# Research Papers — 2026-02 · bundle page 59 of 210 > Full-text markdown of papers #2901–2950 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/59 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/58.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/60.md) ### PHAST: Port-Hamiltonian Architecture for Structured Temporal Dynamics Forecasting Authors: Shubham Bhardwaj, Chandrajit Bajaj Published: 2026-02-20 Categories: cs.LG, cs.AI, cs.CE, eess.SY arXiv: https://arxiv.org/abs/2602.17998v1 Real physical systems are dissipative -- a pendulum slows, a circuit loses charge to heat -- and forecasting their dynamics from partial observations is a central challenge in scientific machine learning. We address the \emph{position-only} (q-only) problem: given only generalized positions~$q_t$ at discrete times (momenta~$p_t$ latent), learn a structured model that (a)~produces stable long-horizon forecasts and (b)~recovers physically meaningful parameters when sufficient structure is provided. The port-Hamiltonian framework makes the conservative-dissipative split explicit via $\dot{x}=(J-R)\nabla H(x)$, guaranteeing $dH/dt\le 0$ when $R\succeq 0$. We introduce \textbf{PHAST} (Port-Hamiltonian Architecture for Structured Temporal dynamics), which decomposes the Hamiltonian into potential~$V(q)$, mass~$M(q)$, and damping~$D(q)$ across three knowledge regimes (KNOWN, PARTIAL, UNKNOWN), uses efficient low-rank PSD/SPD parameterizations, and advances dynamics with Strang splitting. Across thirteen q-only benchmarks spanning mechanical, electrical, molecular, thermal, gravitational, and ecological systems, PHAST achieves the best long-horizon forecasting among competitive baselines and enables physically meaningful parameter recovery when the regime provides sufficient anchors. We show that identification is fundamentally ill-posed without such anchors (gauge freedom), motivating a two-axis evaluation that separates forecasting stability from identifiability. --- ### Whole-Brain Connectomic Graph Model Enables Whole-Body Locomotion Control in Fruit Fly Authors: Zehao Jin, Yaoye Zhu, Chen Zhang, Yanan Sui Published: 2026-02-20 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2602.17997v3 Animals perform coordinated whole-body movements under the control of neural systems shaped by brain-wide connectivity. The mapping of the whole-brain neural connections, or the connectomes, provides a natural graph for modeling sensorimotor information flow, yet its potential as a neural controller for embodied agents remains largely unexplored. Here, we introduce the Fly-connectomic Graph Model, which directly instantiates the whole-brain connectome of an adult Drosophila as a graph-structured neural controller for movements of a simulated biomechanical fruit fly via deep reinforcement learning. We achieve stable performance across diverse locomotion tasks, as well as better sample efficiency compared to both graph and non-graph baselines. Our results demonstrate a biologically informed way towards effective control policy design by translating whole-brain wiring principles into actionable architectural priors, while also improving the interpretability through dynamic information flow. This work also highlights the potential to bridge neuromechanics with embodied intelligence by providing a computational platform for investigating the sensorimotor transformation underlying animal behavior and a paradigm to advance the development of more nature-aligned intelligent systems. --- ### Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers Authors: Mohan Tang, Sidi Lu Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17993v2 Complex problems, whether in math, logic, or planning, are solved by humans through a sequence of steps where the result of one step informs the next. In this work, we adopt the perspective that the reasoning power of Transformers is fundamentally limited by a fixed maximum number of steps along any latent path of computation. To address this, we introduce Turbo Connection (TurboConn), a novel architecture that overcomes the fixed-depth constraint by routing multiple residual connections from the higher-layer hidden states of each token $t$ to the lower layers of token $t+1$. Fine-tuning pre-trained LLMs with our method not only yields accuracy gains of 0.9% to over 10% on benchmarks like GSM8K, Parity, and multi-step arithmetic, but also demonstrates that the density of these backward connections is critical; our dense interaction significantly outperforms "sparse" alternatives that only pass a single hidden state or vector. Notably, TurboConn can be integrated into pre-trained LLMs to overcome task-specific plateaus: while a fine-tuned Qwen-3-1.7B achieves only 53.78% on Parity, adding our architectural modification enables the model to reach 100% accuracy, all without the necessity to retrain the full model from scratch or sophisticated curriculum learning. Our results provide strong empirical evidence that the depth of the computational path is a key factor in reasoning ability, also offering a new mechanism to enhance LLMs without significantly affecting generation latency. --- ### WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics Authors: Madhav Kanda, Sharad Agarwal, Rodrigo Fonseca, Alok Gautam Kumbhare, Pedro Las-Casas Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.17990v3 Multi-agent LLM systems that generate structured workflows from natural-language requests are now deployed in production across cloud automation, DevOps, and enterprise orchestration. Operating them exposes a recurring change-management problem. Routine updates, such as re-running an input, swapping the LLM, or refactoring an agent's prompt or orchestration code, often produce workflows that differ substantially from validated references. Engineers then lack a principled way to decide whether a change is safe to ship. Automatic workflow evaluation is the natural tool, but in practice metric scores are poorly calibrated, and a numeric change rarely communicates the severity of the underlying degradation. We introduce WorkflowPerturb, a controlled benchmark that applies realistic, graded perturbations to golden workflows. It contains 4,973 golden workflows and 44,757 perturbed variants across three perturbation types (Missing Steps, Compressed Steps, Description Changes) at severities of 10%, 30%, and 50%. We benchmark multiple metric families, analyzing their sensitivity and calibration using expected score trajectories and instance-level alert rates. Our results characterize systematic differences across families and support severity-aware interpretation of workflow evaluation scores in change-management settings. WorkflowPerturb is publicly available at https://huggingface.co/datasets/microsoft/WorkflowPerturb . --- ### WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics Authors: Madhav Kanda, Sharad Agarwal, Rodrigo Fonseca, Alok Gautam Kumbhare, Pedro Las-Casas Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.17990v2 Multi-agent LLM systems that generate structured workflows from natural-language requests are now deployed in production across cloud automation, DevOps, and enterprise process orchestration. Operating such systems exposes a recurring change-management problem. Routine updates, such as re-running the same input, swapping the underlying LLM, or refactoring an agent's prompt or orchestration code, frequently produce workflows that differ substantially from previously validated references. Engineers are then left without a principled way to decide whether a change is safe to ship. Automatic workflow evaluation is the natural tool for answering this question. In practice, however, metric scores are poorly calibrated, and a numeric change rarely communicates the severity of the underlying degradation. We introduce WorkflowPerturb, a controlled benchmark for studying workflow evaluation metrics by applying realistic, graded perturbations to golden workflows. WorkflowPerturb contains 4,973 golden workflows and 44,757 perturbed variants across three perturbation types (Missing Steps, Compressed Steps, and Description Changes), each applied at severity levels of 10%, 30%, and 50%. We benchmark multiple metric families and analyze their sensitivity and calibration using expected score trajectories and residuals. Our results characterize systematic differences across metric families and support severity-aware interpretation of workflow evaluation scores in change-management settings. Our dataset will be released upon acceptance. --- ### From Global Radiomics to Parametric Maps: A Unified Workflow Fusing Radiomics and Deep Learning for PDAC Detection Authors: Zengtian Deng, Yimeng He, Yu Shi, Lixia Wang, Touseef Ahmad Qureshi, Xiuzhen Huang, Debiao Li Published: 2026-02-20 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.17986v1 Radiomics and deep learning both offer powerful tools for quantitative medical imaging, but most existing fusion approaches only leverage global radiomic features and overlook the complementary value of spatially resolved radiomic parametric maps. We propose a unified framework that first selects discriminative radiomic features and then injects them into a radiomics-enhanced nnUNet at both the global and voxel levels for pancreatic ductal adenocarcinoma (PDAC) detection. On the PANORAMA dataset, our method achieved AUC = 0.96 and AP = 0.84 in cross-validation. On an external in-house cohort, it achieved AUC = 0.95 and AP = 0.78, outperforming the baseline nnUNet; it also ranked second in the PANORAMA Grand Challenge. This demonstrates that handcrafted radiomics, when injected at both global and voxel levels, provide complementary signals to deep learning models for PDAC detection. Our code can be found at https://github.com/briandzt/dl-pdac-radiomics-global-n-paramaps --- ### Learning Without Training Authors: Ryan O'Dowd Published: 2026-02-20 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.17985v1 Machine learning is at the heart of managing the real-world problems associated with massive data. With the success of neural networks on such large-scale problems, more research in machine learning is being conducted now than ever before. This dissertation focuses on three different projects rooted in mathematical theory for machine learning applications. The first project deals with supervised learning and manifold learning. In theory, one of the main problems in supervised learning is that of function approximation: that is, given some data set $\mathcal{D}=\{(x_j,f(x_j))\}_{j=1}^M$, can one build a model $F\approx f$? We introduce a method which aims to remedy several of the theoretical shortcomings of the current paradigm for supervised learning. The second project deals with transfer learning, which is the study of how an approximation process or model learned on one domain can be leveraged to improve the approximation on another domain. We study such liftings of functions when the data is assumed to be known only on a part of the whole domain. We are interested in determining subsets of the target data space on which the lifting can be defined, and how the local smoothness of the function and its lifting are related. The third project is concerned with the classification task in machine learning, particularly in the active learning paradigm. Classification has often been treated as an approximation problem as well, but we propose an alternative approach leveraging techniques originally introduced for signal separation problems. We introduce theory to unify signal separation with classification and a new algorithm which yields competitive accuracy to other recent active learning algorithms while providing results much faster. --- ### Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering Authors: Amine Kobeissi, Philippe Langlais Published: 2026-02-20 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.17981v1 Retrieval-augmented generation is increasingly used for financial question answering over long regulatory filings, yet reliability depends on retrieving the exact context needed to justify answers in high stakes settings. We study a frequent failure mode in which the correct document is retrieved but the page or chunk that contains the answer is missed, leading the generator to extrapolate from incomplete context. Despite its practical significance, this within-document retrieval failure mode has received limited systematic attention in the Financial Question Answering (QA) literature. We evaluate retrieval at multiple levels of granularity, document, page, and chunk level, and introduce an oracle based analysis to provide empirical upper bounds on retrieval and generative performance. On a 150 question subset of FinanceBench, we reproduce and compare diverse retrieval strategies including dense, sparse, hybrid, and hierarchical methods with reranking and query reformulation. Across methods, gains in document discovery tend to translate into stronger page recall, yet oracle performance still suggests headroom for page and chunk level retrieval. To target this gap, we introduce a domain fine-tuned page scorer that treats pages as an intermediate retrieval unit between documents and chunks. Unlike prior passage-based hierarchical retrieval, we fine-tune a bi-encoder specifically for page-level relevance on financial filings, exploiting the semantic coherence of pages. Overall, our results demonstrate a significant improvement in page recall and chunk retrieval. --- ### Learning Optimal and Sample-Efficient Decision Policies with Guarantees Authors: Daqian Shao Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17978v1 The paradigm of decision-making has been revolutionised by reinforcement learning and deep learning. Although this has led to significant progress in domains such as robotics, healthcare, and finance, the use of RL in practice is challenging, particularly when learning decision policies in high-stakes applications that may require guarantees. Traditional RL algorithms rely on a large number of online interactions with the environment, which is problematic in scenarios where online interactions are costly, dangerous, or infeasible. However, learning from offline datasets is hindered by the presence of hidden confounders. Such confounders can cause spurious correlations in the dataset and can mislead the agent into taking suboptimal or adversarial actions. Firstly, we address the problem of learning from offline datasets in the presence of hidden confounders. We work with instrumental variables (IVs) to identify the causal effect, which is an instance of a conditional moment restrictions (CMR) problem. Inspired by double/debiased machine learning, we derive a sample-efficient algorithm for solving CMR problems with convergence and optimality guarantees, which outperforms state-of-the-art algorithms. Secondly, we relax the conditions on the hidden confounders in the setting of (offline) imitation learning, and adapt our CMR estimator to derive an algorithm that can learn effective imitator policies with convergence rate guarantees. Finally, we consider the problem of learning high-level objectives expressed in linear temporal logic (LTL) and develop a provably optimal learning algorithm that improves sample efficiency over existing methods. Through evaluation on reinforcement learning benchmarks and synthetic and semi-synthetic datasets, we demonstrate the usefulness of the methods developed in this thesis in real-world decision making. --- ### In-Context Pure Exploration in Continuous Decision Spaces Authors: Alessio Russo, Yin-Ching Lee, Ryan Welch, Aldo Pacchiano Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17976v2 In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information so as to identify an unknown ground-truth hypothesis with as few queries as possible. This problem has several motivating applications, including Best-Arm Identification (BAI) in bandits, where actions index hypotheses, and generalized search problems, where strategically chosen queries reveal partial information about a hidden label. In many modern settings, however, the hypothesis, or recommendation space, is continuous: for example, identifying a near optimal action in a continuous-armed bandit, localizing an $ε$-ball contained in a target region, or estimating the minimizer of a function from noisy observations. Existing methods are predominantly frequentist and model-specific, while learned approaches have been limited to finite recommendation spaces. We introduce C-ICPE, a theory-guided learned model for Bayesian fixed-confidence pure exploration with continuous recommendations. C-ICPE meta-trains sequential architectures over a task prior to jointly learn exploration, stopping and recommendations strategies. At inference time, it actively gathers evidence on tasks and identifies an $ε$-optimal recommendation without parameter updates. --- ### Generating adversarial inputs for a graph neural network model of AC power flow Authors: Robert Parker Published: 2026-02-20 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2602.17975v2 This work formulates and solves optimization problems to generate input points that yield high errors between a neural network's predicted AC power flow solution and solutions to the AC power flow equations. We demonstrate this capability on an instance of the CANOS-PF graph neural network model, as implemented by the PF$Δ$ benchmark library, operating on a 14-bus test grid. Generated adversarial points yield errors as large as 3.7 per-unit in reactive power and 0.08 per-unit in voltage magnitude. When minimizing the perturbation from a training point necessary to satisfy adversarial constraints, we find that the constraints can be met with as little as an 0.04 per-unit perturbation in voltage magnitude on a single bus. This work motivates the development of rigorous verification and robust training methods for neural network surrogate models of AC power flow. --- ### PenTiDef: Decentralized Federated Intrusion Detection System with Differential Privacy and Latent-Space Defense via Blockchain Coordination in IIoT Authors: Phan The Duy, Nghi Hoang Khoa, Nguyen Tran Anh Quan, Luong Ha Tien, Ngo Duc Hoang Son, Van-Hau Pham Published: 2026-02-20 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.17973v2 This paper proposes PenTiDef, a fully decentralized, privacy-preserving, and poisoning-resilient framework for decentralized federated IDS (DFL-IDS). PenTiDef synergistically integrates three key components: (i) client-side Distributed Differential Privacy (DDP) with stochastic Gaussian noise to protect gradient leakage, (ii) a lightweight latent-space defense module that extracts and compresses penultimate-layer representations (PLRs) into stable Latent Semantic Representations (LSRs) via AutoEncoder, followed by Centered Kernel Alignment (CKA) and K-Means clustering for robust malicious update detection without auxiliary datasets, and (iii) a permissioned blockchain layer with smart contracts that orchestrates on-chain validation, secure FedAvg aggregation, and immutable auditability, eliminating any central server. Extensive experiments on CIC-IDS2018 and Edge-IIoTSet under both IID and realistic non-IID settings, with adversary ratios up to 40\%, demonstrate that PenTiDef consistently outperforms state-of-the-art baselines (FLARE and FedCC) in detection accuracy and F1-score while maintaining lower training overhead. By jointly addressing privacy, robustness, and decentralization in a unified secure aggregation protocol, PenTiDef provides a practical and scalable solution for trustworthy collaborative intrusion detection in heterogeneous, adversarial IIoT environments. --- ### Student Flow Modeling for School Decongestion via Stochastic Gravity Estimation and Constrained Spatial Allocation Authors: Sebastian Felipe R. Bundoc, Paula Joy B. Martinez, Sebastian C. Ibañez, Erika Fille T. Legara Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17972v1 School congestion, where student enrollment exceeds school capacity, is a major challenge in low- and middle-income countries. It highly impacts learning outcomes and deepens inequities in education. While subsidy programs that transfer students from public to private schools offer a mechanism to alleviate congestion without capital-intensive construction, they often underperform due to fragmented data systems that hinder effective implementation. The Philippine Educational Service Contracting program, one of the world's largest educational subsidy programs, exemplifies these challenges, falling short of its goal to decongest public schools. This prevents the science-based and data-driven analyses needed to understand what shapes student enrollment flows, particularly how families respond to economic incentives and spatial constraints. We introduce a computational framework for modeling student flow patterns and simulating policy scenarios. By synthesizing heterogeneous government data across nearly 3,000 institutions, we employ a stochastic gravity model estimated via negative binomial regression to derive behavioral elasticities for distance, net tuition cost, and socioeconomic determinants. These elasticities inform a doubly constrained spatial allocation mechanism that simulates student redistribution under varying subsidy amounts while respecting both origin candidate pools and destination slot capacities. We find that geographic proximity constrains school choice four times more strongly than tuition cost and that slot capacity, not subsidy amounts, is the binding constraint. Our work demonstrates that subsidy programs alone cannot resolve systemic overcrowding, and computational modeling can empower education policymakers to make equitable, data-driven decisions by revealing the structural constraints that shape effective resource allocation, even when resources are limited. --- ### Minimax optimal adaptive structured transfer learning through semi-parametric domain-varying coefficient model Authors: Hanxiao Chen, Debarghya Mukherjee Published: 2026-02-20 Categories: math.ST, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2602.17967v1 Transfer learning aims to improve inference in a target domain by leveraging information from related source domains, but its effectiveness critically depends on how cross-domain heterogeneity is modeled and controlled. When the conditional mechanism linking covariates and responses varies across domains, indiscriminate information pooling can lead to negative transfer, degrading performance relative to target-only estimation. We study a multi-source, single-target transfer learning problem under conditional distributional drift and propose a semiparametric domain-varying coefficient model (DVCM), in which domain-relatedness is encoded through an observable domain identifier. This framework generalizes classical varying-coefficient models to structured transfer learning and interpolates between invariant and fully heterogeneous regimes. Building on this model, we develop an adaptive transfer learning estimator that selectively borrows strength from informative source domains while provably safeguarding against negative transfer. Our estimator is computationally efficient and easy to implement; we also show that it is minimax rate-optimal and derive its asymptotic distribution, enabling valid uncertainty quantification and hypothesis testing despite data-adaptive pooling and shrinkage. Our results precisely characterize the interplay among domain heterogeneity, the smoothness of the underlying mean function, and the number of source domains and are corroborated by comprehensive numerical experiments and two real-data applications. --- ### Improving Generalizability of Hip Fracture Risk Prediction via Domain Adaptation Across Multiple Cohorts Authors: Shuo Sun, Meiling Zhou, Chen Zhao, Joyce H. Keyak, Nancy E. Lane, Jeffrey D. Deng, Kuan-Jui Su, Hui Shen, Hong-Wen Deng, Kui Zhang, Weihua Zhou Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17962v1 Clinical risk prediction models often fail to be generalized across cohorts because underlying data distributions differ by clinical site, region, demographics, and measurement protocols. This limitation is particularly pronounced in hip fracture risk prediction, where the performance of models trained on one cohort (the source cohort) can degrade substantially when deployed in other cohorts (target cohorts). We used a shared set of clinical and DXA-derived features across three large cohorts - the Study of Osteoporotic Fractures (SOF), the Osteoporotic Fractures in Men Study (MrOS), and the UK Biobank (UKB), to systematically evaluate the performance of three domain adaptation methods - Maximum Mean Discrepancy (MMD), Correlation Alignment (CORAL), and Domain - Adversarial Neural Networks (DANN) and their combinations. For a source cohort with males only and a source cohort with females only, domain-adaptation methods consistently showed improved performance than the no-adaptation baseline (source-only training), and the use of combinations of multiple domain adaptation methods delivered the largest and most stable gains. The method that combines MMD, CORAL, and DANN achieved the highest discrimination with the area under curve (AUC) of 0.88 for a source cohort with males only and 0.95 for a source cohort with females only), demonstrating that integrating multiple domain adaptation methods could produce feature representations that are less sensitive to dataset differences. Unlike existing methods that rely heavily on supervised tuning or assume known outcomes of samples in target cohorts, our outcome-free approaches enable the model selection under realistic deployment conditions and improve generalization of models in hip fracture risk prediction. --- ### Anisotropic local law for non-separable sample covariance matrices Authors: Zhou Fan, Renyuan Ma, Elliot Paquette, Zhichao Wang Published: 2026-02-20 Categories: math.PR, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2602.17960v2 We establish local laws for sample covariance matrices $K = N^{-1}\sum_{i=1}^N \g_i\g_i^*$ where the random vectors $\g_1, \ldots, \g_N \in \R^n$ are independent with common covariance $Σ$. Previous work has largely focused on the separable model $\g = Σ^{1/2}\w$ with $\w$ having independent entries, but this structure is rarely present in statistical applications involving dependent or nonlinearly transformed data. Under a concentration assumption for quadratic forms $\g^*A\g$, we prove an optimal averaged local law showing that the Stieltjes transform of $K$ converges to its deterministic limit uniformly down to the optimal scale $η\geq N^{-1+\eps}$. Under an additional structural assumption on the cumulant tensors of $\g$ -- which interpolates between the highly structured case of independent entries and generic dependence -- we establish the full anisotropic local law, providing entrywise control of the resolvent $(K-zI)^{-1}$ in arbitrary directions. We discuss several classes of non-separable examples satisfying our assumptions, including conditionally mean-zero distributions, the random features model $\g = σ(X\w)$ arising in machine learning, and Gaussian measures with nonlinear tilting. The proofs introduce a tensor network framework for analyzing fluctuation averaging in the presence of higher-order cumulant structure. --- ### Bayesian Online Model Selection Authors: Aida Afshar, Yuke Zhang, Aldo Pacchiano Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17958v1 Online model selection in Bayesian bandits raises a fundamental exploration challenge: When an environment instance is sampled from a prior distribution, how can we design an adaptive strategy that explores multiple bandit learners and competes with the best one in hindsight? We address this problem by introducing a new Bayesian algorithm for online model selection in stochastic bandits. We prove an oracle-style guarantee of $O\left( d^* M \sqrt{T} + \sqrt{(MT)} \right)$ on the Bayesian regret, where $M$ is the number of base learners, $d^*$ is the regret coefficient of the optimal base learner, and $T$ is the time horizon. We also validate our method empirically across a range of stochastic bandit settings, demonstrating performance that is competitive with the best base learner. Additionally, we study the effect of sharing data among base learners and its role in mitigating prior mis-specification. --- ### Hardware-Friendly Input Expansion for Accelerating Function Approximation Authors: Hu Lou, Yin-Jun Gao, Dong-Xiao Zhang, Tai-Jiao Du, Jun-Jie Zhang, Jia-Rui Zhang Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17952v1 One-dimensional function approximation is a fundamental problem in scientific computing and engineering applications. While neural networks possess powerful universal approximation capabilities, their optimization process is often hindered by flat loss landscapes induced by parameter-space symmetries, leading to slow convergence and poor generalization, particularly for high-frequency components. Inspired by the principle of \emph{symmetry breaking} in physics, this paper proposes a hardware-friendly approach for function approximation through \emph{input-space expansion}. The core idea involves augmenting the original one-dimensional input (e.g., $x$) with constant values (e.g., $π$) to form a higher-dimensional vector (e.g., $(π, π, x, π, π)$), effectively breaking parameter symmetries without increasing the network's parameter count. We evaluate the method on ten representative one-dimensional functions, including smooth, discontinuous, high-frequency, and non-differentiable functions. Experimental results demonstrate that input-space expansion significantly accelerates training convergence (reducing LBFGS iterations by 12\% on average) and enhances approximation accuracy (reducing final MSE by 66.3\% for the optimal 5D expansion). Ablation studies further reveal the effects of different expansion dimensions and constant selections, with $π$ consistently outperforming other constants. Our work proposes a low-cost, efficient, and hardware-friendly technique for algorithm design. --- ### ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models Authors: Guoheng Sun, Tingting Du, Kaixi Feng, Chenxiang Luo, Xingguo Ding, Zheyu Shen, Ziyao Wang, Yexiao He, Ang Li Published: 2026-02-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.17951v1 Vision-Language-Action (VLA) models enable instruction-following robotic manipulation, but they are typically pretrained on 2D data and lack 3D spatial understanding. An effective approach is representation alignment, where a strong vision foundation model is used to guide a 2D VLA model. However, existing methods usually apply supervision at only a single layer, failing to fully exploit the rich information distributed across depth; meanwhile, naïve multi-layer alignment can cause gradient interference. We introduce ROCKET, a residual-oriented multi-layer representation alignment framework that formulates multi-layer alignment as aligning one residual stream to another. Concretely, ROCKET employs a shared projector to align multiple layers of the VLA backbone with multiple layers of a powerful 3D vision foundation model via a layer-invariant mapping, which reduces gradient conflicts. We provide both theoretical justification and empirical analyses showing that a shared projector is sufficient and outperforms prior designs, and further propose a Matryoshka-style sparse activation scheme for the shared projector to balance multiple alignment losses. Our experiments show that, combined with a training-free layer selection strategy, ROCKET requires only about 4% of the compute budget while achieving 98.5% state-of-the-art success rate on LIBERO. We further demonstrate the superior performance of ROCKET across LIBERO-Plus and RoboTwin, as well as multiple VLA models. The code and model weights can be found at https://github.com/CASE-Lab-UMD/ROCKET-VLA. --- ### CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications Authors: Victoria Blake, Jamie Novak, Mathew Miller, Sze-yuan Ooi, Blanca Gallego Published: 2026-02-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.17949v2 Background: Clinical named entity recognition tools commonly map free text to Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs). For many downstream tasks, however, the clinically meaningful unit is not a single CUI but a concept set comprising related synonyms, subtypes, and associated concepts. Constructing these sets is labour-intensive, inconsistently performed, and poorly supported by existing tools. Methods We present CUICurate, a graph-based retrieval-augmented generation (GraphRAG) framework for automated UMLS concept set curation. A UMLS knowledge graph (KG) was constructed and embedded for semantic retrieval. Candidate CUIs were retrieved using graph-based expansion and then filtered and classified using large language models (GPT-5 and Qwen3-32B). The framework was evaluated on five lexically heterogeneous clinical concepts against a manually curated concept sets and gold-standard concept sets. Results CUICurate produced substantially larger and more complete concept sets than the manual benchmarks. A single retrieval configuration across concepts achieved high recall of definitive concepts with manageable candidate sets. GPT-5 outperformed manual curation for all concepts and retained at least 95% of definitive gold-standard CUIs, while Qwen3-32B achieved comparable but slightly lower performance. Many missed concepts were not observed in 10,000 MIMIC-III notes. CUICurate infrastructure and end-to-end processing was inexpensive and stable across runs. Conclusions CUICurate offers a scalable, reproducible and cost-efficient approach for generating clinician-reviewable UMLS concept sets tailored to clinical natural language processing and phenotyping applications. --- ### A Geometric Probe of the Accuracy-Robustness Trade-off: Sharp Boundaries in Symmetry-Breaking Dimensional Expansion Authors: Yu Bai, Zhe Wang, Jiarui Zhang, Dong-Xiao Zhang, Yinjun Gao, Jun-Jie Zhang Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17948v1 The trade-off between clean accuracy and adversarial robustness is a pervasive phenomenon in deep learning, yet its geometric origin remains elusive. In this work, we utilize Symmetry-Breaking Dimensional Expansion (SBDE) as a controlled probe to investigate the mechanism underlying this trade-off. SBDE expands input images by inserting constant-valued pixels, which breaks translational symmetry and consistently improves clean accuracy (e.g., from $90.47\%$ to $95.63\%$ on CIFAR-10 with ResNet-18) by reducing parameter degeneracy. However, this accuracy gain comes at the cost of reduced robustness against iterative white-box attacks. By employing a test-time \emph{mask projection} that resets the inserted auxiliary pixels to their training values, we demonstrate that the vulnerability stems almost entirely from the inserted dimensions. The projection effectively neutralizes the attacks and restores robustness, revealing that the model achieves high accuracy by creating \emph{sharp boundaries} (steep loss gradients) specifically along the auxiliary axes. Our findings provide a concrete geometric explanation for the accuracy-robustness paradox: the optimization landscape deepens the basin of attraction to improve accuracy but inevitably erects steep walls along the auxiliary degrees of freedom, creating a fragile sensitivity to off-manifold perturbations. --- ### Understanding the Generalization of Bilevel Programming in Hyperparameter Optimization: A Tale of Bias-Variance Decomposition Authors: Yubo Zhou, Jun Shu, Junmin Liu, Deyu Meng Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17947v1 Gradient-based hyperparameter optimization (HPO) have emerged recently, leveraging bilevel programming techniques to optimize hyperparameter by estimating hypergradient w.r.t. validation loss. Nevertheless, previous theoretical works mainly focus on reducing the gap between the estimation and ground-truth (i.e., the bias), while ignoring the error due to data distribution (i.e., the variance), which degrades performance. To address this issue, we conduct a bias-variance decomposition for hypergradient estimation error and provide a supplemental detailed analysis of the variance term ignored by previous works. We also present a comprehensive analysis of the error bounds for hypergradient estimation. This facilitates an easy explanation of some phenomena commonly observed in practice, like overfitting to the validation set. Inspired by the derived theories, we propose an ensemble hypergradient strategy to reduce the variance in HPO algorithms effectively. Experimental results on tasks including regularization hyperparameter learning, data hyper-cleaning, and few-shot learning demonstrate that our variance reduction strategy improves hypergradient estimation. To explain the improved performance, we establish a connection between excess error and hypergradient estimation, offering some understanding of empirical observations. --- ### Optimizing Graph Causal Classification Models: Estimating Causal Effects and Addressing Confounders Authors: Simi Job, Xiaohui Tao, Taotao Cai, Haoran Xie, Jianming Yong, Xin Wang Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17941v1 Graph data is becoming increasingly prevalent due to the growing demand for relational insights in AI across various domains. Organizations regularly use graph data to solve complex problems involving relationships and connections. Causal learning is especially important in this context, since it helps to understand cause-effect relationships rather than mere associations. Since many real-world systems are inherently causal, graphs can efficiently model these systems. However, traditional graph machine learning methods including graph neural networks (GNNs), rely on correlations and are sensitive to spurious patterns and distribution changes. On the other hand, causal models enable robust predictions by isolating true causal factors, thus making them more stable under such shifts. Causal learning also helps in identifying and adjusting for confounders, ensuring that predictions reflect true causal relationships and remain accurate even under interventions. To address these challenges and build models that are robust and causally informed, we propose CCAGNN, a Confounder-Aware causal GNN framework that incorporates causal reasoning into graph learning, supporting counterfactual reasoning and providing reliable predictions in real-world settings. Comprehensive experiments on six publicly available datasets from diverse domains show that CCAGNN consistently outperforms leading state-of-the-art models. --- ### Tighter Regret Lower Bound for Gaussian Process Bandits with Squared Exponential Kernel in Hypersphere Authors: Shogo Iwazaki Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.17940v1 We study an algorithm-independent, worst-case lower bound for the Gaussian process (GP) bandit problem in the frequentist setting, where the reward function is fixed and has a bounded norm in the known reproducing kernel Hilbert space (RKHS). Specifically, we focus on the squared exponential (SE) kernel, one of the most widely used kernel functions in GP bandits. One of the remaining open questions for this problem is the gap in the \emph{dimension-dependent} logarithmic factors between upper and lower bounds. This paper partially resolves this open question under a hyperspherical input domain. We show that any algorithm suffers $Ω(\sqrt{T (\ln T)^{d} (\ln \ln T)^{-d}})$ cumulative regret, where $T$ and $d$ represent the total number of steps and the dimension of the hyperspherical domain, respectively. Regarding the simple regret, we show that any algorithm requires $Ω(ε^{-2}(\ln \frac{1}ε)^d (\ln \ln \frac{1}ε)^{-d})$ time steps to find an $ε$-optimal point. We also provide the improved $O((\ln T)^{d+1}(\ln \ln T)^{-d})$ upper bound on the maximum information gain for the SE kernel. Our results guarantee the optimality of the existing best algorithm up to \emph{dimension-independent} logarithmic factors under a hyperspherical input domain. --- ### Analyzing LLM Instruction Optimization for Tabular Fact Verification Authors: Xiaotang Du, Giwon Hong, Wai-Chung Kwan, Rohit Saxena, Ivan Titov, Pasquale Minervini, Emily Allaway Published: 2026-02-20 Categories: cs.CL, cs.PL arXiv: https://arxiv.org/abs/2602.17937v1 Instruction optimization provides a lightweight, model-agnostic approach to enhancing the reasoning performance of large language models (LLMs). This paper presents the first systematic comparison of instruction optimization, based on the DSPy optimization framework, for tabular fact verification. We evaluate four out-of-the-box prompting techniques that cover both text-only prompting and code use: direct prediction, Chain-of-Thought (CoT), ReAct with SQL tools, and CodeAct with Python execution. We study three optimizers from the DSPy framework -- COPRO, MiPROv2, and SIMBA -- across four benchmarks and three model families. We find that instruction optimization consistently improves verification accuracy, with MiPROv2 yielding the most stable gains for CoT, and SIMBA providing the largest benefits for ReAct agents, particularly at larger model scales. Behavioral analyses reveal that SIMBA encourages more direct reasoning paths by applying heuristics, thereby improving numerical comparison abilities in CoT reasoning and helping avoid unnecessary tool calls in ReAct agents. Across different prompting techniques, CoT remains effective for tabular fact checking, especially with smaller models. Although ReAct agents built with larger models can achieve competitive performance, they require careful instruction optimization. --- ### Causal Neighbourhood Learning for Invariant Graph Representations Authors: Simi Job, Xiaohui Tao, Taotao Cai, Haoran Xie, Jianming Yong Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17934v1 Graph data often contain noisy and spurious correlations that mask the true causal relationships, which are essential for enabling graph models to make predictions based on the underlying causal structure of the data. Dependence on spurious connections makes it challenging for traditional Graph Neural Networks (GNNs) to generalize effectively across different graphs. Furthermore, traditional aggregation methods tend to amplify these spurious patterns, limiting model robustness under distribution shifts. To address these issues, we propose Causal Neighbourhood Learning with Graph Neural Networks (CNL-GNN), a novel framework that performs causal interventions on graph structure. CNL-GNN effectively identifies and preserves causally relevant connections and reduces spurious influences through the generation of counterfactual neighbourhoods and adaptive edge perturbation guided by learnable importance masking and an attention-based mechanism. In addition, by combining structural-level interventions with the disentanglement of causal features from confounding factors, the model learns invariant node representations that are robust and generalize well across different graph structures. Our approach improves causal graph learning beyond traditional feature-based methods, resulting in a robust classification model. Extensive experiments on four publicly available datasets, including multiple domain variants of one dataset, demonstrate that CNL-GNN outperforms state-of-the-art GNN models. --- ### Memory-Based Advantage Shaping for LLM-Guided Reinforcement Learning Authors: Narjes Nourzad, Carlee Joe-Wong Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17931v1 In environments with sparse or delayed rewards, reinforcement learning (RL) incurs high sample complexity due to the large number of interactions needed for learning. This limitation has motivated the use of large language models (LLMs) for subgoal discovery and trajectory guidance. While LLMs can support exploration, frequent reliance on LLM calls raises concerns about scalability and reliability. We address these challenges by constructing a memory graph that encodes subgoals and trajectories from both LLM guidance and the agent's own successful rollouts. From this graph, we derive a utility function that evaluates how closely the agent's trajectories align with prior successful strategies. This utility shapes the advantage function, providing the critic with additional guidance without altering the reward. Our method relies primarily on offline input and only occasional online queries, avoiding dependence on continuous LLM supervision. Preliminary experiments in benchmark environments show improved sample efficiency and faster early learning compared to baseline RL methods, with final returns comparable to methods that require frequent LLM interaction. --- ### MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance Authors: Narjes Nourzad, Carlee Joe-Wong Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.17930v1 Reinforcement learning (RL) agents often suffer from high sample complexity in sparse or delayed reward settings due to limited prior structure. Large language models (LLMs) can provide subgoal decompositions, plausible trajectories, and abstract priors that facilitate early learning. However, heavy reliance on LLM supervision introduces scalability constraints and dependence on potentially unreliable signals. We propose MIRA (Memory-Integrated Reinforcement Learning Agent), which incorporates a structured, evolving memory graph to guide early training. The graph stores decision-relevant information, including trajectory segments and subgoal structures, and is constructed from both the agent's high-return experiences and LLM outputs. This design amortizes LLM queries into a persistent memory rather than requiring continuous real-time supervision. From this memory graph, we derive a utility signal that softly adjusts advantage estimation to influence policy updates without modifying the underlying reward function. As training progresses, the agent's policy gradually surpasses the initial LLM-derived priors, and the utility term decays, preserving standard convergence guarantees. We provide theoretical analysis showing that utility-based shaping improves early-stage learning in sparse-reward environments. Empirically, MIRA outperforms RL baselines and achieves returns comparable to approaches that rely on frequent LLM supervision, while requiring substantially fewer online LLM queries. Project webpage: https://narjesno.github.io/MIRA/ --- ### ZACH-ViT: Regime-Dependent Inductive Bias in Compact Vision Transformers for Medical Imaging Authors: Athanasios Angelakis Published: 2026-02-20 Categories: cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2602.17929v2 Vision Transformers rely on positional embeddings and class tokens encoding fixed spatial priors. While effective for natural images, these priors may be suboptimal when spatial layout is weakly informative, a frequent condition in medical imaging. We introduce ZACH-ViT (Zero-token Adaptive Compact Hierarchical Vision Transformer), a compact Vision Transformer that removes positional embeddings and the (CLS) token, achieving permutation-invariant patch processing via global average pooling. Zero-token denotes removal of the dedicated aggregation token and positional encodings. Patch tokens remain unchanged. Adaptive residual projections preserve training stability under strict parameter constraints. We evaluate ZACH-ViT across seven MedMNIST datasets under a strict few-shot protocol (50 samples/class, fixed hyperparameters, five seeds). Results reveal regime-dependent behavior: ZACH-ViT (0.25M parameters, trained from scratch) achieves strongest advantage on BloodMNIST and remains competitive on PathMNIST, while relative advantage decreases on datasets with stronger anatomical priors (OCTMNIST, OrganAMNIST), consistent with our hypothesis. Component and pooling ablations show positional support becomes mildly beneficial as spatial structure increases, whereas reintroducing a (CLS) token is consistently unfavorable. These findings support that architectural alignment with data structure can outweigh universal benchmark dominance. Despite minimal size and no pretraining, ZACH-ViT achieves competitive performance under data-scarce conditions, relevant for compact medical imaging and low-resource settings. Code: https://github.com/Bluesman79/ZACH-ViT --- ### Data-driven configuration tuning of glmnet for balancing accuracy and computational efficiency Authors: Shuhei Muroya, Kei Hirose Published: 2026-02-20 Categories: stat.CO, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2602.17922v2 The glmnet package in R is widely used for lasso estimation because of its computational efficiency. Despite its popularity, glmnet occasionally yields solutions that deviate substantially from the true ones because of the inappropriate default configuration of the algorithm. The accuracy of the obtained solutions can be improved by appropriately tuning the configuration. However, such improvements typically increase computational time, resulting in a tradeoff between accuracy and computational efficiency. Therefore, a systematic approach is required to determine the appropriate configuration. To address this need, we propose a unified data-driven framework specifically designed to optimize the configuration by balancing solution path accuracy and computational cost. Specifically, we generate a large-scale training dataset by measuring the accuracy and computation time of glmnet. Using this dataset, we construct neural networks to predict accuracy and computation time from data characteristics and configuration. For a new dataset, the proposed framework uses the trained networks to explore the configuration space and derive a Pareto front that represents the tradeoff between accuracy and computational cost. This front enables automatic selection of the configuration that maximizes accuracy under a user-specified time constraint. The proposed method is implemented in the R package glmnetconf, available at https://github.com/Shuhei-Muroya/glmnetconf.git. --- ### Latent Diffeomorphic Co-Design of End-Effectors for Deformable and Fragile Object Manipulation Authors: Kei Ikemura, Yifei Dong, Florian T. Pokorny Published: 2026-02-20 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.17921v1 Manipulating deformable and fragile objects remains a fundamental challenge in robotics due to complex contact dynamics and strict requirements on object integrity. Existing approaches typically optimize either end-effector design or control strategies in isolation, limiting achievable performance. In this work, we present the first co-design framework that jointly optimizes end-effector morphology and manipulation control for deformable and fragile object manipulation. We introduce (1) a latent diffeomorphic shape parameterization enabling expressive yet tractable end-effector geometry optimization, (2) a stress-aware bi-level co-design pipeline coupling morphology and control optimization, and (3) a privileged-to-pointcloud policy distillation scheme for zero-shot real-world deployment. We evaluate our approach on challenging food manipulation tasks, including grasping and pushing jelly and scooping fillets. Simulation and real-world experiments demonstrate the effectiveness of the proposed method. --- ### Distribution-Free Sequential Prediction with Abstentions Authors: Jialin Yu, Moïse Blanchard Published: 2026-02-20 Categories: cs.LG, cs.DS, stat.ML arXiv: https://arxiv.org/abs/2602.17918v2 We study a sequential prediction problem in which an adversary is allowed to inject arbitrarily many adversarial instances in a stream of i.i.d. instances, but at each round, the learner may also abstain from making a prediction without incurring any penalty if the instance was indeed corrupted. This semi-adversarial setting naturally sits between the classical stochastic case with i.i.d. instances for which function classes with finite VC dimension are learnable; and the adversarial case with arbitrary instances, known to be significantly more restrictive. For this problem, Goel et al. (2023) showed that, if the learner knows the distribution $μ$ of clean samples in advance, learning can be achieved for all VC classes without restrictions on adversary corruptions. This is, however, a strong assumption in both theory and practice: a natural question is whether similar learning guarantees can be achieved without prior distributional knowledge, as is standard in classical learning frameworks (e.g., PAC learning or asymptotic consistency) and other non-i.i.d. models (e.g., smoothed online learning). We therefore focus on the distribution-free setting where $μ$ is unknown and propose an algorithm AbstainBoost based on a boosting procedure of weak learners, which guarantees sublinear error for general VC classes in distribution-free abstention learning for oblivious adversaries. These algorithms also enjoy similar guarantees for adaptive adversaries, for structured function classes including linear classifiers. These results are complemented with corresponding lower bounds, which reveal an interesting polynomial trade-off between misclassification error and number of erroneous abstentions. --- ### Interactions that reshape the interfaces of the interacting parties Authors: David I. Spivak Published: 2026-02-20 Categories: math.CT, cs.LG arXiv: https://arxiv.org/abs/2602.17917v1 Polynomial functors model systems with interfaces: each polynomial specifies the outputs a system can produce and, for each output, the inputs it accepts. The bicategory $\mathbb{O}\mathbf{rg}$ of dynamic organizations \cite{spivak2021learners} gives a notion of state-driven interaction patterns that evolves over time, but each system's interface remains fixed throughout the interaction. Yet in many systems, the outputs sent and inputs received can reshape the interface itself: a cell differentiating in response to chemical signals gains or loses receptors; a sensor damaged by its input loses a channel; a neural network may grow its output resolution during training. Here we introduce *polynomial trees*, elements of the terminal $(u\triangleleft u)$-coalgebra where $u$ is the polynomial associated to a universe of sets, to model such systems: a polynomial tree is a coinductive tree whose nodes carry polynomials, and in which each round of interaction -- an output chosen and an input received -- determines a child tree, hence the next interface. We construct a monoidal closed category $\mathbf{PolyTr}$ of polynomial trees, with coinductively-defined morphisms, tensor product, and internal hom. We then build a bicategory $\mathbb{O}\mathbf{rgTr}$ generalizing $\mathbb{O}\mathbf{rg}$, whose hom-categories parametrize morphisms by state sets with coinductive action-and-update data. We provide a locally fully faithful functor $\mathbb{O}\mathbf{rg}\to\mathbb{O}\mathbf{rgTr}$ via constant trees, those for which the interfaces do not change through time. We illustrate the generalization by suggesting a notion of progressive generative adversarial networks, where gradient feedback determines when the image-generation interface grows to a higher resolution. --- ### From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents Authors: Qiming Zhu, Shunian Chen, Rui Yu, Zhehao Wu, Benyou Wang Published: 2026-02-20 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2602.17913v1 Long-horizon agents often compress interaction histories into write-time summaries. This creates a fundamental write-before-query barrier: compression decisions are made before the system knows what a future query will hinge on. As a result, summaries can cause unverifiable omissions -- decisive constraints (e.g., allergies) may be dropped, leaving the agent unable to justify an answer with traceable evidence. Retaining raw logs restores an authoritative source of truth, but grounding on raw logs by default is expensive: many queries are answerable from summaries, yet raw grounding still requires processing far longer contexts, inflating token consumption and latency. We propose TierMem, a provenance-linked framework that casts retrieval as an inference-time evidence allocation problem. TierMem uses a two-tier memory hierarchy to answer with the cheapest sufficient evidence: it queries a fast summary index by default, and a runtime sufficiency router Escalates to an immutable raw-log store only when summary evidence is insufficient. TierMem then writes back verified findings as new summary units linked to their raw sources. On LoCoMo, TierMem achieves 0.851 accuracy (vs.0.873 raw-only) while reducing input tokens by 54.1\% and latency by 60.7%. --- ### Condition-Gated Reasoning for Context-Dependent Biomedical Question Answering Authors: Jash Rajesh Parekh, Wonbin Kweon, Joey Chan, Rezarta Islamaj, Robert Leaman, Pengcheng Jiang, Chih-Hsuan Wei, Zhizheng Wang, Zhiyong Lu, Jiawei Han Published: 2026-02-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.17911v3 Current biomedical question answering (QA) systems often assume that medical knowledge applies uniformly, yet real-world clinical reasoning is inherently conditional: nearly every decision depends on patient-specific factors such as comorbidities and contraindications. Existing benchmarks do not evaluate such conditional reasoning, and retrieval-augmented or graph-based methods lack explicit mechanisms to ensure that retrieved knowledge is applicable to given context. To address this gap, we propose CondMedQA, the first benchmark for conditional biomedical QA, consisting of multi-hop questions whose answers vary with patient conditions. Furthermore, we propose Condition-Gated Reasoning (CGR), a novel framework that constructs condition-aware knowledge graphs and selectively activates or prunes reasoning paths based on query conditions. Our findings show that CGR more reliably selects condition-appropriate answers while matching or exceeding state-of-the-art performance on biomedical QA benchmarks, highlighting the importance of explicitly modeling conditionality for robust medical reasoning. --- ### Alignment in Time: Peak-Aware Orchestration for Long-Horizon Agentic Systems Authors: Hanjing Shi, Dominic DiFranzo Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.17910v1 Traditional AI alignment primarily focuses on individual model outputs; however, autonomous agents in long-horizon workflows require sustained reliability across entire interaction trajectories. We introduce APEMO (Affect-aware Peak-End Modulation for Orchestration), a runtime scheduling layer that optimizes computational allocation under fixed budgets by operationalizing temporal-affective signals. Instead of modifying model weights, APEMO detects trajectory instability through behavioral proxies and targets repairs at critical segments, such as peak moments and endings. Evaluation across multi-agent simulations and LLM-based planner--executor flows demonstrates that APEMO consistently enhances trajectory-level quality and reuse probability over structural orchestrators. Our results reframe alignment as a temporal control problem, offering a resilient engineering pathway for the development of long-horizon agentic systems. --- ### A Single Image and Multimodality Is All You Need for Novel View Synthesis Authors: Amirhosein Javadi, Chi-Shiang Gau, Konstantinos D. Polyzos, Tara Javidi Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.17909v2 Diffusion-based approaches have recently demonstrated strong performance for single-image novel view synthesis by conditioning generative models on geometry inferred from monocular depth estimation. However, in practice, the quality and consistency of the synthesized views are fundamentally limited by the reliability of the underlying depth estimates, which are often fragile under low-texture, adverse weather, and occlusion-heavy real-world conditions. In this work, we show that incorporating sparse multimodal range measurements provides a simple yet effective way to overcome these limitations. We introduce a multimodal depth reconstruction framework that leverages extremely sparse range sensing data, such as automotive radar or LiDAR, to produce dense depth maps that serve as robust geometric conditioning for diffusion-based novel view synthesis. Our approach models depth in an angular domain using a localized Gaussian Process formulation, enabling computationally efficient inference while explicitly quantifying uncertainty in regions with limited observations. The reconstructed depth and uncertainty are used as a drop-in replacement for monocular depth estimators in existing diffusion-based rendering pipelines, without modifying the generative model itself. Experiments on real-world multimodal driving scenes demonstrate that replacing vision-only depth with our sparse range-based reconstruction substantially improves both geometric consistency and visual quality in single-image novel-view video generation. These results highlight the importance of reliable geometric priors for diffusion-based view synthesis and demonstrate the practical benefits of multimodal sensing even at extreme levels of sparsity. Code is publicly available at: https://github.com/importAmir/MultiModalNVS --- ### Improving Topic Modeling by Distilling Soft Labels from Language Models Authors: Raymond Li, Amirhossein Abaskohi, Chuyuan Li, Gabriel Murray, Giuseppe Carenini Published: 2026-02-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.17907v3 Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we introduce a novel topic model training framework by Distilling Soft Labels (DSL) from Language Models (LMs). To construct the contextually enriched reconstruction signals, we project the next token probabilities, conditioned on a specialized prompt, onto a pre-defined vocabulary, and train the topic models to reconstruct the soft labels using the LM hidden states. This produces higher-quality topics that are more closely aligned with the underlying thematic structure of the corpus. Extensive experiments demonstrate that DSL achieves substantial improvements in topic coherence and assignment accuracy over existing baselines. Additionally, we also introduce a retrieval-based metric, which shows that our approach significantly outperforms existing methods in identifying semantically similar documents, highlighting its effectiveness for retrieval-oriented applications. --- ### Games That Teach, Chats That Convince: Comparing Interactive and Static Formats for Persuasive Learning Authors: Seyed Hossein Alavi, Zining Wang, Shruthi Chockkalingam, Raymond T. Ng, Vered Shwartz Published: 2026-02-20 Categories: cs.HC, cs.AI, cs.CL, cs.ET arXiv: https://arxiv.org/abs/2602.17905v2 Interactive systems such as chatbots and games are increasingly used to persuade and educate on sustainability-related topics, yet it remains unclear how different delivery formats shape learning and persuasive outcomes when content is held constant. Grounding on identical arguments and factual content across conditions, we present a controlled user study comparing three modes of information delivery: static essays, conversational chatbots, and narrative text-based games. Across subjective measures, the chatbot condition consistently outperformed the other modes and increased perceived importance of the topic. However, perceived learning did not reliably align with objective outcomes: participants in the text-based game condition reported learning less than those reading essays, yet achieved higher scores on a delayed (24-hour) knowledge quiz. Additional exploratory analyses further suggest that common engagement proxies, such as verbosity and interaction length, are more closely related to subjective experience than to actual learning. These findings highlight a dissociation between how persuasive experiences feel and what participants retain, and point to important design trade-offs between interactivity, realism, and learning in persuasive systems and serious games. --- ### HalalBench: A Multilingual OCR Benchmark for Food Packaging Ingredient Extraction Authors: Hasan Arief Published: 2026-02-19 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2604.22754v1 No standardized benchmark exists for evaluating OCR on food packaging, despite its critical role in automated halal food verification. Existing benchmarks target documents or scene text, missing the unique challenges of ingredient labels: curved surfaces, dense multilingual text, and sub-8pt fonts. We present HalalBench, the first open multilingual benchmark for food packaging OCR, comprising 1,043 images (50 real, 993 synthetic) with 36,438 annotations in COCO format spanning 14 languages. We evaluate four engines: docTR achieves F1=0.193, ML Kit 0.180, EasyOCR 0.167, while all fail on Japanese (F1=0.000). A clustering ablation shows 36% F1 improvement from our post-processing algorithm. We validate findings through HalalLens (https://halallens.no), a production halal scanner serving 20+ countries. Dataset and code are released under open licenses. --- ### Differentiable Symbolic Planning: A Neural Architecture for Constraint Reasoning with Learned Feasibility Authors: Venkatakrishna Reddy Oruganti Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.02350v1 Neural networks excel at pattern recognition but struggle with constraint reasoning -- determining whether configurations satisfy logical or physical constraints. We introduce Differentiable Symbolic Planning (DSP), a neural architecture that performs discrete symbolic reasoning while remaining fully differentiable. DSP maintains a feasibility channel (phi) that tracks constraint satisfaction evidence at each node, aggregates this into a global feasibility signal (Phi) through learned rule-weighted combination, and uses sparsemax attention to achieve exact-zero discrete rule selection. We integrate DSP into a Universal Cognitive Kernel (UCK) that combines graph attention with iterative constraint propagation. Evaluated on three constraint reasoning benchmarks -- graph reachability, Boolean satisfiability, and planning feasibility -- UCK+DSP achieves 97.4% accuracy on planning under 4x size generalization (vs. 59.7% for ablated baselines), 96.4% on SAT under 2x generalization, and maintains balanced performance on both positive and negative classes where standard neural approaches collapse. Ablation studies reveal that global phi aggregation is critical: removing it causes accuracy to drop from 98% to 64%. The learned phi signal exhibits interpretable semantics, with values of +18 for feasible cases and -13 for infeasible cases emerging without supervision. --- ### OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration Authors: Yiqin Yang, Hao Hu, Yihuan Mao, Jin Zhang, Chengjie Wu, Yuhua Jiang, Xu Yang, Runpeng Xie, Yi Fan, Bo Liu, Yang Gao, Bo Xu et al. Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.02349v1 Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which forms a strong barrier for PbRL. In this work, we address the problem of low query efficiency in offline PbRL, pinpointing two primary reasons: inefficient exploration and overoptimization of learned reward functions. In response to these challenges, we propose a novel algorithm, \textbf{O}ffline \textbf{P}b\textbf{R}L via \textbf{I}n-\textbf{D}ataset \textbf{E}xploration (OPRIDE), designed to enhance the query efficiency of offline PbRL. OPRIDE consists of two key features: a principled exploration strategy that maximizes the informativeness of the queries and a discount scheduling mechanism aimed at mitigating overoptimization of the learned reward functions. Through empirical evaluations, we demonstrate that OPRIDE significantly outperforms prior methods, achieving strong performance with notably fewer queries. Moreover, we provide theoretical guarantees of the algorithm's efficiency. Experimental results across various locomotion, manipulation, and navigation tasks underscore the efficacy and versatility of our approach. --- ### The IJCNN 2025 Review Process Authors: Michele Scarpiniti, Danilo Comminiello Published: 2026-02-19 Categories: cs.DL, cs.LG arXiv: https://arxiv.org/abs/2603.19244v1 The International Joint Conference on Neural Networks (IJCNN) is the premier international conference in the area of neural networks theory, analysis, and applications. The 2025 edition of the conference comprised 5,526 paper submissions, 7,877 active reviewers, 426 area chairs, 2,152 accepted papers, and more than 2,300 attendees. This represents a growth of about 100% in terms of submissions, 200% in terms of reviewers, and over 50% in terms of attendees as compared to the previous edition. In this paper, we describe several key aspects of the whole review process, including a strategy for ranking the scores provided by the reviewers by evaluating a score index and a calibrated version used experimentally to remove reviewer-specific bias from reviews. --- ### A Hybrid Tsallis-Polarization Impurity Measure for Decision Trees: Theoretical Foundations and Empirical Evaluation Authors: Edouard Lansiaux, Idriss Jairi, Hayfa Zgaya-Biau Published: 2026-02-19 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.13241v1 We introduce the Integrated Tsallis Combination (ITC), a hybrid impurity measure for decision tree learning that combines normalized Tsallis entropy with an exponential polarization component. While many existing measures sacrifice theoretical soundness for computational efficiency or vice versa, ITC provides a mathematically principled framework that balances both aspects. The core innovation lies in the complementarity between Tsallis entropy's information-theoretic foundations and the polarization component's sensitivity to distributional asymmetry. We establish key theoretical properties-concavity under explicit parameter conditions, proper boundary conditions, and connections to classical measures-and provide a rigorous justification for the hybridization strategy. Through an extensive comparative evaluation on seven benchmark datasets comparing 23 impurity measures with five-fold repetition, we show that simple parametric measures (Tsallis $α=0.5$) achieve the highest average accuracy ($91.17\%$), while ITC variants yield competitive results ($88.38-89.16\%$) with strong theoretical guarantees. Statistical analysis (Friedman test: $χ^2=3.89$, $p=0.692$) reveals no significant global differences among top performers, indicating practical equivalence for many applications. ITC's value resides in its solid theoretical grounding-proven concavity under suitable conditions, flexible parameterization ($α$, $β$, $γ$), and computational efficiency $O(K)$-making it a rigorous, generalizable alternative when theoretical guarantees are paramount. We provide guidelines for measure selection based on application priorities and release an open-source implementation to foster reproducibility and further research. --- ### DIALECTIC: A Multi-Agent System for Startup Evaluation Authors: Jae Yoon Bae, Simon Malberg, Joyce Galang, Andre Retterath, Georg Groh Published: 2026-02-19 Categories: cs.MA, cs.CE, cs.CL arXiv: https://arxiv.org/abs/2603.12274v1 Venture capital (VC) investors face a large number of investment opportunities but only invest in few of these, with even fewer ending up successful. Early-stage screening of opportunities is often limited by investor bandwidth, demanding tradeoffs between evaluation diligence and number of opportunities assessed. To ease this tradeoff, we introduce DIALECTIC, an LLM-based multi-agent system for startup evaluation. DIALECTIC first gathers factual knowledge about a startup and organizes these facts into a hierarchical question tree. It then synthesizes the facts into natural-language arguments for and against an investment and iteratively critiques and refines these arguments through a simulated debate, which surfaces only the most convincing arguments. Our system also produces numeric decision scores that allow investors to rank and thus efficiently prioritize opportunities. We evaluate DIALECTIC through backtesting on real investment opportunities aggregated from five VC funds, showing that DIALECTIC matches the precision of human VCs in predicting startup success. --- ### ARKV: Adaptive and Resource-Efficient KV Cache Management under Limited Memory Budget for Long-Context Inference in LLMs Authors: Jianlong Lei, Shashikant Ilager Published: 2026-02-19 Categories: cs.AR, cs.AI, cs.DC, cs.PF arXiv: https://arxiv.org/abs/2603.08727v1 Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning, such as agentic workflows and deep research understanding. However, long-context inference is constrained by the KV cache, a transient memory structure that grows linearly with sequence length and batch size, quickly dominating GPU memory usage. Existing memory reduction techniques, including eviction and quantization, often rely on static heuristics and suffer from degraded quality under tight budgets. In this paper, we propose ARKV, a lightweight and adaptive framework that dynamically allocates precision levels to cached tokens based on per-layer attention dynamics and token-level importance. During a short prefill phase, ARKV estimates the original quantization (OQ) ratio of each layer by computing statistical scores such as attention entropy, variance and kurtosis. During decoding, tokens are assigned to one of three states, Original (full precision), Quantization (low precision), or Eviction, according to a fast heavy-hitter scoring strategy. Our experiments on LLaMA3 and Qwen3 models across diverse long- and short-context tasks demonstrate that ARKV preserves ~97% of baseline accuracy on long-context benchmarks while reducing KV memory usage by 4x, with minimal throughput loss. On short-context tasks, ARKV matches full-precision baselines; on GSM8K math reasoning, it significantly outperforms uniform quantization. These results highlight the practical viability of ARKV for scalable LLM deployment, offering fine-grained, data-driven memory control without retraining or architectural modifications. The source code and artifacts can be found in: https://github.com/Large-scale-Sustainable-Computing-LSC/ARKV --- ### CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training Authors: Lukas Thede, Stefan Winzeck, Zeynep Akata, Jonathan Richard Schwarz Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06610v2 Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfortunately, post-training is known to induce forgetting, especially in the ubiquitous use-case of leveraging third-party pre-trained models, which is typically understood as a loss of parametric or factual knowledge. We argue that this accuracy-centric view is insufficient for modern foundation models and instead define forgetting as systematic model drift that degrades behavior and user experience. In this context, we introduce CapTrack, a capability-centric framework for analyzing forgetting in LLMs that combines a behavioral taxonomy with an evaluation suite centered on capability-specific metrics. Using CapTrack, we conduct a large-scale empirical study across post-training algorithms, domains, and model families, including models up to 80B parameters. We find that forgetting extends beyond parametric knowledge, with pronounced drift in robustness and default behaviors. Instruction fine-tuning induces the strongest relative drift, while preference optimization is more conservative and can partially recover lost capabilities. Differences across model families persist, and no universal mitigation emerges. --- ### Valid Feature-Level Inference for Tabular Foundation Models via the Conditional Randomization Test Authors: Mohamed Salem Published: 2026-02-19 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.06609v1 Modern machine learning models are highly expressive but notoriously difficult to analyze statistically. In particular, while black-box predictors can achieve strong empirical performance, they rarely provide valid hypothesis tests or p-values for assessing whether individual features contain information about a target variable. This article presents a practical approach to feature-level hypothesis testing that combines the Conditional Randomization Test (CRT) with TabPFN, a probabilistic foundation model for tabular data. The resulting procedure yields finite-sample valid p-values for conditional feature relevance, even in nonlinear and correlated settings, without requiring model retraining or parametric assumptions. --- ### Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark Authors: Sourav Panda, Tanmay Ambadkar, Shreyash Kale, Abhinav Verma, Jonathan Dodge Published: 2026-02-19 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.06608v2 The research community lacks a middle ground between StarCraft II full game and its mini-games. The full-game's sprawling state-action space renders reward signals sparse and noisy, but in mini-games simple agents saturate performance. This complexity gap hinders steady curriculum design and prevents researchers from experimenting with modern Reinforcement Learning algorithms in RTS environments under realistic compute budgets. To fill this gap, we present the Two-Bridge Map Suite, the first entry in an open-source benchmark series we purposely engineered as an intermediate benchmark to sit between these extremes. By disabling economy mechanics such as resource collection, base building, and fog-of-war, the environment isolates two core tactical skills: long-range navigation and micro-combat. Preliminary experiments show that agents learn coherent maneuvering and engagement behaviors without imposing full-game computational costs. Two-Bridge is released as a lightweight, Gym-compatible wrapper on top of PySC2, with maps, wrappers, and reference scripts fully open-sourced to encourage broad adoption as a standard benchmark. --- ### ASFL: An Adaptive Model Splitting and Resource Allocation Framework for Split Federated Learning Authors: Chuiyang Meng, Ming Tang, Vincent W. S. Wong Published: 2026-02-19 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.04437v1 Federated learning (FL) enables multiple clients to collaboratively train a machine learning model without sharing their raw data. However, the limited computation resources of the clients may result in a high delay and energy consumption on training. In this paper, we propose an adaptive split federated learning (ASFL) framework over wireless networks. ASFL exploits the computation resources of the central server to train part of the model and enables adaptive model splitting as well as resource allocation during training. To optimize the learning performance (i.e., convergence rate) and efficiency (i.e., delay and energy consumption) of ASFL, we theoretically analyze the convergence rate and formulate a joint learning performance and resource allocation optimization problem. Solving this problem is challenging due to the long-term delay and energy consumption constraints as well as the coupling of the model splitting and resource allocation decisions. We propose an online optimization enhanced block coordinate descent (OOE-BCD) algorithm to solve the problem iteratively. Experimental results show that when compared with five baseline schemes, our proposed ASFL framework converges faster and reduces the total delay and energy consumption by up to 75% and 80%, respectively. ---