# Research Papers — 2026-02 · bundle page 92 of 210 > Full-text markdown of papers #4551–4600 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/92 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/91.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/93.md) ### Physics Aware Neural Networks: Denoising for Magnetic Navigation Authors: Aritra Das, Yashas Shende, Muskaan Chugh, Reva Laxmi Chauhan, Arghya Pathak, Debayan Gupta Published: 2026-02-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13690v2 Magnetic-anomaly navigation, leveraging small-scale variations in the Earth's magnetic field, is a promising alternative when GPS is unavailable or compromised. Airborne systems face a key challenge in extracting geomagnetic field data: the aircraft itself induces magnetic noise. Although the classical Tolles-Lawson model addresses this, it inadequately handles stochastically corrupted magnetic data required for navigation. To handle stochastic noise, we propose using two physics-based constraints: divergence-free vector fields and E(3)-equivariance. These ensure the learned magnetic field obeys Maxwell's equation and that outputs transform correctly with sensor position and orientation. The divergence-free constraint is implemented by training a neural network to output a vector potential A, with the magnetic field defined as its curl. For E(3)-equivariance, we use tensor products of geometric tensors represented via spherical harmonics with known rotational transformations. Enforcing physical consistency and restricting the admissible function space acts as an implicit regularizer that improves spatiotemporal performance. We present ablation studies evaluating each constraint alone and jointly across CNNs, MLPs, LTCs, and Contiformers. Continuous-time dynamics and long-term memory are critical for modelling magnetic time series; the Contiformer, which provides both, outperforms existing methods. To mitigate data scarcity, we generate synthetic datasets using the World Magnetic Model (WMM) and time-series conditional GANs, producing realistic, temporally consistent magnetic sequences across varied trajectories and environments. Experiments show that embedding these constraints significantly improves predictive accuracy and physical plausibility, outperforming classical and unconstrained deep learning approaches. Acknowledgement: This work was done in collaboration with Dirac Labs. --- ### Symmetry-Aware Fusion of Vision and Tactile Sensing via Bilateral Force Priors for Robotic Manipulation Authors: Wonju Lee, Matteo Grimaldi, Tao Yu Published: 2026-02-14 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.13689v1 Insertion tasks in robotic manipulation demand precise, contact-rich interactions that vision alone cannot resolve. While tactile feedback is intuitively valuable, existing studies have shown that naïve visuo-tactile fusion often fails to deliver consistent improvements. In this work, we propose a Cross-Modal Transformer (CMT) for visuo-tactile fusion that integrates wrist-camera observations with tactile signals through structured self- and cross-attention. To stabilize tactile embeddings, we further introduce a physics-informed regularization that encourages bilateral force balance, reflecting principles of human motor control. Experiments on the TacSL benchmark show that CMT with symmetry regularization achieves a 96.59% insertion success rate, surpassing naïve and gated fusion baselines and closely matching the privileged "wrist + contact force" configuration (96.09%). These results highlight two central insights: (i) tactile sensing is indispensable for precise alignment, and (ii) principled multimodal fusion, further strengthened by physics-informed regularization, unlocks complementary strengths of vision and touch, approaching privileged performance under realistic sensing. --- ### AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning Authors: Siqian Tong, Xuan Li, Yiwei Wang, Baolong Bi, Yujun Cai, Shenghua Liu, Yuchen He, Chengpeng Hao Published: 2026-02-14 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2602.13685v1 Large Audio Language Models (LALMs) excel at perception but struggle with complex reasoning requiring precise acoustic measurements. While external tools can extract fine-grained features like exact tempo or pitch, effective integration remains challenging: naively using all tools causes information overload, while prompt-based selection fails to assess context-dependent utility. To address this, we propose AuTAgent (Audio Tool Agent), a reinforcement learning framework that learns when and which tools to invoke. By employing a sparse-feedback training strategy with a novel Differential Reward mechanism, the agent learns to filter out irrelevant tools and invokes external assistance only when it yields a net performance gain over the base model. Experimental results confirm that AuTAgent complements the representation bottleneck of LALMs by providing verifiable acoustic evidence. It improves accuracy by 4.20% / 6.20% and 9.80% / 8.00% for open-source and closed-source backbones on the MMAU Test-mini and the MMAR benchmarks, respectively. In addition, further experiments demonstrate exceptional transferability. We highlight the complementary role of external tools in augmenting audio model reasoning. --- ### On the Sparsifiability of Correlation Clustering: Approximation Guarantees under Edge Sampling Authors: Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma Published: 2026-02-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13684v1 Correlation Clustering (CC) is a fundamental unsupervised learning primitive whose strongest LP-based approximation guarantees require $Θ(n^3)$ triangle inequality constraints and are prohibitive at scale. We initiate the study of \emph{sparsification--approximation trade-offs} for CC, asking how much edge information is needed to retain LP-based guarantees. We establish a structural dichotomy between pseudometric and general weighted instances. On the positive side, we prove that the VC dimension of the clustering disagreement class is exactly $n{-}1$, yielding additive $\varepsilon$-coresets of optimal size $\tilde{O}(n/\varepsilon^2)$; that at most $\binom{n}{2}$ triangle inequalities are active at any LP vertex, enabling an exact cutting-plane solver; and that a sparsified variant of LP-PIVOT, which imputes missing LP marginals via triangle inequalities, achieves a robust $\frac{10}{3}$-approximation (up to an additive term controlled by an empirically computable imputation-quality statistic $\overlineΓ_w$) once $\tildeΘ(n^{3/2})$ edges are observed, a threshold we prove is sharp. On the negative side, we show via Yao's minimax principle that without pseudometric structure, any algorithm observing $o(n)$ uniformly random edges incurs an unbounded approximation ratio, demonstrating that the pseudometric condition governs not only tractability but also the robustness of CC to incomplete information. --- ### An Ensemble Learning Approach towards Waste Segmentation in Cluttered Environment Authors: Maimoona Jafar, Syed Imran Ali, Ahsan Saadat, Muhammad Bilal, Shah Khalid Published: 2026-02-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.13681v1 Environmental pollution is a critical global issue, with recycling emerging as one of the most viable solutions. This study focuses on waste segregation, a crucial step in recycling processes to obtain raw material. Recent advancements in computer vision have significantly contributed to waste classification and recognition. In waste segregation, segmentation masks are essential for robots to accurately localize and pick objects from conveyor belts. The complexity of real-world waste environments, characterized by deformed items without specific patterns and overlapping objects, further complicates waste segmentation tasks. This paper proposes an Ensemble Learning approach to improve segmentation accuracy by combining high performing segmentation models, U-Net and FPN, using a weighted average method. U-Net excels in capturing fine details and boundaries in segmentation tasks, while FPN effectively handles scale variation and context in complex environments, and their combined masks result in more precise predictions. The dataset used closely mimics real-life waste scenarios, and preprocessing techniques were applied to enhance feature learning for deep learning segmentation models. The ensemble model, referred to as EL-4, achieved an IoU value of 0.8306, an improvement over U-Net's 0.8065, and reduced Dice loss to 0.09019 from FPN's 0.1183. This study could contribute to the efficiency of waste sorting at Material Recovery Facility, facilitating better raw material acquisition for recycling with minimal human intervention and enhancing the overall throughput. --- ### AllMem: A Memory-centric Recipe for Efficient Long-context Modeling Authors: Ziming Wang, Xiang Wang, Kailong Peng, Lang Qin, Juan Gabriel Kostelec, Christos Sourmpis, Axel Laborieux, Qinghai Guo Published: 2026-02-14 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.13680v1 Large Language Models (LLMs) encounter significant performance bottlenecks in long-sequence tasks due to the computational complexity and memory overhead inherent in the self-attention mechanism. To address these challenges, we introduce \textsc{AllMem}, a novel and efficient hybrid architecture that integrates Sliding Window Attention (SWA) with non-linear Test-Time Training (TTT) memory networks. \textsc{AllMem} enables models to effectively scale to ultra-long contexts while mitigating catastrophic forgetting. This approach not only overcomes the representation constraints typical of linear memory models but also significantly reduces the computational and memory footprint during long-sequence inference. Furthermore, we implement a Memory-Efficient Fine-Tuning strategy to replace standard attention layers in pre-trained models with memory-augmented sliding window layers. This framework facilitates the efficient transformation of any off-the-shelf pre-trained LLM into an \textsc{AllMem}-based architecture. Empirical evaluations confirm that our 4k window model achieves near-lossless performance on 37k LongBench with a marginal 0.83 drop compared to full attention. Furthermore, on InfiniteBench at a 128k context, our 8k window variant outperforms full attention, which validates the effectiveness of our parameterized memory in mitigating noise and maintaining robust long-range modeling without the prohibitive costs of global attention. --- ### Transferable XAI: Relating Understanding Across Domains with Explanation Transfer Authors: Fei Wang, Yifan Zhang, Brian Y. Lim Published: 2026-02-14 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.13675v1 Current Explainable AI (XAI) focuses on explaining a single application, but when encountering related applications, users may rely on their prior understanding from previous explanations. This leads to either overgeneralization and AI overreliance, or burdensome independent memorization. Indeed, related decision tasks can share explanatory factors, but with some notable differences; e.g., body mass index (BMI) affects the risks for heart disease and diabetes at the same rate, but chest pain is more indicative of heart disease. Similarly, models using different attributes for the same task still share signals; e.g., temperature and pressure affect air pollution but in opposite directions due to the ideal gas law. Leveraging transfer of learning, we propose Transferable XAI to enable users to transfer understanding across related domains by explaining the relationship between domain explanations using a general affine transformation framework applied to linear factor explanations. The framework supports explanation transfer across various domain types: translation for data subspace (subsuming prior work on Incremental XAI), scaling for decision task, and mapping for attributes. Focusing on task and attributes domain types, in formative and summative user studies, we investigated how well participants could understand AI decisions from one domain to another. Compared to single-domain and domain-independent explanations, Transferable XAI was the most helpful for understanding the second domain, leading to the best decision faithfulness, factor recall, and ability to relate explanations between domains. This framework contributes to improving the reusability of explanations across related AI applications by explaining factor relationships between subspaces, tasks, and attributes. --- ### LEAD-Drift: Real-time and Explainable Intent Drift Detection by Learning a Data-Driven Risk Score Authors: Md. Kamrul Hossain, Walid Aljoby Published: 2026-02-14 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2602.13672v1 Intent-Based Networking (IBN) simplifies network management, but its reliability is challenged by "intent drift", where the network's state gradually deviates from its intended goal, often leading to silent failures. Conventional approaches struggle to detect the subtle, early stages of intent drift, raising alarms only when degradation is significant and failure is imminent, which limits their effectiveness for proactive assurance. To address this, we propose LEAD-Drift, a framework that detects intent drift in real time to enable proactive failure prevention. LEAD-Drift's core contribution is reformulating intent failure detection as a supervised learning problem by training a lightweight neural network on fixed-horizon labels to predict a future risk score. The model's raw output is then smoothed with an Exponential Moving Average (EMA) and passed through a statistically tuned threshold to generate robust, real-time alerts. Furthermore, we enhance the framework with two key features for operational intelligence: a multi-horizon modeling technique for dynamic time-to-failure estimation, and per-alert explainability using SHAP to identify root-cause KPIs. Our evaluation on a time-series dataset shows LEAD-Drift provides significantly earlier warnings, improving the average lead time by 7.3 minutes (+17.8\%) compared to a distance-based baseline. It also reduces alert noise by 80.2\% compared to a weighted-KPI heuristic, with only a minor trade-off in lead time. These results demonstrate that LEAD-Drift as a highly effective, interpretable, and operationally efficient solution for proactive network assurance in IBN. --- ### MAS-on-the-Fly: In-Context Structural Adaptation of LLM-Based Multi-Agent Systems Authors: Guangyi Liu, Haojun Lin, Huan Zeng, Heng Wang, Quanming Yao Published: 2026-02-14 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2602.13671v2 Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation and lack adaptability after deployment. We study in-context structural adaptation, where structured experience conditions both query-dependent system generation and execution-time reconfiguration without updating LLM parameters. We introduce MASFly, which realizes this adaptation through two complementary mechanisms. First, a retrieval-augmented SOP instantiation mechanism retrieves and adapts successful collaboration patterns to construct a query-specific MAS. Second, an experience-enhanced process supervision mechanism uses a dedicated Watcher agent to monitor execution against prior failure experience and reconfigure the system upon abnormal behavior. Experiments demonstrate that MASFly achieves state-ofthe-art performance, including a 61.7% success rate on TravelPlanner, with strong task adaptability and robustness. --- ### MAS-on-the-Fly: Dynamic Adaptation of LLM-based Multi-Agent Systems at Test Time Authors: Guangyi Liu, Haojun Lin, Huan Zeng, Heng Wang, Quanming Yao Published: 2026-02-14 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2602.13671v1 Large Language Model (LLM)-based multi-agent systems (MAS) have emerged as a promising paradigm for solving complex tasks. However, existing works often rely on manual designs or "one-size-fits-all" automation, lacking dynamic adaptability after deployment. Inspired by how biological systems adapt, we introduce MASFly, a novel multi-agent framework enabling dynamic adaptation at test time. To adapt system generation, MASFly employs a retrieval-augmented SOP instantiation mechanism that leverages a self-constructed repository of successful collaboration patterns, enabling the LLM to assemble customized MASs for new queries. For adaptive execution, MASFly incorporates an experience-guided supervision mechanism, where a dedicated Watcher agent monitors system behaviors with reference to a personalized experience pool and provides real-time interventions. Extensive experiments demonstrate that MASFly achieves state-of-the-art performance, most notably a 61.7% success rate on the TravelPlanner benchmark, while exhibiting strong task adaptability and robustness. --- ### Advancing Analytic Class-Incremental Learning through Vision-Language Calibration Authors: Binyu Zhao, Wei Zhang, Xingrui Yu, Zhaonian Zou, Ivor Tsang Published: 2026-02-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13670v3 Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. While analytic learning enables rapid, recursive closed-form updates, its efficacy is often compromised by accumulated errors and feature incompatibility. In this paper, we first conduct a systematic study to dissect the failure modes of PTM-based analytic CIL, identifying representation rigidity as the primary bottleneck. Motivated by this insight, we propose VILA, a novel dual-branch framework that advances analytic CIL via a two-level vision-language calibration strategy. Specifically, we coherently fuse plastic, task-adapted features with a frozen, universal visual anchor at the feature level through geometric calibration, and leverage cross-modal semantic priors at the decision level to rectify prediction bias. This confluence maintains analytic-learning's extreme efficiency while overcoming its inherent brittleness. Extensive experiments across eight benchmarks demonstrate that VILA consistently yields superior performance, particularly in fine-grained and long-sequence scenarios. Our framework harmonizes high-fidelity prediction with the simplicity of analytic learning. Our code is available at https://github.com/byzhaoAI/VILA. --- ### EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation Authors: Rang Meng, Weipeng Wu, Yuming Li, Chenguang Ma Published: 2026-02-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13669v5 Recent multi-modal video generation models have achieved high visual quality, but their prohibitive latency and limited temporal stability hinder real-time deployment. Streaming inference exacerbates these issues, leading to pronounced multimodal degradation, such as spatial blurring, temporal drift, and lip desynchronization, which creates an unresolved efficiency-performance trade-off. To this end, we propose EchoTorrent, a novel schema with a fourfold design: (1) Multi-Teacher Training fine-tunes a pre-trained model on distinct preference domains to obtain specialized domain experts, which sequentially transfer domain-specific knowledge to a student model; (2) Adaptive CFG Calibration (ACC-DMD), which calibrates the audio CFG augmentation errors in DMD via a phased spatiotemporal schedule, eliminating redundant CFG computations and enabling single-pass inference per step; (3) Hybrid Long Tail Forcing, which enforces alignment exclusively on tail frames during long-horizon self-rollout training via a causal-bidirectional hybrid architecture, effectively mitigates spatiotemporal degradation in streaming mode while enhancing fidelity to reference frames; and (4) VAE Decoder Refiner through pixel-domain optimization of the VAE decoder to recover high-frequency details while circumventing latent-space ambiguities. Extensive experiments and analysis demonstrate that EchoTorrent achieves few-pass autoregressive generation with substantially extended temporal consistency, identity preservation, and audio-lip synchronization. --- ### ALMo: Interactive Aim-Limit-Defined, Multi-Objective System for Personalized High-Dose-Rate Brachytherapy Treatment Planning and Visualization for Cervical Cancer Authors: Edward Chen, Natalie Dullerud, Pang Wei Koh, Thomas Niedermayr, Elizabeth Kidd, Sanmi Koyejo, Carlos Guestrin Published: 2026-02-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13666v1 In complex clinical decision-making, clinicians must often track a variety of competing metrics defined by aim (ideal) and limit (strict) thresholds. Sifting through these high-dimensional tradeoffs to infer the optimal patient-specific strategy is cognitively demanding and historically prone to variability. In this paper, we address this challenge within the context of High-Dose-Rate (HDR) brachytherapy for cervical cancer, where planning requires strictly managing radiation hot spots while balancing tumor coverage against organ sparing. We present ALMo (Aim-Limit-defined Multi-Objective system), an interactive decision support system designed to infer and operationalize clinician intent. ALMo employs a novel optimization framework that minimizes manual input through automated parameter setup and enables flexible control over toxicity risks. Crucially, the system allows clinicians to navigate the Pareto surface of dosimetric tradeoffs by directly manipulating intuitive aim and limit values. In a retrospective evaluation of 25 clinical cases, ALMo generated treatment plans that consistently met or exceeded manual planning quality, with 65% of cases demonstrating dosimetric improvements. Furthermore, the system significantly enhanced efficiency, reducing average planning time to approximately 17 minutes, compared to the conventional 30-60 minutes. While validated in brachytherapy, ALMo demonstrates a generalized framework for streamlining interaction in multi-criteria clinical decision-making. --- ### HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating Authors: Weibin Liao, Jian-guang Lou, Haoyi Xiong Published: 2026-02-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13665v1 While agentic AI systems rely on LLMs to translate user intent into structured function calls, this process is fraught with computational redundancy, leading to high inference latency that hinders real-time applications. This paper identifies and addresses three key redundancies: (1) the redundant processing of a large library of function descriptions for every request; (2) the redundant use of a large, slow model to generate an entire, often predictable, token sequence; and (3) the redundant generation of fixed, boilerplate parameter syntax. We introduce HyFunc, a novel framework that systematically eliminates these inefficiencies. HyFunc employs a hybrid-model cascade where a large model distills user intent into a single "soft token." This token guides a lightweight retriever to select relevant functions and directs a smaller, prefix-tuned model to generate the final call, thus avoiding redundant context processing and full-sequence generation by the large model. To eliminate syntactic redundancy, our "dynamic templating" technique injects boilerplate parameter syntax on-the-fly within an extended vLLM engine. To avoid potential limitations in generalization, we evaluate HyFunc on an unseen benchmark dataset, BFCL. Experimental results demonstrate that HyFunc achieves an excellent balance between efficiency and performance. It achieves an inference latency of 0.828 seconds, outperforming all baseline models, and reaches a performance of 80.1%, surpassing all models with a comparable parameter scale. These results suggest that HyFunc offers a more efficient paradigm for agentic AI. Our code is publicly available at https://github.com/MrBlankness/HyFunc. --- ### LeafNet: A Large-Scale Dataset and Comprehensive Benchmark for Foundational Vision-Language Understanding of Plant Diseases Authors: Khang Nguyen Quoc, Phuong D. Dao, Luyl-Da Quach Published: 2026-02-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.13662v3 Foundation models and vision-language pre-training have significantly advanced Vision-Language Models (VLMs), enabling multimodal processing of visual and linguistic data. However, their application in domain-specific agricultural tasks, such as plant pathology, remains limited due to the lack of large-scale, comprehensive multimodal image--text datasets and benchmarks. To address this gap, we introduce LeafNet, a comprehensive multimodal dataset, and LeafBench, a visual question-answering benchmark developed to systematically evaluate the capabilities of VLMs in understanding plant diseases. The dataset comprises 186,000 leaf digital images spanning 97 disease classes, paired with metadata, generating 13,950 question-answer pairs spanning six critical agricultural tasks. The questions assess various aspects of plant pathology understanding, including visual symptom recognition, taxonomic relationships, and diagnostic reasoning. Benchmarking 12 state-of-the-art VLMs on our LeafBench dataset, we reveal substantial disparity in their disease understanding capabilities. Our study shows performance varies markedly across tasks: binary healthy--diseased classification exceeds 90% accuracy, while fine-grained pathogen and species identification remains below 65%. Direct comparison between vision-only models and VLMs demonstrates the critical advantage of multimodal architectures: fine-tuned VLMs outperform traditional vision models, confirming that integrating linguistic representations significantly enhances diagnostic precision. These findings highlight critical gaps in current VLMs for plant pathology applications and underscore the need for LeafBench as a rigorous framework for methodological advancement and progress evaluation toward reliable AI-assisted plant disease diagnosis. Code is available at https://github.com/EnalisUs/LeafBench. --- ### Optimized Certainty Equivalent Risk-Controlling Prediction Sets Authors: Jiayi Huang, Amirmohammad Farzaneh, Osvaldo Simeone Published: 2026-02-14 Categories: cs.LG, eess.SP arXiv: https://arxiv.org/abs/2602.13660v1 In safety-critical applications such as medical image segmentation, prediction systems must provide reliability guarantees that extend beyond conventional expected loss control. While risk-controlling prediction sets (RCPS) offer probabilistic guarantees on the expected risk, they fail to capture tail behavior and worst-case scenarios that are crucial in high-stakes settings. This paper introduces optimized certainty equivalent RCPS (OCE-RCPS), a novel framework that provides high-probability guarantees on general optimized certainty equivalent (OCE) risk measures, including conditional value-at-risk (CVaR) and entropic risk. OCE-RCPS leverages upper confidence bounds to identify prediction set parameters that satisfy user-specified risk tolerance levels with provable reliability. We establish theoretical guarantees showing that OCE-RCPS satisfies the desired probabilistic constraint for loss functions such as miscoverage and false negative rate. Experiments on image segmentation demonstrate that OCE-RCPS consistently meets target satisfaction rates across various risk measures and reliability configurations, while OCE-CRC fails to provide probabilistic guarantees. --- ### Zero-Order Optimization for LLM Fine-Tuning via Learnable Direction Sampling Authors: Valery Parfenov, Grigoriy Evseev, Andrey Veprikov, Nikolay Bushkov, Stanislav Moiseev, Aleksandr Beznosikov Published: 2026-02-14 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.13659v1 Fine-tuning large pretrained language models (LLMs) is a cornerstone of modern NLP, yet its growing memory demands (driven by backpropagation and large optimizer States) limit deployment in resource-constrained settings. Zero-order (ZO) methods bypass backpropagation by estimating directional derivatives from forward evaluations, offering substantial memory savings. However, classical ZO estimators suffer from high variance and an adverse dependence on the parameter dimensionality $d$, which has constrained their use to low-dimensional problems. In this work, we propose a policy-driven ZO framework that treats the sampling distribution over perturbation directions as a learnable policy and updates it to reduce the variance of directional estimates. We develop a practical algorithm implementing this idea and provide a theoretical analysis, showing that learned sampling distributions improve the quality of gradient information and relax the explicit dependence on $d$ in convergence bounds. Empirically, we validate the approach on challenging LLM fine-tuning benchmarks, demonstrating substantially improved performance compared to standard ZO baselines. Our results suggest that adaptive direction sampling is a promising route to make ZO fine-tuning viable at scale. The source code is available at https://github.com/brain-lab-research/zo_ldsd --- ### Optimizing Point-of-Care Ultrasound Video Acquisition for Probabilistic Multi-Task Heart Failure Detection Authors: Armin Saadat, Nima Hashemi, Bahar Khodabakhshian, Michael Y. Tsang, Christina Luong, Teresa S. M. Tsang, Purang Abolmaesumi Published: 2026-02-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13658v1 Purpose: Echocardiography with point-of-care ultrasound (POCUS) must support clinical decision-making under tight bedside time and operator-effort constraints. We introduce a personalized data acquisition strategy in which an RL agent, given a partially observed multi-view study, selects the next view to acquire or terminates acquisition to support heart-failure (HF) assessment. Upon termination, a diagnostic model jointly predicts aortic stenosis (AS) severity and left ventricular ejection fraction (LVEF), two key HF biomarkers, and outputs uncertainty, enabling an explicit trade-off between diagnostic performance and acquisition cost. Methods: We model POCUS as a sequential acquisition problem: at each step, a video selector (RL agent) chooses the next view to acquire or terminates acquisition. Upon termination, a shared multi-view transformer performs multi-task inference with two heads, ordinal AS classification, and LVEF regression, and outputs Gaussian predictive distributions yielding ordinal probabilities over AS classes and EF thresholds. These probabilities drive a reward that balances expected diagnostic benefit against acquisition cost, producing patient-specific acquisition pathways. Results: The dataset comprises 12,180 patient-level studies, split into training/validation/test sets (75/15/15). On the 1,820 test studies, our method matches full-study performance while using 32% fewer videos, achieving 77.2% mean balanced accuracy (bACC) across AS severity classification and LVEF estimation, demonstrating robust multi-task performance under acquisition budgets. Conclusion: Patient-tailored, cost-aware acquisition can streamline POCUS workflows while preserving decision quality, producing interpretable scan pathways suited to bedside use. The framework is extensible to additional cardiac endpoints and merits prospective evaluation for clinical integration. --- ### Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization Authors: Yibo Wang, Guangda Huzhang, Yuwei Hu, Yu Xia, Shiyin Lu, Qing-Guo Chen, Zhao Xu, Weihua Luo, Kaifu Zhang, Lijun Zhang Published: 2026-02-14 Categories: cs.AI, cs.CL, cs.CV, cs.HC arXiv: https://arxiv.org/abs/2602.13653v1 Recent advances in Multimodal Large Language Models (MLLMs) have substantially driven the progress of autonomous agents for Graphical User Interface (GUI). Nevertheless, in real-world applications, GUI agents are often faced with non-stationary environments, leading to high computational costs for data curation and policy optimization. In this report, we introduce a novel MLLM-centered framework for GUI agents, which consists of two components: agentic-Q estimation and step-wise policy optimization. The former one aims to optimize a Q-model that can generate step-wise values to evaluate the contribution of a given action to task completion. The latter one takes step-wise samples from the state-action trajectory as inputs, and optimizes the policy via reinforcement learning with our agentic-Q model. It should be noticed that (i) all state-action trajectories are produced by the policy itself, so that the data collection costs are manageable; (ii) the policy update is decoupled from the environment, ensuring stable and efficient optimization. Empirical evaluations show that our framework endows Ovis2.5-9B with powerful GUI interaction capabilities, achieving remarkable performances on GUI navigation and grounding benchmarks and even surpassing contenders with larger scales. --- ### Cumulative Utility Parity for Fair Federated Learning under Intermittent Client Participation Authors: Stefan Behfar, Richard Mortier Published: 2026-02-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13651v1 In real-world federated learning (FL) systems, client participation is intermittent, heterogeneous, and often correlated with data characteristics or resource constraints. Existing fairness approaches in FL primarily focus on equalizing loss or accuracy conditional on participation, implicitly assuming that clients have comparable opportunities to contribute over time. However, when participation itself is uneven, these objectives can lead to systematic under-representation of intermittently available clients, even if per-round performance appears fair. We propose cumulative utility parity, a fairness principle that evaluates whether clients receive comparable long-term benefit per participation opportunity, rather than per training round. To operationalize this notion, we introduce availability-normalized cumulative utility, which disentangles unavoidable physical constraints from avoidable algorithmic bias arising from scheduling and aggregation. Experiments on temporally skewed, non-IID federated benchmarks demonstrate that our approach substantially improves long-term representation parity, while maintaining near-perfect performance. --- ### KorMedMCQA-V: A Multimodal Benchmark for Evaluating Vision-Language Models on the Korean Medical Licensing Examination Authors: Byungjin Choi, Seongsu Bae, Sunjun Kweon, Edward Choi Published: 2026-02-14 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.13650v1 We introduce KorMedMCQA-V, a Korean medical licensing-exam-style multimodal multiple-choice question answering benchmark for evaluating vision-language models (VLMs). The dataset consists of 1,534 questions with 2,043 associated images from Korean Medical Licensing Examinations (2012-2023), with about 30% containing multiple images requiring cross-image evidence integration. Images cover clinical modalities including X-ray, computed tomography (CT), electrocardiography (ECG), ultrasound, endoscopy, and other medical visuals. We benchmark over 50 VLMs across proprietary and open-source categories-spanning general-purpose, medical-specialized, and Korean-specialized families-under a unified zero-shot evaluation protocol. The best proprietary model (Gemini-3.0-Pro) achieves 96.9% accuracy, the best open-source model (Qwen3-VL-32B-Thinking) 83.7%, and the best Korean-specialized model (VARCO-VISION-2.0-14B) only 43.2%. We further find that reasoning-oriented model variants gain up to +20 percentage points over instruction-tuned counterparts, medical domain specialization yields inconsistent gains over strong general-purpose baselines, all models degrade on multi-image questions, and performance varies notably across imaging modalities. By complementing the text-only KorMedMCQA benchmark, KorMedMCQA-V forms a unified evaluation suite for Korean medical reasoning across text-only and multimodal conditions. The dataset is available via Hugging Face Datasets: https://huggingface.co/datasets/seongsubae/KorMedMCQA-V. --- ### Joint Time Series Chain: Detecting Unusual Evolving Trend across Time Series Authors: Li Zhang, Nital Patel, Xiuqi Li, Jessica Lin Published: 2026-02-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13649v1 Time series chain (TSC) is a recently introduced concept that captures the evolving patterns in large scale time series. Informally, a time series chain is a temporally ordered set of subsequences, in which consecutive subsequences in the chain are similar to one another, but the last and the first subsequences maybe be dissimilar. Time series chain has the great potential to reveal latent unusual evolving trend in the time series, or identify precursor of important events in a complex system. Unfortunately, existing definitions of time series chains only consider finding chains in a single time series. As a result, they are likely to miss unexpected evolving patterns in interrupted time series, or across two related time series. To address this limitation, in this work, we introduce a new definition called \textit{Joint Time Series Chain}, which is specially designed for the task of finding unexpected evolving trend across interrupted time series or two related time series. Our definition focuses on mitigating the robustness issues caused by the gap or interruption in the time series. We further propose an effective ranking criterion to identify the best chain. We demonstrate that our proposed approach outperforms existing TSC work in locating unusual evolving patterns through extensive empirical evaluations. We further demonstrate the utility of our work with a real-life manufacturing application from Intel. Our source code is publicly available at the supporting page https://github.com/lizhang-ts/JointTSC . --- ### SF-RAG: Structure-Fidelity Retrieval-Augmented Generation for Academic Question Answering Authors: Rui Yu, Tianyi Wang, Ruixia Liu, Yinglong Wang Published: 2026-02-14 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2602.13647v2 Efficient question-answering (QA) over extensive scientific literature is essential for evidence-based engineering decision-making. Retrieval-augmented generation (RAG) is increasingly applied to question-answering over long academic papers, where accurate evidence allocation under a fixed token budget is critical. However, existing approaches flatten papers into unstructured chunks, destroying the native hierarchical structure and forcing retrieval to operate in a disordered space. This produces fragmented contexts, misallocates tokens to non-evidential regions, and increases the reasoning burden for downstream language models.To address these issues, we propose SF-RAG, an RAG framework that treats the native hierarchical structure of academic papers as a low-entropy retrieval prior.SF-RAG first inherits the native hierarchy to construct a structure-fidelity index, which prevents entropy increase at the source.It then designs a path-guided retrieval mechanism that aligns query semantics to relevant sections and selects high relevance root-to-leaf paths under a fixed token budget, yielding compact, coherent, and low-entropy retrieval contexts.In contrast to existing RAG approaches, SF-RAG avoids entropy increase caused by destructive preprocessing and provides a native low-entropy structural basis for subsequent retrieval. We further introduce entropy-based structural diagnostics to quantify retrieval fragmentation and evidence allocation accuracy.Evaluations across three QA benchmarks show that SF-RAG significantly reduces retrieval fragmentation and improves evidence allocation. These structural benefits drive superior answer quality, establishing a scalable foundation for intelligent engineering document systems and future applications in technical specifications. --- ### Hierarchical Audio-Visual-Proprioceptive Fusion for Precise Robotic Manipulation Authors: Siyuan Li, Jiani Lu, Yu Song, Xianren Li, Bo An, Peng Liu Published: 2026-02-14 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.13640v1 Existing robotic manipulation methods primarily rely on visual and proprioceptive observations, which may struggle to infer contact-related interaction states in partially observable real-world environments. Acoustic cues, by contrast, naturally encode rich interaction dynamics during contact, yet remain underexploited in current multimodal fusion literature. Most multimodal fusion approaches implicitly assume homogeneous roles across modalities, and thus design flat and symmetric fusion structures. However, this assumption is ill-suited for acoustic signals, which are inherently sparse and contact-driven. To achieve precise robotic manipulation through acoustic-informed perception, we propose a hierarchical representation fusion framework that progressively integrates audio, vision, and proprioception. Our approach first conditions visual and proprioceptive representations on acoustic cues, and then explicitly models higher-order cross-modal interactions to capture complementary dependencies among modalities. The fused representation is leveraged by a diffusion-based policy to directly generate continuous robot actions from multimodal observations. The combination of end-to-end learning and hierarchical fusion structure enables the policy to exploit task-relevant acoustic information while mitigating interference from less informative modalities. The proposed method has been evaluated on real-world robotic manipulation tasks, including liquid pouring and cabinet opening. Extensive experiment results demonstrate that our approach consistently outperforms state-of-the-art multimodal fusion frameworks, particularly in scenarios where acoustic cues provide task-relevant information not readily available from visual observations alone. Furthermore, a mutual information analysis is conducted to interpret the effect of audio cues in robotic manipulation via multimodal fusion. --- ### Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval Authors: Linlin Wang, Tianqing Zhu, Laiqiao Qin, Longxiang Gao, Wanlei Zhou Published: 2026-02-14 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2602.13639v1 With recent breakthroughs in large language models (LLMs) for reasoning, planning, and complex task generation, artificial intelligence systems are transitioning from isolated single-agent architectures to multi-agent systems with collaborative intelligence. However, in heterogeneous multi-agent systems (HMAS), capability differences among agents give rise to consistent cognitive problems, where strong and weak models fail to contribute effectively. We define the collaboration as a strong-weak system. Through comprehensive experiments, we disclose a counterintuitive phenomenon in the strong-weak system: a strong-weak collaboration may under-perform weak-weak combinations, revealing that cognitive mismatching are key bottlenecks limiting heterogeneous cooperation. To overcome these challenges, we propose an Entropy-Based Adaptive Guidance Framework that dynamically aligns the guidance with the cognitive state of each agent. The framework quantifies the understanding of weak agents through multi-dimensional entropy metrics - covering expression, uncertainty, structure, coherence, and relevance - and adaptively adjusts the intensity of the guidance at light, moderate and intensive levels. Furthermore, a Retrieval-Augmented Generation (RAG) mechanism is incorporated to retain successful collaboration experiences, enabling both immediate adaptation and long-term learning. Extensive experiments on three benchmark datasets, GSM8K, MBPP, and CVRP demonstrate that our approach consistently enhances the effectiveness and stability of heterogeneous collaboration. The results highlight that adaptive guidance not only mitigates cognitive imbalance but also establishes a scalable pathway toward more robust, cooperative multi-agent intelligence. --- ### DCDM: Divide-and-Conquer Diffusion Models for Consistency-Preserving Video Generation Authors: Haoyu Zhao, Yuang Zhang, Junqi Cheng, Jiaxi Gu, Zenghui Lu, Peng Shu, Zuxuan Wu, Yu-Gang Jiang Published: 2026-02-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13637v1 Recent video generative models have demonstrated impressive visual fidelity, yet they often struggle with semantic, geometric, and identity consistency. In this paper, we propose a system-level framework, termed the Divide-and-Conquer Diffusion Model (DCDM), to address three key challenges: (1) intra-clip world knowledge consistency, (2) inter-clip camera consistency, and (3) inter-shot element consistency. DCDM decomposes video consistency modeling under these scenarios into three dedicated components while sharing a unified video generation backbone. For intra-clip consistency, DCDM leverages a large language model to parse input prompts into structured semantic representations, which are subsequently translated into coherent video content by a diffusion transformer. For inter-clip camera consistency, we propose a temporal camera representation in the noise space that enables precise and stable camera motion control, along with a text-to-image initialization mechanism to further enhance controllability. For inter-shot consistency, DCDM adopts a holistic scene generation paradigm with windowed cross-attention and sparse inter-shot self-attention, ensuring long-range narrative coherence while maintaining computational efficiency. We validate our framework on the test set of the CVM Competition at AAAI'26, and the results demonstrate that the proposed strategies effectively address these challenges. --- ### Layer-Guided UAV Tracking: Enhancing Efficiency and Occlusion Robustness Authors: Yang Zhou, Derui Ding, Ran Sun, Ying Sun, Haohua Zhang Published: 2026-02-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13636v2 Visual object tracking (VOT) plays a pivotal role in unmanned aerial vehicle (UAV) applications. Addressing the trade-off between accuracy and efficiency, especially under challenging conditions like unpredictable occlusion, remains a significant challenge. This paper introduces LGTrack, a unified UAV tracking framework that integrates dynamic layer selection, efficient feature enhancement, and robust representation learning for occlusions. By employing a novel lightweight Global-Grouped Coordinate Attention (GGCA) module, LGTrack captures long-range dependencies and global contexts, enhancing feature discriminability with minimal computational overhead. Additionally, a lightweight Similarity-Guided Layer Adaptation (SGLA) module replaces knowledge distillation, achieving an optimal balance between tracking precision and inference efficiency. Experiments on three datasets demonstrate LGTrack's state-of-the-art real-time speed (258.7 FPS on UAVDT) while maintaining competitive tracking accuracy (82.8\% precision). Code is available at https://github.com/XiaoMoc/LGTrack --- ### Optimization-Free Graph Embedding via Distributional Kernel for Community Detection Authors: Shuaibin Song, Kai Ming Ting, Kaifeng Zhang, Tianrun Liang Published: 2026-02-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13634v1 Neighborhood Aggregation Strategy (NAS) is a widely used approach in graph embedding, underpinning both Graph Neural Networks (GNNs) and Weisfeiler-Lehman (WL) methods. However, NAS-based methods are identified to be prone to over-smoothing-the loss of node distinguishability with increased iterations-thereby limiting their effectiveness. This paper identifies two characteristics in a network, i.e., the distributions of nodes and node degrees that are critical for expressive representation but have been overlooked in existing methods. We show that these overlooked characteristics contribute significantly to over-smoothing of NAS-methods. To address this, we propose a novel weighted distribution-aware kernel that embeds nodes while taking their distributional characteristics into consideration. Our method has three distinguishing features: (1) it is the first method to explicitly incorporate both distributional characteristics; (2) it requires no optimization; and (3) it effectively mitigates the adverse effects of over-smoothing, allowing WL to preserve node distinguishability and expressiveness even after many iterations of embedding. Experiments demonstrate that our method achieves superior community detection performance via spectral clustering, outperforming existing graph embedding methods, including deep learning methods, on standard benchmarks. --- ### A generalizable foundation model for intraoperative understanding across surgical procedures Authors: Kanggil Park, Yongjun Jeon, Soyoung Lim, Seonmin Park, Jongmin Shin, Jung Yong Kim, Sehyeon An, Jinsoo Rhu, Jongman Kim, Gyu-Seong Choi, Namkee Oh, Kyu-Hwan Jung Published: 2026-02-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13633v1 In minimally invasive surgery, clinical decisions depend on real-time visual interpretation, yet intraoperative perception varies substantially across surgeons and procedures. This variability limits consistent assessment, training, and the development of reliable artificial intelligence systems, as most surgical AI models are designed for narrowly defined tasks and do not generalize across procedures or institutions. Here we introduce ZEN, a generalizable foundation model for intraoperative surgical video understanding trained on more than 4 million frames from over 21 procedures using a self-supervised multi-teacher distillation framework. We curated a large and diverse dataset and systematically evaluated multiple representation learning strategies within a unified benchmark. Across 20 downstream tasks and full fine-tuning, frozen-backbone, few-shot and zero-shot settings, ZEN consistently outperforms existing surgical foundation models and demonstrates robust cross-procedure generalization. These results suggest a step toward unified representations for surgical scene understanding and support future applications in intraoperative assistance and surgical training assessment. --- ### Benchmark Leakage Trap: Can We Trust LLM-based Recommendation? Authors: Mingqiao Zhang, Qiyao Peng, Yinghui Wang, Hongtao Liu, Yumeng Wang Published: 2026-02-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13626v3 The expanding integration of Large Language Models (LLMs) into recommender systems poses critical challenges to evaluation reliability. This paper identifies and investigates a previously overlooked issue: benchmark data leakage in LLM-based recommendation. This phenomenon occurs when LLMs are exposed to and potentially memorize benchmark datasets during pre-training or fine-tuning, leading to artificially inflated performance metrics that fail to reflect true model performance. To validate this phenomenon, we simulate diverse data leakage scenarios by conducting continued pre-training of foundation models on strategically blended corpora, which include user-item interactions from both in-domain and out-of-domain sources. Our experiments reveal a dual-effect of data leakage: when the leaked data is domain-relevant, it induces substantial but spurious performance gains, misleadingly exaggerating the model's capability. In contrast, domain-irrelevant leakage typically degrades recommendation accuracy, highlighting the complex and contingent nature of this contamination. Our findings reveal that data leakage acts as a critical, previously unaccounted-for factor in LLM-based recommendation, which could impact the true model performance. We release our code at https://github.com/yusba1/LLMRec-Data-Leakage. --- ### Anthropomorphism on Risk Perception: The Role of Trust and Domain Knowledge in Decision-Support AI Authors: Manuele Reani, Xiangyang He, Zuolan Bao Published: 2026-02-14 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.13625v1 Anthropomorphic design is routinely used to make conversational agents more approachable and engaging. Yet its influence on users' perceptions remains poorly understood. Drawing on psychological theories, we propose that anthropomorphism influences risk perception via two complementary forms of trust, and that domain knowledge moderates these relationships. To test our model, we conducted a large-scale online experiment (N = 1,256) on a financial decision-support system implementing different anthropomorphic designs. We found that anthropomorphism indirectly reduces risk perception by increasing both cognitive and affective trust. Domain knowledge moderates these paths: participants with low financial knowledge experience a negative indirect effect of perceived anthropomorphism on risk perception via cognitive trust, whereas those with high financial knowledge exhibit a positive direct and indirect effect. We discuss theoretical contributions to human-AI interaction and design implications for calibrating trust in anthropomorphic decision-support systems for responsible AI. --- ### Locally Private Parametric Methods for Change-Point Detection Authors: Anuj Kumar Yadav, Cemre Cadir, Yanina Shkel, Michael Gastpar Published: 2026-02-14 Categories: stat.ML, cs.IT, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2602.13619v1 We study parametric change-point detection, where the goal is to identify distributional changes in time series, under local differential privacy. In the non-private setting, we derive improved finite-sample accuracy guarantees for a change-point detection algorithm based on the generalized log-likelihood ratio test, via martingale methods. In the private setting, we propose two locally differentially private algorithms based on randomized response and binary mechanisms, and analyze their theoretical performance. We derive bounds on detection accuracy and validate our results through empirical evaluation. Our results characterize the statistical cost of local differential privacy in change-point detection and show how privacy degrades performance relative to a non-private benchmark. As part of this analysis, we establish a structural result for strong data processing inequalities (SDPI), proving that SDPI coefficients for Rényi divergences and their symmetric variants (Jeffreys-Rényi divergences) are achieved by binary input distributions. These results on SDPI coefficients are also of independent interest, with applications to statistical estimation, data compression, and Markov chain mixing. --- ### DiffusionRollout: Uncertainty-Aware Rollout Planning in Long-Horizon PDE Solving Authors: Seungwoo Yoo, Juil Koo, Daehyeon Choi, Minhyuk Sung Published: 2026-02-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.13616v1 We propose DiffusionRollout, a novel selective rollout planning strategy for autoregressive diffusion models, aimed at mitigating error accumulation in long-horizon predictions of physical systems governed by partial differential equations (PDEs). Building on the recently validated probabilistic approach to PDE solving, we further explore its ability to quantify predictive uncertainty and demonstrate a strong correlation between prediction errors and standard deviations computed over multiple samples-supporting their use as a proxy for the model's predictive confidence. Based on this observation, we introduce a mechanism that adaptively selects step sizes during autoregressive rollouts, improving long-term prediction reliability by reducing the compounding effect of conditioning on inaccurate prior outputs. Extensive evaluation on long-trajectory PDE prediction benchmarks validates the effectiveness of the proposed uncertainty measure and adaptive planning strategy, as evidenced by lower prediction errors and longer predicted trajectories that retain a high correlation with their ground truths. --- ### From What to How: Bridging User Requirements with Software Development Using Large Language Models Authors: Xiao He, Ru Chen, Jialun Cao Published: 2026-02-14 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.13611v1 Recently, large language models (LLMs) are extensively utilized to enhance development efficiency, leading to numerous benchmarks for evaluating their performance. However, these benchmarks predominantly focus on implementation, overlooking the equally critical aspect of software design. This gap raises two pivotal questions: (1) Can LLMs handle software design? (2) Can LLMs write code following the specific designs? To investigate these questions, this paper proposes DesBench, a design-aware benchmark for evaluating LLMs on three software design-related tasks: design-aware code generation, object-oriented modeling, and the design of acceptance test cases. DesBench comprises 30 manually crafted Java projects that include requirement documents, design models, implementations, and acceptance tests, amounting to a total of 30 design models, 194 Java classes, and 737 test cases. We evaluated seven state-of-the-art LLMs, including three DeepSeek R1, two Qwen2.5, and two GPT models, using DesBench. The results reveal that LLMs remain significantly challenged by the intricacies of software design: (1) For code generation, LLMs struggle to produce correct implementations when provided with only high-level or no designs. (2) In object-oriented modeling, while LLMs can accurately identify objects and classes, they face challenges in defining operations and inter-class relationships. (3) Acceptance test cases generated by LLMs from functional requirements achieve code coverage quality comparable to those written by humans. Our research highlights the current limitations of LLMs in managing software design and calls for further investigation into new design methodologies and languages suitable for LLM-based development. --- ### Multi-Modal Sensing and Fusion in mmWave Beamforming for Connected Vehicles: A Transformer Based Framework Authors: Muhammad Baqer Mollah, Honggang Wang, Mohammad Ataul Karim, Hua Fang Published: 2026-02-14 Categories: cs.NI, cs.AI, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2602.13606v1 Millimeter wave (mmWave) communication, utilizing beamforming techniques to address the inherent path loss limitation, is considered as one of the key technologies to support ever increasing high throughput and low latency demands of connected vehicles. However, adopting standard defined beamforming approach in highly dynamic vehicular environments often incurs high beam training overheads and reduction in the available airtime for communications, which is mainly due to exchanging pilot signals and exhaustive beam measurements. To this end, we present a multi-modal sensing and fusion learning framework as a potential alternative solution to reduce such overheads. In this framework, we first extract the representative features from the sensing modalities by modality specific encoders, then, utilize multi-head cross-modal attention to learn dependencies and correlations between different modalities, and subsequently fuse the multimodal features to obtain predicted top-k beams so that the best line-of-sight links can be proactively established. To show the generalizability of the proposed framework, we perform a comprehensive experiment in four different vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) scenarios from real world multimodal and 60 GHz mmWave wireless sensing data. The experiment reveals that the proposed framework (i) achieves up to 96.72% accuracy on predicting top-15 beams correctly, (ii) incurs roughly 0.77 dB average power loss, and (iii) improves the overall latency and beam searching space overheads by 86.81% and 76.56% respectively for top-15 beams compared to standard defined approach. --- ### Towards Sparse Video Understanding and Reasoning Authors: Chenwei Xu, Zhen Ye, Shang Wu, Weijian Li, Zihan Wang, Zhuofan Xia, Lie Lu, Pranav Maneriker, Fan Du, Manling Li, Han Liu Published: 2026-02-14 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.13602v2 We present \revise (\underline{Re}asoning with \underline{Vi}deo \underline{S}parsity), a multi-round agent for video question answering (VQA). Instead of uniformly sampling frames, \revise selects a small set of informative frames, maintains a summary-as-state across rounds, and stops early when confident. It supports proprietary vision-language models (VLMs) in a ``plug-and-play'' setting and enables reinforcement fine-tuning for open-source models. For fine-tuning, we introduce EAGER (Evidence-Adjusted Gain for Efficient Reasoning), an annotation-free reward with three terms: (1) Confidence gain: after new frames are added, we reward the increase in the log-odds gap between the correct option and the strongest alternative; (2) Summary sufficiency: at answer time we re-ask using only the last committed summary and reward success; (3) Correct-and-early stop: answering correctly within a small turn budget is rewarded. Across multiple VQA benchmarks, \revise improves accuracy while reducing frames, rounds, and prompt tokens, demonstrating practical sparse video reasoning. --- ### SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Authors: Jiacheng Zhang, Feng Liu, Chao Du, Tianyu Pang Published: 2026-02-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13600v2 A line of recent training-free methods for mitigating hallucinations in large vision-language models (LVLMs) operates by amplifying attention to visual tokens during autoregressive generation within a single forward pass. We refer to this paradigm as visual attention amplification (VAA). In this paper, we identify a dual failure pattern in existing VAA methods caused by their use of a fixed amplification factor across generation steps: it can be too weak at some steps, leaving hallucinations unresolved, while too strong at others, introducing new hallucinations. Motivated by this finding, we propose Step-wise Adaptive Visual Attention Amplification (SAVAA), a new VAA framework that estimates hallucination risk for each generated token and uses the estimated risk to adaptively amplify visual attention at the next generation step. Specifically, we introduce Visual Grounding Entropy (VGE), a lightweight hallucination-risk estimator that augments predictive entropy with visual grounding, assigning higher risk to tokens that are uncertain, weakly grounded in the image, or both. Guided by VGE, SAVAA uses the estimated risk to calibrate the VAA factor for the next generation step, applying stronger amplification to higher-risk steps and weaker amplification to lower-risk steps. Across LLaVA-NeXT-7B, Qwen3-VL-8B, and InternVL3.5-8B, SAVAA significantly outperforms baseline methods on generative hallucination benchmarks such as CHAIR, SHR and AMBER. Code is available at: https://github.com/JiachengZ01/SAVVA. --- ### The Quantization Trap: Breaking Linear Scaling Laws in Multi-Hop Reasoning Authors: Henry Han, Xiyang Liu, Xiaodong Wang, Fei Han, Xiaodong Li Published: 2026-02-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13595v2 Neural scaling laws provide a predictable recipe for AI advancement: reducing numerical precision should linearly improve computational efficiency and energy profile ($E \propto \mathrm{bits}$). In this paper, we demonstrate that this scaling law breaks in the context of multi-hop reasoning. We reveal a 'quantization trap' where reducing precision from 16-bit to 8/4-bit paradoxically increases net energy consumption while degrading reasoning accuracy. We provide a rigorous theoretical decomposition that attributes this failure to hardware casting overhead, the hidden latency cost of dequantization kernels, which becomes a dominant bottleneck in sequential reasoning chains, as well as to a sequential energy amortization failure. As a result, scaling law breaking is unavoidable in practice. We formalize a Critical Model Scale $N^*$ that predicts when the trap dissolves or deepens as a function of model size, batch size, and hardware configuration, validated across a 120$\times$ range (0.6B--72B) on six GPU architectures. Our findings suggest that the industry's "smaller-is-better" heuristic is mathematically counterproductive for complex reasoning tasks. --- ### Hippocampus: An Efficient and Scalable Memory Module for Agentic AI Authors: Yi Li, Lianjie Cao, Faraz Ahmed, Puneet Sharma, Bingzhe Li Published: 2026-02-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13594v1 Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency and poor storage scalability. We introduce Hippocampus, an agentic memory management system that uses compact binary signatures for semantic search and lossless token-ID streams for exact content reconstruction. Its core is a Dynamic Wavelet Matrix (DWM) that compresses and co-indexes both streams to support ultra-fast search in the compressed domain, thus avoiding costly dense-vector or graph computations. This design scales linearly with memory size, making it suitable for long-horizon agentic deployments. Empirically, our evaluation shows that Hippocampus reduces end-to-end retrieval latency by up to 31$\times$ and cuts per-query token footprint by up to 14$\times$, while maintaining accuracy on both LoCoMo and LongMemEval benchmarks. --- ### Two-Stream Interactive Joint Learning of Scene Parsing and Geometric Vision Tasks Authors: Guanfeng Tang, Hongbo Zhao, Ziwei Long, Jiayao Li, Bohong Xiao, Wei Ye, Hanli Wang, Rui Fan Published: 2026-02-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.13588v1 Inspired by the human visual system, which operates on two parallel yet interactive streams for contextual and spatial understanding, this article presents Two Interactive Streams (TwInS), a novel bio-inspired joint learning framework capable of simultaneously performing scene parsing and geometric vision tasks. TwInS adopts a unified, general-purpose architecture in which multi-level contextual features from the scene parsing stream are infused into the geometric vision stream to guide its iterative refinement. In the reverse direction, decoded geometric features are projected into the contextual feature space for selective heterogeneous feature fusion via a novel cross-task adapter, which leverages rich cross-view geometric cues to enhance scene parsing. To eliminate the dependence on costly human-annotated correspondence ground truth, TwInS is further equipped with a tailored semi-supervised training strategy, which unleashes the potential of large-scale multi-view data and enables continuous self-evolution without requiring ground-truth correspondences. Extensive experiments conducted on three public datasets validate the effectiveness of TwInS's core components and demonstrate its superior performance over existing state-of-the-art approaches. The source code will be made publicly available upon publication. --- ### A First Proof Sprint Authors: Joseph Corneli Published: 2026-02-14 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2602.13587v1 This monograph reports a multi-agent proof sprint on ten research-level problems, combining rapid draft generation with adversarial verification, targeted repair, and explicit provenance. The workflow uses wiring-diagram decompositions of claim dependencies to localize gaps and coordinate reviewer-driven revisions. Final outcomes are heterogeneous but explicit: the manuscript distinguishes mathematical status from QC-validation status. Mathematically, Problem~3 has a validation-complete existence path under the scoped criterion used here (uniqueness/irreducibility treated as optional), Problem 5 is solved in a scope-limited form for $F_O$-local connective spectra, Problem 10 is conditional under clearly stated assumptions (with explicit necessity counterexamples when assumptions are dropped), and Problems 4 and 6 are partial with named remaining obligations in the general case (including an unconditional $K_n$ result for Problem 6 with $c_0 = 1/3$). Problem 7 is treated as provisionally closed via the rotation-route theorem chain, pending independent ledger re-check. At the QC layer, Problems~7 and~9 have node-level validation artifacts but still contain unresolved verifier gaps. The main methodological result is that structure-aware verification and layer-switching strategies improve reliability and calibration in compressed proof sprints. --- ### Interpretable clustering via optimal multi-way decision trees Authors: Hayato Suzuki, Shunnosuke Ikeda, Naoki Nishimura, Yuichi Takano Published: 2026-02-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13586v2 Clustering is a fundamental unsupervised learning technique for uncovering data structures to facilitate knowledge discovery and decision-making. While clustering accuracy is crucial, interpretability significantly impacts the practical value of clustering results, particularly in high-risk decision-making contexts. Although decision-tree-based clustering methods offer high interpretability through explicit splitting rules, existing approaches often rely on local greedy search or require expensive computational costs limited to binary splits, resulting in deeper, less interpretable trees. To overcome these limitations, we establish a high-performance computational framework named Interpretable Clustering via Optimal Multi-way Trees (ICOMT). We make three primary contributions. First, we propose a new discretization method for numerical features using one-dimensional K-means clustering to capture data distributions. Second, we formulate a binary linear optimization (BLO) problem to guarantee tree optimality. Third, extensive validation on four public datasets demonstrates that our ICOMT method outperforms existing baselines, achieving superior clustering accuracy while maintaining shallow, concise tree structures. --- ### Interpretable clustering via optimal multiway-split decision trees Authors: Hayato Suzuki, Shunnosuke Ikeda, Yuichi Takano Published: 2026-02-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13586v1 Clustering serves as a vital tool for uncovering latent data structures, and achieving both high accuracy and interpretability is essential. To this end, existing methods typically construct binary decision trees by solving mixed-integer nonlinear optimization problems, often leading to significant computational costs and suboptimal solutions. Furthermore, binary decision trees frequently result in excessively deep structures, which makes them difficult to interpret. To mitigate these issues, we propose an interpretable clustering method based on optimal multiway-split decision trees, formulated as a 0-1 integer linear optimization problem. This reformulation renders the optimization problem more tractable compared to existing models. A key feature of our method is the integration of a one-dimensional K-means algorithm for the discretization of continuous variables, allowing for flexible and data-driven branching. Extensive numerical experiments on publicly available real-world datasets demonstrate that our method outperforms baseline methods in terms of clustering accuracy and interpretability. Our method yields multiway-split decision trees with concise decision rules while maintaining competitive performance across various evaluation metrics. --- ### Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation Authors: Binglei Li, Mengping Yang, Zhiyu Tan, Junping Zhang, Hao Li Published: 2026-02-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13585v2 Recent text-to-image (T2I) diffusion models have achieved remarkable advancement, yet faithfully following complex textual descriptions remains challenging due to insufficient interactions between textual and visual features. Prior approaches enhance such interactions via architectural design or handcrafted textual condition weighting, but lack flexibility and overlook the dynamic interactions across different blocks and denoising stages. To provide a more flexible and efficient solution to this problem, we propose Diff-Aid, a lightweight inference-time method that adaptively adjusts per-token text and image interactions across transformer blocks and denoising timesteps. Beyond improving generation quality, Diff-Aid yields interpretable modulation patterns that reveal how different blocks, timesteps, and textual tokens contribute to semantic alignment during denoising. As a plug-and-play module, Diff-Aid can be seamlessly integrated into downstream applications for further improvement, including style LoRAs, controllable generation, and zero-shot editing. Experiments on strong baselines (SD 3.5 and FLUX) demonstrate consistent improvements in prompt adherence, visual quality, and human preference across various metrics. Our code and models will be released. --- ### Differentiable Rule Induction from Raw Sequence Inputs Authors: Kun Gao, Katsumi Inoue, Yongzhi Cao, Hanpin Wang, Feng Yang Published: 2026-02-14 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.13583v1 Rule learning-based models are widely used in highly interpretable scenarios due to their transparent structures. Inductive logic programming (ILP), a form of machine learning, induces rules from facts while maintaining interpretability. Differentiable ILP models enhance this process by leveraging neural networks to improve robustness and scalability. However, most differentiable ILP methods rely on symbolic datasets, facing challenges when learning directly from raw data. Specifically, they struggle with explicit label leakage: The inability to map continuous inputs to symbolic variables without explicit supervision of input feature labels. In this work, we address this issue by integrating a self-supervised differentiable clustering model with a novel differentiable ILP model, enabling rule learning from raw data without explicit label leakage. The learned rules effectively describe raw data through its features. We demonstrate that our method intuitively and precisely learns generalized rules from time series and image data. --- ### Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges Authors: Ruomeng Ding, Yifei Pang, He Sun, Yizhong Wang, Zhiwei Steven Wu, Zhun Deng Published: 2026-02-14 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.13576v2 Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language rubrics and validated on benchmarks. We identify a previously under-recognized vulnerability in this workflow, which we term Rubric-Induced Preference Drift (RIPD). Even when rubric edits pass benchmark validation, they can still produce systematic and directional shifts in a judge's preferences on target domains. Because rubrics serve as a high-level decision interface, such drift can emerge from seemingly natural, criterion-preserving edits and remain difficult to detect through aggregate benchmark metrics or limited spot-checking. We further show this vulnerability can be exploited through rubric-based preference attacks, in which benchmark-compliant rubric edits steer judgments away from a fixed human or trusted reference on target domains, systematically inducing RIPD and reducing target-domain accuracy up to 9.5% (helpfulness) and 27.9% (harmlessness). When these judgments are used to generate preference labels for downstream post-training, the induced bias propagates through alignment pipelines and becomes internalized in trained policies. This leads to persistent and systematic drift in model behavior. Overall, our findings highlight evaluation rubrics as a sensitive and manipulable control interface, revealing a system-level alignment risk that extends beyond evaluator reliability alone. The code is available at: https://github.com/ZDCSlab/Rubrics-as-an-Attack-Surface. Warning: Certain sections may contain potentially harmful content that may not be appropriate for all readers. --- ### Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges Authors: Ruomeng Ding, Yifei Pang, He Sun, Yizhong Wang, Zhiwei Steven Wu, Zhun Deng Published: 2026-02-14 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.13576v1 Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language rubrics and validated on benchmarks. We identify a previously under-recognized vulnerability in this workflow, which we term Rubric-Induced Preference Drift (RIPD). Even when rubric edits pass benchmark validation, they can still produce systematic and directional shifts in a judge's preferences on target domains. Because rubrics serve as a high-level decision interface, such drift can emerge from seemingly natural, criterion-preserving edits and remain difficult to detect through aggregate benchmark metrics or limited spot-checking. We further show this vulnerability can be exploited through rubric-based preference attacks, in which benchmark-compliant rubric edits steer judgments away from a fixed human or trusted reference on target domains, systematically inducing RIPD and reducing target-domain accuracy up to 9.5% (helpfulness) and 27.9% (harmlessness). When these judgments are used to generate preference labels for downstream post-training, the induced bias propagates through alignment pipelines and becomes internalized in trained policies. This leads to persistent and systematic drift in model behavior. Overall, our findings highlight evaluation rubrics as a sensitive and manipulable control interface, revealing a system-level alignment risk that extends beyond evaluator reliability alone. The code is available at: https://github.com/ZDCSlab/Rubrics-as-an-Attack-Surface. Warning: Certain sections may contain potentially harmful content that may not be appropriate for all readers. --- ### Elo-Evolve: A Co-evolutionary Framework for Language Model Alignment Authors: Jing Zhao, Ting Zhen, Junwei Bao, Hongfei Jiang, Yang Song Published: 2026-02-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.13575v2 Current alignment methods for Large Language Models (LLMs) rely on compressing vast amounts of human preference data into static, absolute reward functions, leading to data scarcity, noise sensitivity, and training instability. We introduce Elo-Evolve, a co-evolutionary framework that redefines alignment as dynamic multi-agent competition within an adaptive opponent pool. Our approach makes two key innovations: (1) eliminating Bradley-Terry model dependencies by learning directly from binary win/loss outcomes in pairwise competitions, and (2) implementing Elo-orchestrated opponent selection that provides automatic curriculum learning through temperature-controlled sampling. We ground our approach in PAC learning theory, demonstrating that pairwise comparison achieves superior sample complexity and empirically validate a 4.5x noise reduction compared to absolute scoring approaches. Experimentally, we train a Qwen2.5-7B model using our framework with opponents including Qwen2.5-14B, Qwen2.5-32B, and Qwen3-8B models. Results demonstrate a clear performance hierarchy: point-based methods < static pairwise training < Elo-Evolve across Alpaca Eval 2.0 and MT-Bench, validating the progressive benefits of pairwise comparison and dynamic opponent selection for LLM alignment. --- ### LLM-Confidence Reranker: A Training-Free Approach for Enhancing Retrieval-Augmented Generation Systems Authors: Zhipeng Song, Xiangyu Kong, Xinrui Bao, Yizhi Zhou, Jiulong Jiao, Sitong Liu, Yuhang Zhou, Heng Qi Published: 2026-02-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.13571v1 Large language models (LLMs) have revolutionized natural language processing, yet hallucinations in knowledge-intensive tasks remain a critical challenge. Retrieval-augmented generation (RAG) addresses this by integrating external knowledge, but its efficacy depends on accurate document retrieval and ranking. Although existing rerankers demonstrate effectiveness, they frequently necessitate specialized training, impose substantial computational expenses, and fail to fully exploit the semantic capabilities of LLMs, particularly their inherent confidence signals. We propose the LLM-Confidence Reranker (LCR), a training-free, plug-and-play algorithm that enhances reranking in RAG systems by leveraging black-box LLM confidence derived from Maximum Semantic Cluster Proportion (MSCP). LCR employs a two-stage process: confidence assessment via multinomial sampling and clustering, followed by binning and multi-level sorting based on query and document confidence thresholds. This approach prioritizes relevant documents while preserving original rankings for high-confidence queries, ensuring robustness. Evaluated on BEIR and TREC benchmarks with BM25 and Contriever retrievers, LCR--using only 7--9B-parameter pre-trained LLMs--consistently improves NDCG@5 by up to 20.6% across pre-trained LLM and fine-tuned Transformer rerankers, without degradation. Ablation studies validate the hypothesis that LLM confidence positively correlates with document relevance, elucidating LCR's mechanism. LCR offers computational efficiency, parallelism for scalability, and broad compatibility, mitigating hallucinations in applications like medical diagnosis. --- ### Who Do LLMs Trust? Human Experts Matter More Than Other LLMs Authors: Anooshka Bajaj, Zoran Tiganj Published: 2026-02-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13568v1 Large language models (LLMs) increasingly operate in environments where they encounter social information such as other agents' answers, tool outputs, or human recommendations. In humans, such inputs influence judgments in ways that depend on the source's credibility and the strength of consensus. This paper investigates whether LLMs exhibit analogous patterns of influence and whether they privilege feedback from humans over feedback from other LLMs. Across three binary decision-making tasks, reading comprehension, multi-step reasoning, and moral judgment, we present four instruction-tuned LLMs with prior responses attributed either to friends, to human experts, or to other LLMs. We manipulate whether the group is correct and vary the group size. In a second experiment, we introduce direct disagreement between a single human and a single LLM. Across tasks, models conform significantly more to responses labeled as coming from human experts, including when that signal is incorrect, and revise their answers toward experts more readily than toward other LLMs. These results reveal that expert framing acts as a strong prior for contemporary LLMs, suggesting a form of credibility-sensitive social influence that generalizes across decision domains. ---