Lima, Selby Mykael Lima dos Santos, Rejani Bandeira Vieira Sousa Published: 2026-02-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.00350v1 The prevailing paradigm in artificial intelligence research equates progress with scale: larger models trained on broader datasets are presumed to yield superior capabilities. This assumption, while empirically productive for general-purpose applications, obscures a fundamental epistemological tension between breadth and depth of knowledge. We introduce the concept of \emph{Monotropic Artificial Intelligence} -- language models that deliberately sacrifice generality to achieve extraordinary precision within narrowly circumscribed domains. Drawing on the cognitive theory of monotropism developed to understand autistic cognition, we argue that intense specialization represents not a limitation but an alternative cognitive architecture with distinct advantages for safety-critical applications. We formalize the defining characteristics of monotropic models, contrast them with conventional polytropic architectures, and demonstrate their viability through Mini-Enedina, a 37.5-million-parameter model that achieves near-perfect performance on Timoshenko beam analysis while remaining deliberately incompetent outside its domain. Our framework challenges the implicit assumption that artificial general intelligence constitutes the sole legitimate aspiration of AI research, proposing instead a cognitive ecology in which specialized and generalist systems coexist complementarily. --- ### COOP$^2$: Defining, Observing, and Repairing Cooperation in LLM Multi-Agent Systems Authors: Hanqing Yang, Narjes Nourzad, Shiyu Chen, Marie Siew, Jingdi Chen, Carlee Joe-Wong Published: 2026-02-27 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.00349v2 Many complex tasks require extended effort, diverse capabilities, or coordinated actions beyond what a single agent can provide. However, simply adding more agents does not guarantee better performance, as effective cooperation depends on how agents interact with each other and with task structure to satisfy evolving constraints over time. This challenge is amplified for LLM-based multi-agent systems (LLM-MAS): plans, messages, and revisions occur in natural language, whereas task progress depends on grounded environment actions. Current evaluations mostly treat cooperation as an implicit ingredient of final task success, leaving both cooperation and the effect of multi-agent interaction on task dynamics difficult to study. We introduce COOP$^2$, an evaluation framework that grounds high-level agent cooperation dynamics in LLM-MAS within task progress in the environment. COOP$^2$ then defines cooperative tasks with verifiable cooperative requirements, allowing us to analyze how cooperation unfolds over time with respect to task progress, as well as where and why cooperation breaks down. Building on this framework, we develop COOP$^2$-Repair, which predicts constraint failures from group plans and opens targeted repair channels for guided revisions. Across two environments and three communication structures, COOP$^2$-Repair improves task success and constraint satisfaction while exposing the additional decision overhead and communication load required for repair. The project web page can be found at: https://happyeureka.github.io/coop2. --- ### Challenges in Enabling Private Data Valuation Authors: Yiwei Fu, Tianhao Wang, Varun Chandrasekaran Published: 2026-02-27 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00342v1 Data valuation methods quantify how individual training examples contribute to a model's behavior, and are increasingly used for dataset curation, auditing, and emerging data markets. As these techniques become operational, they raise serious privacy concerns: valuation scores can reveal whether a person's data was included in training, whether it was unusually influential, or what sensitive patterns exist in proprietary datasets. This motivates the study of privacy-preserving data valuation. However, privacy is fundamentally in tension with valuation utility under differential privacy (DP). DP requires outputs to be insensitive to any single record, while valuation methods are explicitly designed to measure per-record influence. As a result, naive privatization often destroys the fine-grained distinctions needed to rank or attribute value, particularly in heterogeneous datasets where rare examples exert outsized effects. In this work, we analyze the feasibility of DP-compatible data valuation. We identify the core algorithmic primitives across common valuation frameworks that induce prohibitive sensitivity, explaining why straightforward DP mechanisms fail. We further derive design principles for more privacy-amenable valuation procedures and empirically characterize how privacy constraints degrade ranking fidelity across representative methods and datasets. Our results clarify the limits of current approaches and provide a foundation for developing valuation methods that remain useful under rigorous privacy guarantees. --- ### Detecting Transportation Mode Using Dense Smartphone GPS Trajectories and Transformer Models Authors: Yuandong Zhang, Othmane Echchabi, Tianshu Feng, Wenyi Zhang, Hsuai-Kai Liao, Charles Chang Published: 2026-02-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00340v3 Transportation mode detection is an important topic within GeoAI and transportation research. In this study, we introduce SpeedTransformer, a novel Transformer-based model that relies solely on speed inputs to infer transportation modes from dense smartphone GPS trajectories. In benchmark experiments, SpeedTransformer outperformed traditional deep learning models, such as the Long Short-Term Memory (LSTM) network. Moreover, the model demonstrated strong flexibility in transfer learning, achieving high accuracy across geographical regions after fine-tuning with small datasets. Finally, we deployed the model in a real-world experiment, where it consistently outperformed baseline models under complex built environments and high data uncertainty. These findings suggest that Transformer architectures, when combined with dense GPS trajectories, hold substantial potential for advancing transportation mode detection and broader mobility-related research. --- ### Diffusion-Based Low-Light Image Enhancement with Color and Luminance Priors Authors: Xuanshuo Fu, Lei Kang, Javier Vazquez-Corral Published: 2026-02-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00337v1 Low-light images often suffer from low contrast, noise, and color distortion, degrading visual quality and impairing downstream vision tasks. We propose a novel conditional diffusion framework for low-light image enhancement that incorporates a Structured Control Embedding Module (SCEM). SCEM decomposes a low-light image into four informative components including illumination, illumination-invariant features, shadow priors, and color-invariant cues. These components serve as control signals that condition a U-Net-based diffusion model trained with a simplified noise-prediction loss. Thus, the proposed SCEM equipped Diffusion method enforces structured enhancement guided by physical priors. In experiments, our model is trained only on the LOLv1 dataset and evaluated without fine-tuning on LOLv2-real, LSRW, DICM, MEF, and LIME. The method achieves state-of-the-art performance in quantitative and perceptual metrics, demonstrating strong generalization across benchmarks. https://casted.github.io/scem/. --- ### Dynamic Proximal Gradient Algorithms for Schatten-$p$ Quasi-Norm Regularized Problems Authors: Weiping Shen, Linglingzhi Zhu, Yaohua Hu, Chong Li, Xiaoqi Yang Published: 2026-02-27 Categories: math.OC, math.NA, stat.ML arXiv: https://arxiv.org/abs/2603.00333v1 This paper investigates numerical solution methods for the Schatten-$p$ quasi-norm regularized problem with $p \in (0,1)$, which has been widely studied for finding low-rank solutions of linear inverse problems and gained successful applications in various mathematics and applied science fields. We propose a dynamic proximal gradient algorithm that, through the use of the Cayley transformation, avoids computationally expensive singular value decompositions at each iteration, thereby significantly reducing the computational complexity. The algorithm incorporates two step size selection strategies: an adaptive backtracking search and an explicit step size rule. We establish the sublinear convergence of the proposed algorithm for all $p \in (0,1)$ within the framework of the Kurdyka-Lojasiewicz property. Notably, under mild assumptions, we show that the generated sequence converges to a stationary point of the objective function of the problem. For the special case when $p=1$, the linear convergence is further proved under the strict complementarity-type regularity condition commonly used in the linear convergence analysis of the forward-backward splitting algorithms. Preliminary numerical results validate the superior computational efficiency of the proposed algorithm. --- ### Vectorized Adaptive Histograms for Sparse Oblique Forests Authors: Ariel Lubonja, Jungsang Yoon, Haoyin Xu, Yue Wan, Yilin Xu, Richard Stotz, Mathieu Guillame-Bert, Joshua T. Vogelstein, Randal Burns Published: 2026-02-27 Categories: cs.LG, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2603.00326v1 Classification using sparse oblique random forests provides guarantees on uncertainty and confidence while controlling for specific error types. However, they use more data and more compute than other tree ensembles because they create deep trees and need to sort or histogram linear combinations of data at runtime. We provide a method for dynamically switching between histograms and sorting to find the best split. We further optimize histogram construction using vector intrinsics. Evaluating this on large datasets, our optimizations speedup training by 1.7-2.5x compared to existing oblique forests and 1.5-2x compared to standard random forests. We also provide a GPU and hybrid CPU-GPU implementation. --- ### Proof-of-Perception: Certified Tool-Using Multimodal Reasoning with Compositional Conformal Guarantees Authors: Arya Fayyazi, Haleh Akrami Published: 2026-02-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00324v1 We present Proof-of-Perception (PoP), a tool-using framework that casts multimodal reasoning as an executable graph with explicit reliability guarantees. Each perception or logic node outputs a conformal set, yielding calibrated, stepwise uncertainty; a lightweight controller uses these certificates to allocate compute under a budget, expanding with extra tool calls only when needed and stopping early otherwise. This grounds answers in verifiable evidence, reduces error compounding and hallucinations, and enables principled accuracy-compute trade-offs. Across document, chart, and multi-image QA benchmarks, PoP improves performance and reliability over strong chain-of-thought, ReAct-style, and program-of-thought baselines while using computation more efficiently. --- ### AESP: A Human-Sovereign Economic Protocol for AI Agents with Privacy-Preserving Settlement Authors: Jian Sheng Wang Published: 2026-02-27 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.00318v1 As AI agents increasingly perform economic tasks on behalf of humans, a fundamental tension arises between agent autonomy and human control over financial assets. We present the Agent Economic Sovereignty Protocol (AESP), a layered protocol in which agents transact autonomously at machine speed on crypto-native infrastructure while remaining cryptographically bound to human-defined governance boundaries. AESP enforces the invariant that agents are economically capable but never economically sovereign through five mechanisms: (1) a deterministic eight-check policy engine with tiered escalation; (2) human-in-the-loop review with automatic, explicit, and biometric tiers; (3) EIP-712 dual-signed commitments with escrow; (4) HKDF-based context-isolated privacy with batched consolidation; and (5) an ACE-GF-based cryptographic substrate. We formalize two testable hypotheses on security coverage and latency overhead, and specify a complete evaluation methodology with baselines and ablation design. The protocol is implemented as an open-source TypeScript SDK (208 tests, ten modules) with interoperability via MCP and A2A. --- ### When Metrics Disagree: Automatic Similarity vs. LLM-as-a-Judge for Clinical Dialogue Evaluation Authors: Bian Sun, Zhenjian Wang, Orvill de la Torre, Zirui Wang Published: 2026-02-27 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.00314v2 As Large Language Models (LLMs) are increasingly integrated into healthcare to address complex inquiries, ensuring their reliability remains a critical challenge. Recent studies have highlighted that generic LLMs often struggle in clinical contexts, occasionally producing misleading guidance. To mitigate these risks, this research focuses on the domain-specific adaptation of \textbf{Llama-2-7B} using the \textbf{Low-Rank Adaptation (LoRA)} technique. By injecting trainable low-rank matrices into the Transformer layers, we efficiently adapted the model using authentic patient-physician transcripts while preserving the foundational knowledge of the base model. Our objective was to enhance precision and contextual relevance in responding to medical queries by capturing the specialized nuances of clinical discourse. Due to the resource-intensive nature of large-scale human validation, the model's performance was evaluated through a dual-track framework: \textbf{Track A} utilized traditional lexical similarity metrics (e.g., BLEU, ROUGE), while \textbf{Track B} employed an "LLM-as-a-Judge" paradigm using GPT-4 for semantic assessment. Our results demonstrate that while the LoRA-enhanced model achieved significant improvements across all quantitative lexical dimensions, a profound disagreement surfaced in the GPT-4 evaluation, which marginally favored the baseline model's conversational flow. This metric divergence underscores a pivotal finding: traditional automated scores may not fully reflect clinical utility. Consequently, we propose that while automated metrics and LLM judges serve as valuable developmental proxies, rigorous validation by human medical experts remains an indispensable requirement for the safe deployment of LLMs in healthcare settings. --- ### How Well Do Multimodal Models Reason on ECG Signals? Authors: Maxwell A. Xu, Harish Haresamudram, Catherine W. Liu, Patrick Langer, Jathurshan Pradeepkumar, Wanting Mao, Sunita J. Ferns, Aradhana Verma, Jimeng Sun, Paul Schmiedmayer, Xin Liu, Daniel McDuff et al. Published: 2026-02-27 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00312v2 While multimodal large language models offer a promising solution to the "black box" nature of health AI by generating interpretable reasoning traces, verifying the validity of these traces remains a critical challenge. Existing evaluation methods are either unscalable, relying on manual clinician review, or superficial, utilizing proxy metrics (e.g. QA) that fail to capture the semantic correctness of clinical logic. In this work, we introduce a reproducible framework for evaluating reasoning in ECG signals. We propose decomposing reasoning into two distinct, components: (i) Perception, the accurate identification of patterns within the raw signal, and (ii) Deduction, the logical application of domain knowledge to those patterns. To evaluate Perception, we employ an agentic framework that generates code to empirically verify the temporal structures described in the reasoning trace. To evaluate Deduction, we measure the alignment of the model's logic against a structured database of established clinical criteria in a retrieval-based approach. This dual-verification method enables the scalable assessment of "true" reasoning capabilities. --- ### DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths Authors: Hanqing Yang, Hyungwoo Lee, Yuhang Yao, Zhiwei Liu, Kay Liu, Jingdi Chen, Carlee Joe-Wong Published: 2026-02-27 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.00309v2 The increasingly popular agentic AI paradigm promises to harness the power of multiple, general-purpose large language model (LLM) agents to collaboratively complete complex tasks. While many agentic AI systems reduce complexity through predefined workflows or fixed agent roles, the ideal is to support truly autonomous agents capable of emergent collaboration across many interacting agents. Yet in practice, such unstructured interactions often lead to redundant work and cascading failures that are difficult to interpret or correct. In this work, we study multi-agent systems composed of general-purpose LLM agents that solve problems through emergent collaboration, without relying on predefined roles, control flows, or communication constraints. We introduce the Dynamic Interaction Graph (DIG), which captures emergent collaboration as a time-evolving causal network of agent activations and interactions. DIG makes emergent collaboration observable and explainable for the first time, enabling real-time identification, explanation, and correction of collaboration-induced error patterns directly from agents' collaboration paths. Thus, DIG fills a critical gap in understanding how general LLM agents solve problems together in truly agentic multi-agent systems. The project webpage can be found at: https://happyeureka.github.io/dig. --- ### From Prerequisites to Predictions: Validating a Geometric Hallucination Taxonomy Through Controlled Induction Authors: Matic Korun Published: 2026-02-27 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.00307v1 We test whether a geometric hallucination taxonomy -- classifying failures as center-drift (Type~1), wrong-well convergence (Type~2), or coverage gaps (Type~3) -- can distinguish hallucination types through controlled induction in GPT-2. Using a two-level statistical design with prompts ($N = 15$/group) as the unit of inference, we run each experiment 20 times with different generation seeds to quantify result stability. In static embeddings, Type~3 norm separation is robust (significant in 18/20 runs, Holm-corrected in 14/20, median $r = +0.61$). In contextual hidden states, the Type~3 norm effect direction is stable (19/20 runs) but underpowered at $N = 15$ (significant in 4/20, median $r = -0.28$). Types~1 and~2 do not separate in either space (${\leq}\,3/20$ runs). Token-level tests inflate significance by 4--16$\times$ through pseudoreplication -- a finding replicated across all 20 runs. The results establish coverage-gap hallucinations as the most geometrically distinctive failure mode, carried by magnitude rather than direction, and confirm the Type~1/2 non-separation as genuine at 124M parameters. --- ### When does Chain-of-Thought Help: A Markovian Perspective Authors: Zihan Wang, Yijun Dong, Qi Lei Published: 2026-02-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00306v1 Chain-of-Thought (CoT) prompting is a widely used inference-time technique for improving reasoning, yet its gains are uneven across tasks. We analyze when and why CoT helps by modeling the step-wise reasoning trajectory as a Markov chain. Each intermediate step is a state and the dependence between steps is captured by a transition kernel. Our theory identifies transition alignment, whether instances share a common step-wise transition kernel, as the key determinant of CoT's effectiveness. When transitions are identical across steps, CoT reduces inference-time sample complexity: fewer context sample trajectories suffice to recover the final decision. In contrast, when transitions differ across steps, these gains can vanish. We further quantify how noise in intermediate steps modulates CoT's benefit. Beyond theory, we design synthetic benchmarks that isolate these factors to complement prior results on real-world tasks and to empirically validate our predictions. --- ### Polynomial Surrogate Training for Differentiable Ternary Logic Gate Networks Authors: Sai Sandeep Damera, Ryan Matheu, Aniruddh G. Puranic, John S. Baras Published: 2026-02-27 Categories: cs.LG, cs.AI, cs.LO arXiv: https://arxiv.org/abs/2603.00302v1 Differentiable logic gate networks (DLGNs) learn compact, interpretable Boolean circuits via gradient-based training, but all existing variants are restricted to the 16 two-input binary gates. Extending DLGNs to Ternary Kleene $K_3$ logic and training DTLGNs where the UNKNOWN state enables principled abstention under uncertainty is desirable. However, the support set of potential gates per neuron explodes to $19{,}683$, making the established softmax-over-gates training approach intractable. We introduce Polynomial Surrogate Training (PST), which represents each ternary neuron as a degree-$(2,2)$ polynomial with 9 learnable coefficients (a $2{,}187\times$ parameter reduction) and prove that the gap between the trained network and its discretized logic circuit is bounded by a data-independent commitment loss that vanishes at convergence. Scaling experiments from 48K to 512K neurons on CIFAR-10 demonstrate that this hardening gap contracts with overparameterization. Ternary networks train $2$-$3\times$ faster than binary DLGNs and discover true ternary gates that are functionally diverse. On synthetic and tabular tasks we find that the UNKNOWN output acts as a Bayes-optimal uncertainty proxy, enabling selective prediction in which ternary circuits surpass binary accuracy once low-confidence predictions are filtered. More broadly, PST establishes a general polynomial-surrogate methodology whose parameterization cost grows only quadratically with logic valence, opening the door to many-valued differentiable logic. --- ### Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning Authors: Xintong Li, Sha Li, Rongmei Lin, Hongye Jin, Linwei Li, Hejie Cui, Sarah Zhang, Chia-Yuan Chang, Kewei Cheng, Besnik Fetahu, Priyanka Nigam, Jingbo Shang et al. Published: 2026-02-27 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00296v1 Large reasoning models improve with more test-time computation, but often overthink, producing unnecessarily long chains-of-thought that raise cost without improving accuracy. Prior reinforcement learning approaches typically rely on a single outcome reward with trajectory-level length penalties, which cannot distinguish essential from redundant reasoning steps and therefore yield blunt compression. Although recent work incorporates step-level signals, such as offline pruning, supervised data construction, or verifier-based intermediate rewards, reasoning length is rarely treated as an explicit step-level optimization objective during RL. We propose Step-wise Adaptive Penalization (SWAP), a fine-grained framework that allocates length reduction across steps based on intrinsic contribution. We estimate step importance from the model's on-policy log-probability improvement toward the correct answer, then treat excess length as a penalty mass redistributed to penalize low-importance steps more heavily while preserving high-importance reasoning. We optimize with a unified outcome-process advantage within group-relative policy optimization. Extensive experiments demonstrate that SWAP reduces reasoning length by 64.3% on average while improving accuracy by 5.7% relative to the base model. --- ### Scalable Gaussian process modeling of parametrized spatio-temporal fields Authors: Srinath Dama, Prasanth B. Nair Published: 2026-02-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00290v1 We introduce a scalable Gaussian process (GP) framework with deep product kernels for data-driven learning of parametrized spatio-temporal fields over fixed or parameter-dependent domains. The proposed framework learns a continuous representation, enabling predictions at arbitrary spatio-temporal coordinates, independent of the training data resolution. We leverage Kronecker matrix algebra to formulate a computationally efficient training procedure with complexity that scales nearly linearly with the total number of spatio-temporal grid points. A key feature of our approach is the efficient computation of the posterior variance at essentially the same computational cost as the posterior mean (exactly for Cartesian grids and via rigorous bounds for unstructured grids), thereby enabling scalable uncertainty quantification. Numerical studies on a range of benchmark problems demonstrate that the proposed method achieves accuracy competitive with operator learning methods such as Fourier neural operators and deep operator networks. On the one-dimensional unsteady Burgers' equation, our method surpasses the accuracy of projection-based reduced-order models. These results establish the proposed framework as an effective tool for data-driven surrogate modeling, particularly when uncertainty estimates are required for downstream tasks. --- ### Seeking Necessary and Sufficient Information from Multimodal Medical Data Authors: Boyu Chen, Weiye Bao, Junjie Liu, Michael Shen, Bo Peng, Paul Taylor, Zhu Li, Mengyue Yang Published: 2026-02-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00289v1 Learning multimodal representations from medical images and other data sources can provide richer information for decision-making. While various multimodal models have been developed for this, they overlook learning features that are both necessary (must be present for the outcome to occur) and sufficient (enough to determine the outcome). We argue learning such features is crucial as they can improve model performance by capturing essential predictive information, and enhance model robustness to missing modalities as each modality can provide adequate predictive signals. Such features can be learned by leveraging the Probability of Necessity and Sufficiency (PNS) as a learning objective, an approach that has proven effective in unimodal settings. However, extending PNS to multimodal scenarios remains underexplored and is non-trivial as key conditions of PNS estimation are violated. We address this by decomposing multimodal representations into modality-invariant and modality-specific components, then deriving tractable PNS objectives for each. Experiments on synthetic and real-world medical datasets demonstrate our method's effectiveness. Code will be available on GitHub. --- ### TraderBench: How Robust Are AI Agents in Adversarial Capital Markets? Authors: Xiaochuang Yuan, Hui Xu, Silvia Xu, Cui Zou, Jing Xiong Published: 2026-02-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.00285v1 Evaluating AI agents in finance faces two key challenges: static benchmarks require costly expert annotation yet miss the dynamic decision-making central to real-world trading, while LLM-based judges introduce uncontrolled variance on domain-specific tasks. We introduce TraderBench, a benchmark that addresses both issues. It combines expert-verified static tasks (knowledge retrieval, analytical reasoning) with adversarial trading simulations scored purely on realized performance-Sharpe ratio, returns, and drawdown-eliminating judge variance entirely. The framework features two novel tracks: crypto trading with four progressive market-manipulation transforms, and options derivatives scoring across P&L accuracy, Greeks, and risk management. Trading scenarios can be refreshed with new market data to prevent benchmark contamination. Evaluating 13 models (8B open-source to frontier) on ~50 tasks, we find: (1) 8 of 13 models score ~33 on crypto with <1-point variation across adversarial conditions, exposing fixed non-adaptive strategies; (2) extended thinking helps retrieval (+26 points) but has zero impact on trading (+0.3 crypto, -0.1 options). These findings reveal that current agents lack genuine market adaptation, underscoring the need for performance-grounded evaluation in finance. --- ### Ozone Cues Mitigate Reflected Downwelling Radiance in LWIR Absorption-Based Ranging Authors: Unay Dorken Gallastegi, Wentao Shangguan, Vaibhav Choudhary, Akshay Agarwal, Hoover Rueda-Chacón, Martin J. Stevens, Vivek K Goyal Published: 2026-02-27 Categories: cs.CV, eess.SP arXiv: https://arxiv.org/abs/2603.00273v1 Passive long-wave infrared (LWIR) absorption-based ranging relies on atmospheric absorption to estimate distances to objects from their emitted thermal radiation. First demonstrated decades ago for objects much hotter than the air and recently extended to scenes with low temperature variations, this ranging has depended on reflected radiance being negligible. Downwelling radiance is especially problematic, sometimes causing large inaccuracies. In two new ranging methods, we use characteristic features from ozone absorption to estimate the contribution of reflected downwelling radiance. The quadspectral method gives a simple closed-form range estimate from four narrowband measurements, two at a water vapor absorption line and two at an ozone absorption line. The hyperspectral method uses a broader spectral range to improve accuracy while also providing estimates of temperature, emissivity profiles, and contributions of downwelling from a collection of zenith angles. Experimental results demonstrate improved ranging accuracy, in one case reducing error from over 100 m when reflected light is not modeled to 6.8 m with the quadspectral method and 1.2 m with the hyperspectral method. --- ### LLMs Remember First, Forget Last: Dual-Process Interference in Large Language Models Authors: Sourav Chattaraj, Kanak Raj Published: 2026-02-27 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.00270v3 Large language models can process millions of tokens, yet how they handle conflicting information within context remains poorly understood. From patient health logs tracking evolving vital signs to legal documents with superseding clauses, real-world applications routinely require models to retrieve specific values from streams of semantically similar, competing updates. We adapt classical interference paradigms from cognitive psychology to compare retroactive interference (RI; recalling initial values after updates) and proactive interference (PI; recalling recent values despite competing prior encodings) across 39 LLMs spanning 1B to 2.5T parameters. Every model exhibits the same pattern: PI causes substantially greater degradation than RI (d = 1.73), the opposite of the typical human finding where new information more readily disrupts old. Four lines of evidence indicate that RI and PI engage distinct mechanisms: model size predicts RI resistance but not PI; the two scores correlate only weakly; error analysis reveals qualitatively different failure profiles, with RI failures reflecting passive retrieval failure and PI failures reflecting active primacy intrusion; and hallucination rates remain below 1% in both conditions. An adaptive bootstrap design further shows that RI decays smoothly while PI collapses bimodally at high interference, consistent with gradual dilution versus winner-take-all attention dynamics. These findings characterize a systematic primacy bias in transformer attention, with implications for reliable deployment in settings where in-context information evolves over time. --- ### Transformers Remember First, Forget Last: Dual-Process Interference in LLMs Authors: Sourav Chattaraj, Kanak Raj Published: 2026-02-27 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.00270v2 When large language models encounter conflicting information in context, which memories survive -- early or recent? We adapt classical interference paradigms from cognitive psychology to answer this question, testing 39 LLMs across diverse architectures and scales. Every model shows the same pattern: proactive interference (PI) dominates retroactive interference (RI) universally (Cohen's d = 1.73, p < 0.0001), meaning early encodings are protected at the cost of recent information -- the opposite of human memory, where RI typically dominates. Three findings indicate that RI and PI reflect separate memory mechanisms. RI and PI are uncorrelated (R^2 = 0.044), rejecting a unified "memory capacity." Model size predicts RI resistance (R^2 = 0.49) but not PI (R^2 = 0.06, n.s.) -- only RI is capacity-dependent. And error analysis reveals distinct failure modes: RI failures are passive retrieval failures (51%), while PI failures show active primacy intrusion (56%); both show <1% hallucination. These patterns parallel the consolidation-retrieval distinction in cognitive science, suggesting that transformer attention creates a primacy bias with direct implications for interference-heavy applications. --- ### Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking Authors: Shuzhi Gong, Richard O. Sinnott, Jianzhong Qi, Cecile Paris, Preslav Nakov, Zhuohan Xie Published: 2026-02-27 Categories: cs.AI, cs.IR, cs.SI arXiv: https://arxiv.org/abs/2603.00267v1 Misinformation spreading over the Internet poses a significant threat to both societies and individuals, necessitating robust and scalable fact-checking that relies on retrieving accurate and trustworthy evidence. Previous methods rely on semantic and social-contextual patterns learned from training data, which limits their generalization to new data distributions. Recently, Retrieval Augmented Generation (RAG) based methods have been proposed to utilize the reasoning capability of LLMs with retrieved grounding evidence documents. However, these methods largely rely on textual similarity for evidence retrieval and struggle to retrieve evidence that captures multi-hop semantic relations within rich document contents. These limitations lead to overlooking subtle factual correlations between the evidence and the claims to be fact-checked during evidence retrieval, thus causing inaccurate veracity predictions. To address these issues, we propose WKGFC, which exploits authorized open knowledge graph as a core resource of evidence. LLM-enabled retrieval is designed to assess the claims and retrieve the most relevant knowledge subgraphs, forming structured evidence for fact verification. To augment the knowledge graph evidence, we retrieve web contents for completion. The above process is implemented as an automatic Markov Decision Process (MDP): A reasoning LLM agent decides what actions to take according to the current evidence and the claims. To adapt the MDP for fact-checking, we use prompt optimization to fine-tune the agentic LLM. --- ### Adversarial Patch Generation for Visual-Infrared Dense Prediction Tasks via Joint Position-Color Optimization Authors: He Li, Wenyue He, Weihang Kong, Xingchen Zhang Published: 2026-02-27 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.00266v1 Multimodal adversarial attacks for dense prediction remain largely underexplored. In particular, visual-infrared (VI) perception systems introduce unique challenges due to heterogeneous spectral characteristics and modality-specific intensity distributions. Existing adversarial patch methods are primarily designed for single-modal inputs and fail to account for crossspectral inconsistencies, leading to reduced attack effectiveness and poor stealthiness when applied to VI dense prediction models. To address these challenges, we propose a joint position-color optimization framework (AP-PCO) for generating adversarial patches in visual-infrared settings. The proposed method optimizes patch placement and color composition simultaneously using a fitness function derived from model outputs, enabling a single patch to perturb both visible and infrared modalities. To further bridge spectral discrepancies, we introduce a crossmodal color adaptation strategy that constrains patch appearance according to infrared grayscale characteristics while maintaining strong perturbations in the visible domain, thereby reducing cross-spectral saliency. The optimization procedure operates without requiring internal model information, supporting flexible black-box attacks. Extensive experiments on visual-infrared dense prediction tasks demonstrate that the proposed AP-PCO achieves consistently strong attack performance across multiple architectures, providing a practical benchmark for robustness evaluation in VI perception systems. --- ### CoPeP: Benchmarking Continual Pretraining for Protein Language Models Authors: Darshan Patil, Pranshu Malviya, Mathieu Reymond, Quentin Fournier, Sarath Chandar Published: 2026-02-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00253v2 Protein language models (pLMs) have recently gained significant attention for their ability to uncover relationships between sequence, structure, and function from evolutionary statistics, thereby accelerating therapeutic drug discovery. These models learn from large protein databases that are continuously updated by the biology community and whose dynamic nature motivates the application of continual learning, not only to keep up with the ever-growing data, but also as an opportunity to take advantage of the temporal meta-information that is created during this process. As a result, we introduce the Continual Pretraining of Protein Language Models (CoPeP) benchmark, a novel benchmark for evaluating continual learning approaches on pLMs. Specifically, we curate a sequence of protein datasets derived from the UniProt Knowledgebase spanning a decade and define metrics to assess pLM performance across 31 protein understanding tasks. We evaluate several methods from the continual learning literature, including replay, unlearning, and plasticity-based methods, some of which have never been applied to models and data of this scale. Our findings reveal that incorporating temporal meta-information improves perplexity by up to 7% even when compared to training on data from all tasks jointly. Moreover, even at scale, several continual learning methods outperform naive continual pretraining. The CoPeP benchmark offers an exciting opportunity to study these methods at scale in an impactful real-world application. --- ### A Monte Carlo estimator of flow fields for sampling and noise problems Authors: Michael S. Albergo, Gurtej Kanwar Published: 2026-02-27 Categories: hep-lat, cs.LG arXiv: https://arxiv.org/abs/2603.00252v1 Learned field transformations may help address ubiquitous critical slowing down and signal-to-noise problems in lattice field theory. In the context of an annealed sequence of distributions, field transformations are defined by integrating flow fields that exactly solve a local transport problem. These proceedings discuss a new Monte Carlo approach to evaluating these flow fields, which can then be used directly in such contexts or as a means of generating unbiased training data for machine learning approaches. By defining the Monte Carlo estimator using coupled Langevin noise, the statistical noise in the required integrals is significantly mitigated. Demonstrations of the method include a U(1) transport problem and an SU(N) glueball correlator. --- ### GENAI WORKBENCH: AI-Assisted Analysis and Synthesis of Engineering Systems from Multimodal Engineering Data Authors: H. Sinan Bank, Daniel R. Herber Published: 2026-02-27 Categories: cs.SE, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2603.00251v2 Modern engineering design platforms excel at discipline-specific tasks such as CAD, CAM, and CAE, but often lack native systems engineering frameworks. This creates a disconnect where system-level requirements and architectures are managed separately from detailed component design, hindering holistic development and increasing integration risks. To address this, we present the conceptual framework for the GenAI Workbench, a Model-Based Systems Engineering (MBSE) environment that integrates systems engineering principles into the designer's workflow. Built on an open-source PLM platform, it establishes a unified digital thread by linking semantic data from documents, physical B-rep geometry, and relational system graphs. The workbench facilitates an AI-assisted workflow where a designer can ingest source documents, from which the system automatically extracts requirements and uses vision-language models to generate an initial system architecture, such as a Design Structure Matrix (DSM). This paper presents the conceptual architecture, proposed methodology, and anticipated impact of this work-in-progress framework, which aims to foster a more integrated, data-driven, and informed engineering design methodology. --- ### Scaling Quantum Machine Learning without Tricks: Full-Resolution and Diverse Image Generation Authors: Jonas Jäger, Florian J. Kiwit, Carlos A. Riofrío Published: 2026-02-27 Categories: quant-ph, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.00233v2 Quantum generative modeling is a rapidly evolving discipline at the intersection of quantum computing and machine learning. Contemporary quantum machine learning is generally limited to toy examples or heavily restricted datasets with few elements. This is not only due to the current limitations of available quantum hardware but also due to the absence of inductive biases arising from application-agnostic designs. Current quantum solutions must resort to tricks to scale down high-resolution images, such as relying heavily on dimensionality reduction or utilizing multiple quantum models for low-resolution image patches. Building on recent developments in classical image loading to quantum computers, we circumvent these limitations and train quantum Wasserstein GANs on the established classical MNIST and Fashion-MNIST datasets. Using the complete datasets, our system generates full-resolution images across all ten classes and establishes a new state-of-the-art performance with a single end-to-end quantum generator without tricks. As a proof-of-principle, we also demonstrate that our approach can be extended to color images, exemplified on the Street View House Numbers dataset. We analyze how the choice of variational circuit architecture introduces inductive biases, which crucially unlock this performance. Furthermore, enhanced noise input techniques enable highly diverse image generation while maintaining quality. Finally, we show promising results even under quantum shot noise conditions. --- ### Pretty Good Measurement for Radiomics: A Quantum-Inspired Multi-Class Classifier for Lung Cancer Subtyping and Prostate Cancer Risk Stratification Authors: Giuseppe Sergioli, Carlo Cuccu, Giovanni Pasini, Alessandro Stefano, Giorgio Russo, Andrés Camilo Granda Arango, Roberto Giuntini Published: 2026-02-27 Categories: cs.CV, quant-ph arXiv: https://arxiv.org/abs/2603.00223v2 We investigate a quantum-inspired approach to supervised multi-class classification based on the Pretty Good Measurement (PGM), viewed as an operator-valued decision rule derived from quantum state discrimination. The method associates each class with an encoded mixed state and performs classification through a single POVM construction, thus providing a genuinely multi-class strategy without reduction to pairwise or one-vs-rest schemes. In this perspective, classification is reformulated as the discrimination of a finite ensemble of class-dependent density operators, with performance governed by the geometry induced by the encoding map and by the overlap structure among classes. To assess the practical scope of this framework, we apply the PGM-based classifier to two biomedical radiomics case studies: histopathological subtyping of non-small-cell lung carcinoma (NSCLC) and prostate cancer (PCa) risk stratification. The evaluation is conducted under protocols aligned with previously reported radiomics studies, enabling direct comparison with established classical baselines. The results show that the PGM-based classifier is consistently competitive and, in several settings, improves upon standard methods. In particular, the method performs especially well in the NSCLC binary and three-class tasks, while remaining competitive in the four-class case, where increased class overlap yields a more demanding discrimination geometry. In the PCa study, the PGM classifier remains close to the strongest ensemble baseline and exhibits clinically relevant sensitivity--specificity trade-offs across feature-selection scenarios. --- ### Empowering Future Cybersecurity Leaders: Advancing Students through FINDS Education for Digital Forensic Excellence Authors: Yashas Hariprasad, Subhash Gurappa, Sundararaj S. Iyengar, Jerry F. Miller, Pronab Mohanty, Naveen Kumar Chaudhary Published: 2026-02-27 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2603.00222v2 The Forensics Investigations Network in Digital Sciences (FINDS) Research Center of Excellence (CoE), funded by the U.S. Army Research Laboratory, advances Digital Forensic Engineering Education (DFEE) through an integrated research education framework for AI enabled cybersecurity workforce development. FINDS combines high performance computing (HPC), secure software engineering, adversarial analytics, and experiential learning to address emerging cyber and synthetic media threats. This paper introduces the Multidependency Capacity Building Skills Graph (MCBSG), a directed acyclic graph based model that encodes hierarchical and cross domain dependencies among competencies in AI-driven forensic programming, statistical inference, digital evidence processing, and threat detection. The MCBSG enables structured modeling of skill acquisition pathways and quantitative capacity assessment. Supervised machine learning methods, including entropy-based Decision Tree Classifiers and regression modeling, are applied to longitudinal multi cohort datasets capturing mentoring interactions, laboratory performance metrics, curriculum artifacts, and workshop participation. Feature importance analysis and cross validation identify key predictors of technical proficiency and research readiness. Three year statistical evaluation demonstrates significant gains in forensic programming accuracy, adversarial reasoning, and HPC-enabled investigative workflows. Results validate the MCBSG as a scalable, interpretable framework for data-driven, inclusive cybersecurity education aligned with national defense workforce priorities. --- ### A medical coding language model trained on clinical narratives from a population-wide cohort of 1.8 million patients Authors: Joakim Edin, Sedrah Butt Balaganeshan, Annike Kjølby Kristensen, Lars Maaløe, Ioannis Louloudis, Søren Brunak Published: 2026-02-27 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.00221v2 Medical coding translates clinical documentation into standardized codes for billing, research, and public health, but manual coding is time-consuming and error-prone. Existing automation efforts rely on small datasets that poorly represent real-world patient heterogeneity. We trained a language model on 5.8 million electronic health records from 1.8 million patients across nearly all specialties in Eastern Denmark (2006--2016) to predict ICD-10 codes from clinical notes, medications, and laboratory results. Evaluated on 270,000 held-out patients, the model achieved a micro F1 of 71.8% and a top-10 recall of 95.5%. Performance varied by specialty (F1: 53--91%), with higher scores in specialties with well-defined diagnostic criteria. Codes appearing predominantly as secondary diagnoses had markedly lower F1 scores. For three such codes (suicide-related behaviors, weight disorders, and hypertension), the model identified thousands of uncoded cases, of which 76-86% were confirmed valid upon manual review, suggesting systematic under-coding rather than model error. These findings suggest under-coding of secondary diagnoses in Eastern Denmark during this period, with potential implications for epidemiological research, public health surveillance, and understanding of multimorbidity. Similar time constraints and reimbursement structures in other healthcare systems suggest this may not be isolated to this dataset. The model can automate coding for approximately 50% of cases and provide accurate suggestions for most others, and may offer a practical solution to help capture missed secondary conditions. --- ### GLIDE-Reg: Global-to-Local Deformable Registration Using Co-Optimized Foundation and Handcrafted Features Authors: Yunzheng Zhu, Aichi Chien, Kimaya kulkarni, Luoting Zhuang, Stephen Park, Ricky Savjani, Daniel Low, William Hsu Published: 2026-02-27 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2603.00218v2 Deformable registration is crucial in medical imaging. Several existing applications include lesion tracking, probabilistic atlas generation, and treatment response evaluation. However, current methods often lack robustness and generalizability across two key factors: spatial resolution and differences in anatomical coverage. We jointly optimize a registration field and a learnable dimensionality reduction module so that compressed VFM embeddings remain registration-relevant, and fuse these global semantic cues with MIND local descriptors. GLIDE-Reg achieves average dice similarity coefficients (DSC) across 6 anatomical structures of 0.859, 0.862, and 0.901 in two public cohorts (Lung250M and NLST) and one institution cohort (UCLA5DCT), and outperforms the state-of-the-art DEEDS (0.834, 0.858, 0.900) with relative improvements of 3.0%, 0.5%, and 0.1%. For target registration errors, GLIDE-Reg achieves 1.58 mm on Lung250M landmarks (compared to 1.25 mm on corrField and 1.91 mm on DEEDS) and 1.11 mm on NLST nodule centers (compared to 1.11 mm on DEEDS). The substantiated performance on the nodule centers also demonstrates its robustness across challenging downstream tasks, such as nodule tracking, which is an essential prior step for early-stage lung cancer diagnosis. --- ### Physical Evaluation of Naturalistic Adversarial Patches for Camera-Based Traffic-Sign Detection Authors: Brianna D'Urso, Tahmid Hasan Sakib, Syed Rafay Hasan, Terry N. Guo Published: 2026-02-27 Categories: cs.CV, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2603.00217v1 This paper studies how well Naturalistic Adversarial Patches (NAPs) transfer to a physical traffic sign setting when the detector is trained on a customized dataset for an autonomous vehicle (AV) environment. We construct a composite dataset, CompGTSRB (which is customized dataset for AV environment), by pasting traffic sign instances from the German Traffic Sign Recognition Benchmark (GTSRB) onto undistorted backgrounds captured from the target platform. CompGTSRB is used to train a YOLOv5 model and generate patches using a Generative Adversarial Network (GAN) with latent space optimization, following existing NAP methods. We carried out a series of experiments on our Quanser QCar testbed utilizing the front CSI camera provided in QCar. Across configurations, NAPs reduce the detector's STOP class confidence. Different configurations include distance, patch sizes, and patch placement. These results along with a detailed step-by-step methodology indicate the utility of CompGTSRB dataset and the proposed systematic physical protocols for credible patch evaluation. The research further motivate researching the defenses that address localized patch corruption in embedded perception pipelines. --- ### Agentic Scientific Simulation: Execution-Grounded Model Construction and Reconstruction Authors: Knut-Andreas Lie, Olav Møyner, Elling Svee, Jakob Torben Published: 2026-02-27 Categories: cs.SE, cs.AI, cs.MS, physics.geo-ph arXiv: https://arxiv.org/abs/2603.00214v1 LLM agents are increasingly used for code generation, but physics-based simulation poses a deeper challenge: natural-language descriptions of simulation models are inherently underspecified, and different admissible resolutions of implicit choices produce physically valid but scientifically distinct configurations. Without explicit detection and resolution of these ambiguities, neither the correctness of the result nor its reproducibility from the original description can be assured. This paper investigates agentic scientific simulation, where model construction is organized as an execution-grounded interpret-act-validate loop and the simulator serves as the authoritative arbiter of physical validity rather than merely a runtime. We present JutulGPT, a reference implementation built on the fully differentiable Julia-based reservoir simulator JutulDarcy. The agent combines structured retrieval of documentation and examples with code synthesis, static analysis, execution, and systematic interpretation of solver diagnostics. Underspecified modelling choices are detected explicitly and resolved either autonomously (with logged assumptions) or through targeted user queries. The results demonstrate that agent-mediated model construction can be grounded in simulator validation, while also revealing a structural limitation: choices resolved tacitly through simulator defaults are invisible to the assumption log and to any downstream representation. A secondary experiment with autonomous reconstruction of a reference model from progressively abstract textual descriptions shows that reconstruction variability exposes latent degrees of freedom in simulation descriptions and provides a practical methodology for auditing reproducibility. All code, prompts, and agent logs are publicly available. --- ### Universal NP-Hardness of Clustering under General Utilities Authors: Angshul Majumdar Published: 2026-02-27 Categories: cs.CC, cs.AI arXiv: https://arxiv.org/abs/2603.00210v2 Clustering is a central primitive in unsupervised learning, yet practice is dominated by heuristics whose outputs can be unstable and highly sensitive to representations, hyperparameters, and initialisation. Existing theoretical results are largely objective-specific and do not explain these behaviours at a unifying level. We formalise the common optimisation core underlying diverse clustering paradigms by defining the Universal Clustering Problem (UCP): the maximisation of a polynomial-time computable partition utility over a finite metric space. We prove the NP-hardness of UCP via two independent polynomial-time reductions from graph colouring and from exact cover by 3-sets (X3C). By mapping ten major paradigms -- including k-means, GMMs, DBSCAN, spectral clustering, and affinity propagation -- to the UCP framework, we demonstrate that each inherits this fundamental intractability. Our results provide a unified explanation for characteristic failure modes, such as local optima in alternating methods and greedy merge-order traps in hierarchical clustering. Finally, we show that clustering limitations reflect interacting computational and epistemic constraints, motivating a shift toward stability-aware objectives and interaction-driven formulations with explicit guarantees. --- ### Universal NP-Hardness of Clustering under General Utilities Authors: Angshul Majumdar Published: 2026-02-27 Categories: cs.CC, cs.AI arXiv: https://arxiv.org/abs/2603.00210v1 Clustering is a central primitive in unsupervised learning, yet practice is dominated by heuristics whose outputs can be unstable and highly sensitive to representations, hyperparameters, and initialisation. Existing theoretical results are largely objective-specific and do not explain these behaviours at a unifying level. We formalise the common optimisation core underlying diverse clustering paradigms by defining the Universal Clustering Problem (UCP): the maximisation of a polynomial-time computable partition utility over a finite metric space. We prove the NP-hardness of UCP via two independent polynomial-time reductions from graph colouring and from exact cover by 3-sets (X3C). By mapping ten major paradigms -- including k-means, GMMs, DBSCAN, spectral clustering, and affinity propagation -- to the UCP framework, we demonstrate that each inherits this fundamental intractability. Our results provide a unified explanation for characteristic failure modes, such as local optima in alternating methods and greedy merge-order traps in hierarchical clustering. Finally, we show that clustering limitations reflect interacting computational and epistemic constraints, motivating a shift toward stability-aware objectives and interaction-driven formulations with explicit guarantees. --- ### Tipping the Balance: Impact of Class Imbalance Correction on the Performance of Clinical Risk Prediction Models Authors: Amalie Koch Andersen, Hadi Mehdizavareh, Arijit Khan, Tobias Becher, Simone Britsch, Markward Britsch, Morten Bøttcher, Simon Winther, Palle Duun Rohde, Morten Hasselstrøm Jensen, Simon Lebech Cichosz Published: 2026-02-27 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2603.00208v1 Objective: ML-based clinical risk prediction models are increasingly used to support decision-making in healthcare. While class-imbalance correction techniques are commonly applied to improve model performance in settings with rare outcomes, their impact on probabilistic calibration remains insufficiently understood. This study evaluated the effect of widely used resampling strategies on both discrimination and calibration across real-world clinical prediction tasks. Methods: Ten clinical datasets spanning diverse medical domains and including 605,842 patients were analyzed. Multiple machine-learning model families, including linear models and several non-linear approaches, were evaluated. Models were trained on the original data and under three commonly used 1:1 class-imbalance correction strategies (SMOTE, RUS, ROS). Performance was assessed on held-out data using discrimination and calibration metrics. Results: Across all datasets and model families, resampling had no positive impact on predictive performance. Changes in the Receiver Operating Characteristic Area Under Curve (ROC-AUC) relative to models trained on the original data were small and inconsistent (ROS: -0.002, p<0.05; RUS: -0.004, p>0.05; SMOTE: -0.01, p<0.05), with no resampling strategy demonstrating a systematic improvement. In contrast, resampling in general degraded the calibration performance. Models trained using imbalance correction exhibited higher Brier scores (0.029 to 0.080, p<0.05), reflecting poorer probabilistic accuracy, and marked deviations in calibration intercept and slope, indicating systematic distortions of predicted risk despite preserved rank-based performance. Conclusion: In a diverse set of real-world clinical prediction tasks, commonly used class-imbalance correction techniques did not provide generalizable improvements in discrimination and were associated with degraded calibration. --- ### VisRef: Visual Refocusing while Thinking Improves Test-Time Scaling in Multi-Modal Large Reasoning Models Authors: Soumya Suvra Ghosal, Youngeun Kim, Zhuowei Li, Ritwick Chaudhry, Linghan Xu, Hongjing Zhang, Jakub Zablocki, Yifan Xing, Qin Zhang Published: 2026-02-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00207v1 Advances in large reasoning models have shown strong performance on complex reasoning tasks by scaling test-time compute through extended reasoning. However, recent studies observe that in vision-dependent tasks, extended textual reasoning at inference time can degrade performance as models progressively lose attention to visual tokens and increasingly rely on textual priors alone. To address this, prior works use reinforcement learning (RL)-based fine-tuning to route visual tokens or employ refocusing mechanisms during reasoning. While effective, these methods are computationally expensive, requiring large-scale data generation and policy optimization. To leverage the benefits of test-time compute without additional RL fine-tuning, we propose VisRef, a visually grounded test-time scaling framework. Our key idea is to actively guide the reasoning process by re-injecting a coreset of visual tokens that are semantically relevant to the reasoning context while remaining diverse and globally representative of the image, enabling more grounded multi-modal reasoning. Experiments on three visual reasoning benchmarks with state-of-the-art multi-modal large reasoning models demonstrate that, under fixed test-time compute budgets, VisRef consistently outperforms existing test-time scaling approaches by up to 6.4%. --- ### TACIT Benchmark: A Programmatic Visual Reasoning Benchmark for Generative and Discriminative Models Authors: Daniel Nobrega Medeiros Published: 2026-02-27 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.00206v1 Existing visual reasoning benchmarks predominantly rely on natural language prompts, evaluate narrow reasoning modalities, or depend on subjective scoring procedures such as LLM-as-judge. We introduce the TACIT Benchmark, a programmatic visual reasoning benchmark comprising 10 tasks across 6 reasoning domains: spatial navigation, abstract pattern completion, causal simulation, logical constraint satisfaction, graph theory, and topology. The benchmark provides dual-track evaluation: a generative track in which models must produce solution images verified through deterministic computer-vision pipelines, and a discriminative track offering five-way multiple choice with structurally plausible near-miss distractors. Each distractor violates exactly one structural constraint, requiring models to reason about fine-grained visual differences rather than exploit superficial cues. Version 0.1.0 distributes 6,000 puzzles (108,000 PNG images across three resolutions) with fully deterministic seeded generation and reproducible verification. The dataset, generation code, and evaluation harness are released under the Apache 2.0 license on HuggingFace (DOI: 10.57967/hf/7904). --- ### Efficient Flow Matching for Sparse-View CT Reconstruction Authors: Jiayang Shi, Lincen Yang, Zhong Li, Tristan van Leeuwen, Daniel M. Pelt, K. Joost Batenburg Published: 2026-02-27 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.00205v2 Generative models, particularly Diffusion Models (DM), have shown strong potential for Computed Tomography (CT) reconstruction serving as expressive priors for solving ill-posed inverse problems. However, diffusion-based reconstruction relies on Stochastic Differential Equations (SDEs) for forward diffusion and reverse denoising, where such stochasticity can interfere with repeated data consistency corrections in CT reconstruction. Since CT reconstruction is often time-critical in clinical and interventional scenarios, improving reconstruction efficiency is essential. In contrast, Flow Matching (FM) models sampling as a deterministic Ordinary Differential Equation (ODE), yielding smooth trajectories without stochastic noise injection. This deterministic formulation is naturally compatible with repeated data consistency operations. Furthermore, we observe that FM-predicted velocity fields exhibit strong correlations across adjacent steps. Motivated by this, we propose an FM-based CT reconstruction framework (FMCT) and an efficient variant (EFMCT) that reuses previously predicted velocity fields over consecutive steps to substantially reduce the number of Neural network Function Evaluations (NFEs), thereby improving inference efficiency. We provide theoretical analysis showing that the error introduced by velocity reuse is bounded when combined with data consistency operations. Extensive experiments demonstrate that FMCT/EFMCT achieve competitive reconstruction quality while significantly improving computational efficiency compared with diffusion-based methods. The codebase is open-sourced at https://github.com/EFMCT/EFMCT. ---