# Research Papers — 2026-02 · bundle page 94 of 210 > Full-text markdown of papers #4651–4700 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/94 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/93.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/95.md) ### Structural Divergence Between AI-Agent and Human Social Networks in Moltbook Authors: Wenpin Hou, Zhicheng Ji Published: 2026-02-13 Categories: physics.soc-ph, cs.AI arXiv: https://arxiv.org/abs/2602.15064v1 Large populations of AI agents are increasingly embedded in online environments, yet little is known about how their collective interaction patterns compare to human social systems. Here, we analyze the full interaction network of Moltbook, a platform where AI agents and humans coexist, and systematically compare its structure to well-characterized human communication networks. Although Moltbook follows the same node-edge scaling relationship observed in human systems, indicating comparable global growth constraints, its internal organization diverges markedly. The network exhibits extreme attention inequality, heavy-tailed and asymmetric degree distributions, suppressed reciprocity, and a global under-representation of connected triadic structures. Community analysis reveals a structured modular architecture with elevated modularity and comparatively lower community size inequality relative to degree-preserving null models. Together, these findings show that AI-agent societies can reproduce global structural regularities of human networks while exhibiting fundamentally different internal organizing principles, highlighting that key features of human social organization are not universal but depend on the nature of the interacting agents. --- ### Safe-SDL:Establishing Safety Boundaries and Control Mechanisms for AI-Driven Self-Driving Laboratories Authors: Zihan Zhang, Haohui Que, Junhan Chang, Xin Zhang, Hao Wei, Tong Zhu Published: 2026-02-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.15061v1 The emergence of Self-Driving Laboratories (SDLs) transforms scientific discovery methodology by integrating AI with robotic automation to create closed-loop experimental systems capable of autonomous hypothesis generation, experimentation, and analysis. While promising to compress research timelines from years to weeks, their deployment introduces unprecedented safety challenges differing from traditional laboratories or purely digital AI. This paper presents Safe-SDL, a comprehensive framework for establishing robust safety boundaries and control mechanisms in AI-driven autonomous laboratories. We identify and analyze the critical ``Syntax-to-Safety Gap'' -- the disconnect between AI-generated syntactically correct commands and their physical safety implications -- as the central challenge in SDL deployment. Our framework addresses this gap through three synergistic components: (1) formally defined Operational Design Domains (ODDs) that constrain system behavior within mathematically verified boundaries, (2) Control Barrier Functions (CBFs) that provide real-time safety guarantees through continuous state-space monitoring, and (3) a novel Transactional Safety Protocol (CRUTD) that ensures atomic consistency between digital planning and physical execution. We ground our theoretical contributions through analysis of existing implementations including UniLabOS and the Osprey architecture, demonstrating how these systems instantiate key safety principles. Evaluation against the LabSafety Bench reveals that current foundation models exhibit significant safety failures, demonstrating that architectural safety mechanisms are essential rather than optional. Our framework provides both theoretical foundations and practical implementation guidance for safe deployment of autonomous scientific systems, establishing the groundwork for responsible acceleration of AI-driven discovery. --- ### CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperation Authors: Tengjie Zhu, Guanyu Cai, Yang Zhaohui, Guanzhu Ren, Haohui Xie, ZiRui Wang, Junsong Wu, Jingbo Wang, Xiaokang Yang, Yao Mu, Yichao Yan Published: 2026-02-13 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2602.15060v2 Long-horizon whole-body humanoid teleoperation remains challenging due to accumulated global pose drift, particularly on full-sized humanoids. Although recent learning-based tracking methods enable agile and coordinated motions, they typically operate in the robot's local frame and neglect global pose feedback, leading to drift and instability during extended execution. In this work, we present CLOT, a real-time whole-body humanoid teleoperation system that achieves closed-loop global motion tracking via high-frequency localization feedback. CLOT synchronizes operator and robot poses in a closed loop, enabling drift-free human-to-humanoid mimicry over long timehorizons. However, directly imposing global tracking rewards in reinforcement learning, often results in aggressive and brittle corrections. To address this, we propose a data-driven randomization strategy that decouples observation trajectories from reward evaluation, enabling smooth and stable global corrections. We further regularize the policy with an adversarial motion prior to suppress unnatural behaviors. To support CLOT, we collect 20 hours of carefully curated human motion data for training the humanoid teleoperation policy. We design a transformer-based policy and train it for over 1300 GPU hours. The policy is deployed on a full-sized humanoid with 31 DoF (excluding hands). Both simulation and real-world experiments verify high-dynamic motion, high-precision tracking, and strong robustness in sim-to-real humanoid teleoperation. Motion data, demos and code can be found in our website. --- ### REMem: Reasoning with Episodic Memory in Language Agent Authors: Yiheng Shu, Saisri Padmaja Jonnalagedda, Xiang Gao, Bernal Jiménez Gutiérrez, Weijian Qi, Kamalika Das, Huan Sun, Yu Su Published: 2026-02-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13530v3 Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, memory in language agents remains mainly semantic, and current agents are not yet capable of effectively recollecting and reasoning over interaction histories. We identify and formalize the core challenges of episodic recollection and reasoning from this gap, and observe that existing work often overlooks episodicity, lacks explicit event modeling, or overemphasizes simple retrieval rather than complex reasoning. We present REMem, a two-phase framework for constructing and reasoning with episodic memory: 1) Offline indexing, where REMem converts experiences into a hybrid memory graph that flexibly links time-aware gists and facts. 2) Online inference, where REMem employs an agentic retriever with carefully curated tools for iterative retrieval over the memory graph. Comprehensive evaluation across four episodic memory benchmarks shows that REMem substantially outperforms state-of-the-art memory systems such as Mem0 and HippoRAG 2, showing 3.4% and 13.4% absolute improvements on episodic recollection and reasoning tasks, respectively. Moreover, REMem also demonstrates more robust refusal behavior for unanswerable questions. --- ### SecureGate: Learning When to Reveal PII Safely via Token-Gated Dual-Adapters for Federated LLMs Authors: Mohamed Shaaban, Mohamed Elmahallawy Published: 2026-02-13 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2602.13529v2 Federated learning (FL) enables collaborative training across organizational silos without sharing raw data, making it attractive for privacy-sensitive applications. With the rapid adoption of large language models (LLMs), federated fine-tuning of generative LLMs has gained attention as a way to leverage distributed data while preserving confidentiality. However, this setting introduces fundamental challenges: (i) privacy leakage of personally identifiable information (PII) due to LLM memorization, and (ii) a persistent tension between global generalization and local utility under heterogeneous data. Existing defenses, such as data sanitization and differential privacy, reduce leakage but often degrade downstream performance. We propose SecureGate, a privacy-aware federated fine-tuning framework for LLMs that provides fine-grained privacy control without sacrificing utility. SecureGate employs a dual-adapter LoRA architecture: a secure adapter that learns sanitized, globally shareable representations, and a revealing adapter that captures sensitive, organization-specific knowledge. A token-controlled gating module selectively activates these adapters at inference time, enabling controlled information disclosure without retraining. Extensive experiments across multiple LLMs and real-world datasets show that SecureGate improves task utility while substantially reducing PII leakage, achieving up to a 31.66X reduction in inference attack accuracy and a 17.07X reduction in extraction recall for unauthorized requests. Additionally, it maintains 100% routing reliability to the correct adapter and incurs only minimal computational and communication overhead. --- ### Singular Vectors of Attention Heads Align with Features Authors: Gabriel Franco, Carson Loughridge, Mark Crovella Published: 2026-02-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13524v2 Identifying feature representations in language models is a central task in mechanistic interpretability. Several recent studies have made the observation that feature representations can be inferred in some cases from singular vectors of attention matrices. However, sound justification for this phenomenon is lacking. In this paper we address that question, asking: why and when do singular vectors align with features? First, we demonstrate that singular vectors robustly align with features in a model where features can be directly observed. We then show theoretically that such alignment is expected under a range of conditions. We close by asking how, operationally, alignment may be recognized in real models where feature representations are not directly observable. We identify sparse attention decomposition as a testable prediction of alignment, and show evidence that it emerges in real models in a manner consistent with predictions. Together these results suggest that alignment of singular vectors with features can be a sound and theoretically justified basis for feature identification in language models. --- ### Frequency-Enhanced Hilbert Scanning Mamba for Short-Term Arctic Sea Ice Concentration Prediction Authors: Feng Gao, Zheng Gong, Wenli Liu, Yanhai Gan, Zhuoran Zheng, Junyu Dong, Qian Du Published: 2026-02-13 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.13522v1 While Mamba models offer efficient sequence modeling, vanilla versions struggle with temporal correlations and boundary details in Arctic sea ice concentration (SIC) prediction. To address these limitations, we propose Frequency-enhanced Hilbert scanning Mamba Framework (FH-Mamba) for short-term Arctic SIC prediction. Specifically, we introduce a 3D Hilbert scan mechanism that traverses the 3D spatiotemporal grid along a locality-preserving path, ensuring that adjacent indices in the flattened sequence correspond to neighboring voxels in both spatial and temporal dimensions. Additionally, we incorporate wavelet transform to amplify high-frequency details and we also design a Hybrid Shuffle Attention module to adaptively aggregate sequence and frequency features. Experiments conducted on the OSI-450a1 and AMSR2 datasets demonstrate that our FH-Mamba achieves superior prediction performance compared with state-of-the-art baselines. The results confirm the effectiveness of Hilbert scanning and frequency-aware attention in improving both temporal consistency and edge reconstruction for Arctic SIC forecasting. Our codes are publicly available at https://github.com/oucailab/FH-Mamba. --- ### Arming Data Agents with Tribal Knowledge Authors: Shubham Agarwal, Asim Biswal, Sepanta Zeighami, Alvin Cheung, Joseph Gonzalez, Aditya G. Parameswaran Published: 2026-02-13 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2602.13521v2 Natural language to SQL (NL2SQL) translation enables non-expert users to query relational databases through natural language. Recently, NL2SQL agents, powered by the reasoning capabilities of Large Language Models (LLMs), have significantly advanced NL2SQL translation. Nonetheless, NL2SQL agents still make mistakes when faced with large-scale real-world databases because they lack knowledge of how to correctly leverage the underlying data (e.g., knowledge about the intent of each column) and form misconceptions about the data when querying it, leading to errors. Prior work has studied generating facts about the database to provide more context to NL2SQL agents, but such approaches simply restate database contents without addressing the agent's misconceptions. In this paper, we propose Tk-Boost, a bolt-on framework for augmenting any NL2SQL agent with tribal knowledge: knowledge that corrects the agent's misconceptions in querying the database accumulated through experience using the database. To accumulate experience, Tk-Boost first asks the NL2SQL agent to answer a few queries on the database, identifies the agent's misconceptions by analyzing its mistakes on the database, and generates tribal knowledge to address them. To enable accurate retrieval, Tk-Boost indexes this knowledge with applicability conditions that specify the query features for which the knowledge is useful. When answering new queries, Tk-Boost uses this knowledge to provide feedback to the NL2SQL agent, resolving the agent's misconceptions during SQL generation, and thus improving the agent's accuracy. Extensive experiments across the BIRD and Spider 2.0 benchmarks with various NL2SQL agents shows Tk-Boost improves NL2SQL agents accuracy by up to 16.9% on Spider 2.0 and 13.7% on BIRD --- ### Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens Authors: Wei-Lin Chen, Liqian Peng, Tian Tan, Chao Zhao, Blake JianHang Chen, Ziqian Lin, Alec Go, Yu Meng Published: 2026-02-13 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.13517v2 Large language models (LLMs) have demonstrated impressive reasoning capabilities by scaling test-time compute via long Chain-of-Thought (CoT). However, recent findings suggest that raw token counts are unreliable proxies for reasoning quality: increased generation length does not consistently correlate with accuracy and may instead signal "overthinking," leading to performance degradation. In this work, we quantify inference-time effort by identifying deep-thinking tokens -- tokens where internal predictions undergo significant revisions in deeper model layers prior to convergence. Across four challenging mathematical and scientific benchmarks (AIME 24/25, HMMT 25, and GPQA-diamond) and a diverse set of reasoning-focused models (GPT-OSS, DeepSeek-R1, and Qwen3), we show that deep-thinking ratio (the proportion of deep-thinking tokens in a generated sequence) exhibits a robust and consistently positive correlation with accuracy, substantially outperforming both length-based and confidence-based baselines. Leveraging this insight, we introduce Think@n, a test-time scaling strategy that prioritizes samples with high deep-thinking ratios. We demonstrate that Think@n matches or exceeds standard self-consistency performance while significantly reducing inference costs by enabling the early rejection of unpromising generations based on short prefixes. --- ### SPILLage: Agentic Oversharing on the Web Authors: Jaechul Roh, Eugene Bagdasarian, Hamed Haddadi, Ali Shahin Shamsabadi Published: 2026-02-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13516v1 LLM-powered agents are beginning to automate user's tasks across the open web, often with access to user resources such as emails and calendars. Unlike standard LLMs answering questions in a controlled ChatBot setting, web agents act "in the wild", interacting with third parties and leaving behind an action trace. Therefore, we ask the question: how do web agents handle user resources when accomplishing tasks on their behalf across live websites? In this paper, we formalize Natural Agentic Oversharing -- the unintentional disclosure of task-irrelevant user information through an agent trace of actions on the web. We introduce SPILLage, a framework that characterizes oversharing along two dimensions: channel (content vs. behavior) and directness (explicit vs. implicit). This taxonomy reveals a critical blind spot: while prior work focuses on text leakage, web agents also overshare behaviorally through clicks, scrolls, and navigation patterns that can be monitored. We benchmark 180 tasks on live e-commerce sites with ground-truth annotations separating task-relevant from task-irrelevant attributes. Across 1,080 runs spanning two agentic frameworks and three backbone LLMs, we demonstrate that oversharing is pervasive with behavioral oversharing dominates content oversharing by 5x. This effect persists -- and can even worsen -- under prompt-level mitigation. However, removing task-irrelevant information before execution improves task success by up to 17.9%, demonstrating that reducing oversharing improves task success. Our findings underscore that protecting privacy in web agents is a fundamental challenge, requiring a broader view of "output" that accounts for what agents do on the web, not just what they type. Our datasets and code are available at https://github.com/jrohsc/SPILLage. --- ### SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning Authors: Jintao Zhang, Kai Jiang, Chendong Xiang, Weiqi Feng, Yuezhou Hu, Haocheng Xi, Jianfei Chen, Jun Zhu Published: 2026-02-13 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.13515v1 Many training-free sparse attention methods are effective for accelerating diffusion models. Recently, several works suggest that making sparse attention trainable can further increase sparsity while preserving generation quality. We study three key questions: (1) when do the two common masking rules, i.e., Top-k and Top-p, fail, and how can we avoid these failures? (2) why can trainable sparse attention reach higher sparsity than training-free methods? (3) what are the limitations of fine-tuning sparse attention using the diffusion loss, and how can we address them? Based on this analysis, we propose SpargeAttention2, a trainable sparse attention method that achieves high sparsity without degrading generation quality. SpargeAttention2 includes (i) a hybrid masking rule that combines Top-k and Top-p for more robust masking at high sparsity, (ii) an efficient trainable sparse attention implementation, and (iii) a distillation-inspired fine-tuning objective to better preserve generation quality during fine-tuning using sparse attention. Experiments on video diffusion models show that SpargeAttention2 reaches 95% attention sparsity and a 16.2x attention speedup while maintaining generation quality, consistently outperforming prior sparse attention methods. --- ### Learning Gradient Flow: Using Equation Discovery to Accelerate Engineering Optimization Authors: Grant Norman, Conor Rowan, Kurt Maute, Alireza Doostan Published: 2026-02-13 Categories: math.OC, cs.CE, cs.LG, math.DS, math.NA arXiv: https://arxiv.org/abs/2602.13513v2 In this work, we investigate the use of data-driven equation discovery for dynamical systems to model and forecast continuous-time dynamics of unconstrained optimization problems. To avoid expensive evaluations of the objective function and its gradient, we leverage trajectory data on the optimization variables to learn the continuous-time dynamics associated with gradient descent, Newton's method, and ADAM optimization. The discovered gradient flows are then solved as a surrogate for the original optimization problem. To this end, we introduce the Learned Gradient Flow (LGF) optimizer, which is equipped to build surrogate models of variable polynomial order in full- or reduced-dimensional spaces at user-defined intervals in the optimization process. We demonstrate the efficacy of this approach on several standard problems from engineering mechanics and scientific machine learning, including two inverse problems, structural topology optimization, and two forward solves with different discretizations. Our results suggest that the learned gradient flows can significantly expedite convergence by capturing critical features of the optimization trajectory while avoiding expensive evaluations of the objective and its gradient. --- ### Stochastic variance reduced extragradient methods for solving hierarchical variational inequalities Authors: Pavel Dvurechensky, Andrea Ebner, Johannes Carl Schnebel, Shimrit Shtern, Mathias Staudigl Published: 2026-02-13 Categories: math.OC, cs.GT, cs.LG arXiv: https://arxiv.org/abs/2602.13510v1 We are concerned with optimization in a broad sense through the lens of solving variational inequalities (VIs) -- a class of problems that are so general that they cover as particular cases minimization of functions, saddle-point (minimax) problems, Nash equilibrium problems, and many others. The key challenges in our problem formulation are the two-level hierarchical structure and finite-sum representation of the smooth operators in each level. For this setting, we are the first to prove convergence rates and complexity statements for variance-reduced stochastic algorithms approaching the solution of hierarchical VIs in Euclidean and Bregman setups. --- ### Benchmarking Video Foundation Models for Remote Parkinson's Disease Screening Authors: Md Saiful Islam, Ekram Hossain, Abdelrahman Abdelkader, Tariq Adnan, Fazla Rabbi Mashrur, Sooyong Park, Praveen Kumar, Qasim Sudais, Natalia Chunga, Nami Shah, Jan Freyberg, Christopher Kanan et al. Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13507v2 Video-based assessments offer a scalable pathway for remote Parkinson's disease (PD) screening. While traditional approaches rely on handcrafted features mimicking clinical scales, recent advances in video foundation models (VFMs) enable representation learning without task-specific customization. However, the comparative effectiveness of different VFM architectures across diverse clinical tasks remains poorly understood. We present a large-scale systematic study using a novel video dataset from 1,888 participants (727 with PD), comprising 32,847 videos across 16 standardized clinical tasks. We evaluate seven state-of-the-art VFMs -- including VideoPrism, V-JEPA, ViViT, and VideoMAE -- to determine their robustness in clinical screening. By evaluating frozen embeddings with a linear classification head, we demonstrate that task saliency is highly model-dependent: VideoPrism excels in capturing visual speech kinematics (no audio) and facial expressivity, while V-JEPA proves superior for upper-limb motor tasks. Notably, TimeSformer remains highly competitive for rhythmic tasks like finger tapping. Our experiments yield AUCs of 76.4 - 85.3% and accuracies of 71.5 - 80.6%. While high specificity (up to 90.3%) suggests strong potential for ruling out healthy individuals, the lower sensitivity (43.2 - 57.3%) highlights the need for task-aware calibration and integration of multiple tasks and modalities. Overall, this work establishes a rigorous baseline for VFM-based PD screening and provides a roadmap for selecting suitable tasks and architectures in remote neurological monitoring. Code and anonymized structured data are publicly available: https://anonymous.4open.science/r/parkinson\_video\_benchmarking-A2C5 --- ### $γ$-weakly $θ$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions Authors: Mohammad Pedramfar, Vaneet Aggarwal Published: 2026-02-13 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2602.13506v2 Optimizing non-convex functions is a fundamental challenge across machine learning and combinatorial optimization. We introduce and study $γ$-weakly $θ$-up-concavity, a novel first-order condition that characterizes a broad class of such functions. This condition provides a powerful unifying framework, strictly generalizing both DR-submodular and One-Sided Smooth (OSS) functions while capturing broader forms of scale-dependent curvature, including accumulating-then-diminishing returns and flat-start behavior. Our central theoretical contribution demonstrates that $γ$-weakly $θ$-up-concave functions are upper-linearizable: for any feasible point, we can construct a linear surrogate whose gains provably approximate the original non-linear objective. A key technical contribution is a nonuniform upper-linearization argument yielding approximation coefficients that depend explicitly on the curvature parameters and the geometry of the feasible region. This linearizability yields immediate and unified approximation guarantees for a wide range of problems. Specifically, we obtain unified approximation guarantees for offline optimization as well as static and dynamic regret bounds in online settings via standard reductions to linear optimization. Moreover, our framework recovers the optimal approximation coefficient for DR-submodular maximization and improves existing approximation coefficients for OSS optimization, particularly over matroid constraints. --- ### From Perceptions To Evidence: Detecting AI-Generated Content In Turkish News Media With A Fine-Tuned Bert Classifier Authors: Ozancan Ozdemir Published: 2026-02-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.13504v1 The rapid integration of large language models into newsroom workflows has raised urgent questions about the prevalence of AI-generated content in online media. While computational studies have begun to quantify this phenomenon in English-language outlets, no empirical investigation exists for Turkish news media, where existing research remains limited to qualitative interviews with journalists or fake news detection. This study addresses that gap by fine-tuning a Turkish-specific BERT model (dbmdz/bert-base-turkish-cased) on a labeled dataset of 3,600 articles from three major Turkish outlets with distinct editorial orientations for binary classification of AI-rewritten content. The model achieves 0.9708 F1 score on the held-out test set with symmetric precision and recall across both classes. Subsequent deployment on over 3,500 unseen articles spanning between 2023 and 2026 reveals consistent cross-source and temporally stable classification patterns, with mean prediction confidence exceeding 0.96 and an estimated 2.5 percentage of examined news content rewritten or revised by LLMs on average. To the best of our knowledge, this is the first study to move beyond self-reported journalist perceptions toward empirical, data-driven measurement of AI usage in Turkish news media. --- ### Translating Dietary Standards into Healthy Meals with Minimal Substitutions Authors: Trevor Chan, Ilias Tagkopoulos Published: 2026-02-13 Categories: cs.AI, q-bio.OT arXiv: https://arxiv.org/abs/2602.13502v1 An important goal for personalized diet systems is to improve nutritional quality without compromising convenience or affordability. We present an end-to-end framework that converts dietary standards into complete meals with minimal change. Using the What We Eat in America (WWEIA) intake data for 135,491 meals, we identify 34 interpretable meal archetypes that we then use to condition a generative model and a portion predictor to meet USDA nutritional targets. In comparisons within archetypes, generated meals are better at following recommended daily intake (RDI) targets by 47.0%, while remaining compositionally close to real meals. Our results show that by allowing one to three food substitutions, we were able to create meals that were 10% more nutritious, while reducing costs 19-32%, on average. By turning dietary guidelines into realistic, budget-aware meals and simple swaps, this framework can underpin clinical decision support, public-health programs, and consumer apps that deliver scalable, equitable improvements in everyday nutrition. --- ### TrasMuon: Trust-Region Adaptive Scaling for Orthogonalized Momentum Optimizers Authors: Peng Cheng, Jiucheng Zang, Qingnan Li, Liheng Ma, Yufei Cui, Yingxue Zhang, Boxing Chen, Ming Jian, Wen Tong Published: 2026-02-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13498v2 Muon-style optimizers leverage Newton-Schulz (NS) iterations to orthogonalize updates, yielding update geometries that often outperform Adam-series methods. However, this orthogonalization discards magnitude information, rendering training sensitive to step-size hyperparameters and vulnerable to high-energy bursts. To mitigate this, we introduce TrasMuon (\textbf{T}rust \textbf{R}egion \textbf{A}daptive \textbf{S}caling \textbf{Muon}). TrasMuon preserves the near-isometric geometry of Muon while stabilizing magnitudes through (i) global RMS calibration and (ii) energy-based trust-region clipping. We demonstrate that while reintroducing adaptive scaling improves optimization efficiency, it typically exacerbates instability due to high-energy outliers. TrasMuon addresses this by defining a trust region based on relative energy ratios, confining updates to a stable zone. Empirical experiments on vision and language models demonstrate that TrasMuon converges faster than baselines. Furthermore, experiments without warmup stages confirm TrasMuon's superior stability and robustness. --- ### Future of Edge AI in biodiversity monitoring Authors: Aude Vuilliomenet, Kate E. Jones, Duncan Wilson Published: 2026-02-13 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.13496v1 1. Many ecological decisions are slowed by the gap between collecting and analysing biodiversity data. Edge computing moves processing closer to the sensor, with edge artificial intelligence (AI) enabling on-device inference, reducing reliance on data transfer and continuous connectivity. In principle, this shifts biodiversity monitoring from passive logging towards autonomous, responsive sensing systems. In practice, however, adoption remains fragmented, with key architectural trade-offs, performance constraints, and implementation challenges rarely reported systematically. 2. Here, we analyse 82 studies published between 2017 and 2025 that implement edge computing for biodiversity monitoring across acoustic, vision, tracking, and multi-modal systems. We synthesise hardware platforms, AI model optimisation, and wireless communication to critically assess how design choices shape ecological inference, deployment longevity, and operational feasibility. 3. Publications increased from 3 in 2017 to 19 in 2025. We identify four system types: (I) TinyML, low-power microcontrollers (MCUs) for single-taxon or rare-event detection; (II) Edge AI, single-board computers (SBCs) for multi-species classification and real-time alerts; (III) Distributed edge AI; and (IV) Cloud AI for retrospective processing pipelines. Each system type represents context-dependent trade-offs among power consumption, computational capability, and communication requirements. 4. Our analysis reveals the evolution of edge computing systems from proof-of-concept to robust, scalable tools. We argue that edge computing offers opportunities for responsive biodiversity management, but realising this potential requires increased collaboration between ecologists, engineers, and data scientists to align model development and system design with ecological questions, field constraints, and ethical considerations. --- ### What Do We Mean by 'Pilot Study': Early Findings from a Meta-Review of Pilot Study Reporting at CHI Authors: Belu Ticona, Amna Liaqat, Antonios Anastasopoulos Published: 2026-02-13 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.13488v1 Pilot studies (PS) are ubiquitous in HCI research. CHI papers routinely reference 'pilot studies', 'pilot tests', or 'preliminary studies' to justify design decisions, verify procedures, or motivate methodological choices. Yet despite their frequency, the role of pilot studies in HCI remains conceptually vague and empirically underexamined. Unlike fields such as medicine, nursing, and education, where pilot and feasibility studies have well-established definitions, guidelines, reporting standards and even a dedicated research journal, the CHI community lacks a shared understanding of what constitutes a pilot study, why they are conducted, and how they should be reported. Many papers reference pilots 'in passing', without details about design, outcomes, or how the pilot informed the main study. This variability suggests a methodological blind spot in our community. --- ### Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity Authors: Fei Wu, Jia Hu, Geyong Min, Shiqiang Wang Published: 2026-02-13 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2602.13486v3 Federated low-rank adaptation (FedLoRA) has facilitated communication-efficient and privacy-preserving fine-tuning of foundation models for downstream tasks. In practical federated learning scenarios, client heterogeneity in system resources and data distributions motivates the use of heterogeneous LoRA ranks across clients. However, we identify a previously overlooked phenomenon in heterogeneous FedLoRA with SVD-based allocation, termed rank collapse, where the energy of the global update becomes concentrated in the minimum shared rank, resulting in suboptimal performance and high sensitivity to rank configurations. Through theoretical analysis, we reveal the underlying mechanism of rank collapse: a mismatch between rank-agnostic aggregation weights and rank-dependent client contributions, which systematically suppresses higher-rank updates at a geometric rate over rounds. Motivated by this insight, we propose raFLoRA, a rank-partitioned aggregation method that decomposes local updates into rank partitions and then aggregates each partition weighted by its effective client contributions. Extensive experiments across vision, language, and reasoning tasks show that raFLoRA prevents rank collapse, improves model performance, and enhances robustness across diverse heterogeneous configurations compared with strong FedLoRA baselines. --- ### Preventing Rank Collapse in Federated Low-Rank Adaptation with Client Heterogeneity Authors: Fei Wu, Jia Hu, Geyong Min, Shiqiang Wang Published: 2026-02-13 Categories: cs.LG, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2602.13486v2 Federated low-rank adaptation (FedLoRA) has facilitated communication-efficient and privacy-preserving fine-tuning of foundation models for downstream tasks. In practical federated learning scenarios, client heterogeneity in system resources and data distributions motivates the use of heterogeneous LoRA ranks across clients. However, we identify a previously overlooked phenomenon in heterogeneous FedLoRA with SVD-based allocation, termed rank collapse, where the energy of the global update becomes concentrated in the minimum shared rank, resulting in suboptimal performance and high sensitivity to rank configurations. Through theoretical analysis, we reveal the root cause of rank collapse: a mismatch between rank-agnostic aggregation weights and rank-dependent client contributions, which systematically suppresses higher-rank updates at a geometric rate over rounds. Motivated by this insight, we propose raFLoRA, a rank-partitioned aggregation method that decomposes local updates into rank partitions and then aggregates each partition weighted by its effective client contributions. Extensive experiments across vision, language, and reasoning tasks show that raFLoRA prevents rank collapse, improves model performance, and enhances robustness across diverse heterogeneous configurations compared with strong FedLoRA baselines. --- ### Federated Learning of Nonlinear Temporal Dynamics with Graph Attention-based Cross-Client Interpretability Authors: Ayse Tursucular, Ayush Mohanty, Nazal Mohamed, Nagi Gebraeel Published: 2026-02-13 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2602.13485v2 Networks of modern industrial systems are increasingly monitored by distributed sensors, where each system comprises multiple subsystems generating high dimensional time series data. These subsystems are often interdependent, making it important to understand how temporal patterns at one subsystem relate to others. This is challenging in decentralized settings where raw measurements cannot be shared and client observations are heterogeneous. In practical deployments each subsystem (client) operates a fixed proprietary model that cannot be modified or retrained, limiting existing approaches. Nonlinear dynamics further make cross client temporal interdependencies difficult to interpret because they are embedded in nonlinear state transition functions. We present a federated framework for learning temporal interdependencies across clients under these constraints. Each client maps high dimensional local observations to low dimensional latent states using a nonlinear state space model. A central server learns a graph structured neural state transition model over the communicated latent states using a Graph Attention Network. For interpretability we relate the Jacobian of the learned server side transition model to attention coefficients, providing the first interpretable characterization of cross client temporal interdependencies in decentralized nonlinear systems. We establish theoretical convergence guarantees to a centralized oracle and validate the framework through synthetic experiments demonstrating convergence, interpretability, scalability and privacy. Additional real world experiments show performance comparable to decentralized baselines. --- ### Finding Interpretable Prompt-Specific Circuits in Language Models Authors: Gabriel Franco, Lucas M. Tassis, Azalea Rohr, Mark Crovella Published: 2026-02-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13483v2 Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. A crucial part of finding circuits is understanding why each attention head attends where it does. To this end, we introduce ACC++, an improved circuit-tracing method based on the principle of attention-causal communication (ACC) (1), which identifies signals, i.e., contents of low dimensional subspaces that cause attention on a token pair. ACC++ extracts circuits from a single forward pass, without replacement models or patching. Circuits identified by ACC++ consist of components that are causal for the model's attention decisions, together with the low-dimensional signals used to communicate between them. Here, we first detail the conceptual advances that ACC++ makes over previous work. We then show that across multiple models, a substantial portion of ACC++ signals are interpretable: many signals admit a short natural-language description. We next present a number of new insights into model behavior obtained via ACC++. First, we use ACC++'s interpretable circuits to characterize the sensitivity of indirect object identification (IOI) circuits to prompt structure. We find that prompt-specific circuits form well-defined clusters, and across clusters, heads receive systematically different signals corresponding to distinct mechanisms for identifying the IO name. Next, in multilingual IOI, ACC++ circuits show that while model components are reused across languages, signals are often language-specific. In a four-language IOI case study, cross-language circuit distances are consistent with linguistic relatedness. Together, these results show that ACC++ can shed light on a broad spectrum of model behaviors. --- ### Comparing Classifiers: A Case Study Using PyCM Authors: Sadra Sabouri, Alireza Zolanvari, Sepand Haghighi Published: 2026-02-13 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.13482v1 Selecting an optimal classification model requires a robust and comprehensive understanding of the performance of the model. This paper provides a tutorial on the PyCM library, demonstrating its utility in conducting deep-dive evaluations of multi-class classifiers. By examining two different case scenarios, we illustrate how the choice of evaluation metrics can fundamentally shift the interpretation of a model's efficacy. Our findings emphasize that a multi-dimensional evaluation framework is essential for uncovering small but important differences in model performance. However, standard metrics may miss these subtle performance trade-offs. --- ### MELT: A Behavioral Trace Dataset for High-Risk Memecoin Launch Detection Authors: Sihao Hu, Selim Furkan Tekin, Yichang Xu, Ling Liu Published: 2026-02-13 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2602.13480v2 Launchpads have become the dominant mechanism for issuing memecoins, exposing investors to a new class of high-risk launches that existing rug-pull detection methods cannot capture. We argue that detecting these threats requires structured behavioral traces that underlie raw heterogeneous blockchain data, i.e., how insiders accumulate, coordinate, and unwind positions. To enable such analysis, we introduce MELT (MEmecoin Launch Trace, the first behavioral trace dataset for analyzing and detecting high-risk memecoin launches on Solana. MELT covers 41k+ memecoin launches with 200M+ transactions parsed into typed behavioral records that distinguish swaps, wash trades, transfers, and mints. Beyond per-account behaviors, MELT contributes bundle-trace data that links accounts controlled by the same entity, revealing that, on average, 36.5% of token supply is held by coordinated accounts, a concealment strategy that disguises the true ownership concentration from unsuspecting buyers. On top of these traces, MELT provides 122 behavioral features and risk-level annotations, enabling supervised learning at a population scale. We benchmark representative ML models on the high-risk launch detection task. Integrating their predictions into a simple memecoin selection strategy reduces investment loss significantly, demonstrating that behavioral traces can be translated into risk mitigation. Our dataset and code is available at https://github.com/git-disl/MELT. --- ### GLIMPSE : Real-Time Text Recognition and Contextual Understanding for VQA in Wearables Authors: Akhil Ramachandran, Ankit Arun, Ashish Shenoy, Abhay Harpale, Srihari Jayakumar, Debojeet Chatterjee, Mohsen Moslehpour, Pierce Chuang, Yichao Lu, Vikas Bhardwaj, Peyman Heidari Published: 2026-02-13 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2602.13479v1 Video Large Language Models (Video LLMs) have shown remarkable progress in understanding and reasoning about visual content, particularly in tasks involving text recognition and text-based visual question answering (Text VQA). However, deploying Text VQA on wearable devices faces a fundamental tension: text recognition requires high-resolution video, but streaming high-quality video drains battery and causes thermal throttling. Moreover, existing models struggle to maintain coherent temporal context when processing text across multiple frames in real-time streams. We observe that text recognition and visual reasoning have asymmetric resolution requirements - OCR needs fine detail while scene understanding tolerates coarse features. We exploit this asymmetry with a hybrid architecture that performs selective high-resolution OCR on-device while streaming low-resolution video for visual context. On a benchmark of text-based VQA samples across five task categories, our system achieves 72% accuracy at 0.49x the power consumption of full-resolution streaming, enabling sustained VQA sessions on resource-constrained wearables without sacrificing text understanding quality. --- ### OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage Authors: Akshat Naik, Jay Culligan, Yarin Gal, Philip Torr, Rahaf Aljundi, Alasdair Paren, Adel Bibi Published: 2026-02-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13477v2 As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has examined the safety and misuse risks associated with agents. However, much of this has focused on the single-agent case and/or setups missing basic engineering safeguards such as access control, revealing a scarcity of threat modeling in multi-agent systems. We investigate the security vulnerabilities of a popular multi-agent pattern known as the orchestrator setup, in which a central agent decomposes and delegates tasks to specialized agents. Through red-teaming a concrete setup representative of a likely future use case, we demonstrate a novel attack vector, OMNI-LEAK, that compromises several agents to leak sensitive data through a single indirect prompt injection, even in the presence of data access control. We report the susceptibility of frontier models to different categories of attacks, finding that both reasoning and non-reasoning models are vulnerable, even when the attacker lacks insider knowledge of the implementation details. Our work highlights the importance of safety research to generalize from single-agent to multi-agent settings, in order to reduce the serious risks of real-world privacy breaches and financial losses and overall public trust in AI agents. --- ### AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge Authors: Noriaki Hirose, Catherine Glossop, Dhruv Shah, Sergey Levine Published: 2026-02-13 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.13476v1 Robotic foundation models achieve strong generalization by leveraging internet-scale vision-language representations, but their massive computational cost creates a fundamental bottleneck: high inference latency. In dynamic environments, this latency breaks the control loop, rendering powerful models unsafe for real-time deployment. We propose AsyncVLA, an asynchronous control framework that decouples semantic reasoning from reactive execution. Inspired by hierarchical control, AsyncVLA runs a large foundation model on a remote workstation to provide high-level guidance, while a lightweight, onboard Edge Adapter continuously refines actions at high frequency. To bridge the domain gap between these asynchronous streams, we introduce an end-to-end finetuning protocol and a trajectory re-weighting strategy that prioritizes dynamic interactions. We evaluate our approach on real-world vision-based navigation tasks with communication delays up to 6 seconds. AsyncVLA achieves a 40% higher success rate than state-of-the-art baselines, effectively bridging the gap between the semantic intelligence of large models and the reactivity required for edge robotics. --- ### Efficient and Debiased Learning of Average Hazard Under Non-Proportional Hazards Authors: Xiang Meng, Lu Tian, Kenneth Kehl, Hajime Uno Published: 2026-02-13 Categories: stat.ME, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2602.13475v1 The hazard ratio from the Cox proportional hazards model is a ubiquitous summary of treatment effect. However, when hazards are non-proportional, the hazard ratio can lose a stable causal interpretation and become study-dependent because it effectively averages time-varying effects with weights determined by follow-up and censoring. We consider the average hazard (AH) as an alternative causal estimand: a population-level person-time event rate that remains well-defined and interpretable without assuming proportional hazards. Although AH can be estimated nonparametrically and regression-style adjustments have been proposed, existing approaches do not provide a general framework for flexible, high-dimensional nuisance estimation with valid sqrt{n} inference. We address this gap by developing a semiparametric, doubly robust framework for covariate-adjusted AH. We establish pathwise differentiability of AH in the nonparametric model, derive its efficient influence function, and construct cross-fitted, debiased estimators that leverage machine learning for nuisance estimation while retaining asymptotically normal, sqrt{n}-consistent inference under mild product-rate conditions. Simulations demonstrate that the proposed estimator achieves small bias and near-nominal confidence-interval coverage across proportional and non-proportional hazards settings, including crossing-hazards regimes where Cox-based summaries can be unstable. We illustrate practical utility in comparative effectiveness research by comparing immunotherapy regimens for advanced melanoma using SEER-Medicare linked data. --- ### NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines Authors: Guoan Wang, Shihao Yang, Feng Liu Published: 2026-02-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13473v4 Although foundation models have achieved remarkable success in general domains, applying them to electroencephalography (EEG) analysis is constrained by substantial data requirements and large parameter counts, which incur prohibitive computational costs and impede deployment in resource-constrained clinical environments. General-purpose automated machine learning frameworks are likewise ill-suited to this domain, since exploration within an unbounded programmatic space fails to incorporate essential neurophysiological priors and frequently yields neuroscientifically implausible solutions. We therefore propose NeuroWeaver, a unified autonomous evolutionary agent that generalizes across diverse EEG datasets and tasks by reformulating pipeline engineering as a discrete constrained optimization problem solved through large language model (LLM)-driven generation of executable code. A Domain-Informed Subspace Initialization confines the search to a neuroscientifically plausible manifold, while a Multi-Objective Evolutionary Optimization dynamically balances performance, novelty, and efficiency via self-reflective refinement. Across five heterogeneous benchmarks, NeuroWeaver synthesizes lightweight pipelines that outperform state-of-the-art task-specific methods on nearly all metrics and attain accuracy comparable to large-scale foundation models, even surpassing them on the HMC and Workload benchmarks with only $0.18$M and $0.011$M parameters, respectively. --- ### NeuroWeaver: An Autonomous Evolutionary Agent for Exploring the Programmatic Space of EEG Analysis Pipelines Authors: Guoan Wang, Shihao Yang, Jun-En Ding, Feng Liu Published: 2026-02-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13473v2 Although foundation models have demonstrated remarkable success in general domains, the application of these models to electroencephalography (EEG) analysis is constrained by substantial data requirements and high parameterization. These factors incur prohibitive computational costs, thereby impeding deployment in resource-constrained clinical environments. Conversely, general-purpose automated machine learning frameworks are often ill-suited for this domain, as exploration within an unbounded programmatic space fails to incorporate essential neurophysiological priors and frequently yields solutions that lack scientific plausibility. To address these limitations, we propose NeuroWeaver, a unified autonomous evolutionary agent designed to generalize across diverse EEG datasets and tasks by reformulating pipeline engineering as a discrete constrained optimization problem. Specifically, we employ a Domain-Informed Subspace Initialization to confine the search to neuroscientifically plausible manifolds, coupled with a Multi-Objective Evolutionary Optimization that dynamically balances performance, novelty, and efficiency via self-reflective refinement. Empirical evaluations across five heterogeneous benchmarks demonstrate that NeuroWeaver synthesizes lightweight solutions that consistently outperform state-of-the-art task-specific methods and achieve performance comparable to large-scale foundation models, despite utilizing significantly fewer parameters. --- ### How Multimodal Large Language Models Support Access to Visual Information: A Diary Study With Blind and Low Vision People Authors: Ricardo E. Gonzalez Penuela, Crescentia Jung, Sharon Y Lin, Ruiying Hu, Shiri Azenkot Published: 2026-02-13 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.13469v2 Multimodal large language models (MLLMs) are changing how Blind and Low Vision (BLV) people access visual information. Unlike traditional visual interpretation tools that only provide descriptions, MLLM-enabled applications offer conversational assistance, where users can ask questions to obtain goal-relevant details. However, evidence about their performance in the real-world and implications for BLV people's daily lives remains limited. To address this, we conducted a two-week diary study, where we captured 20 BLV participants' use of an MLLM-enabled visual interpretation application. Although participants rated the visual interpretations of the application as "trustworthy" (mean=3.76 out of 5, max=extremely trustworthy) and "somewhat satisfying" (mean=4.13 out of 5, max=very satisfying), the AI often produced incorrect answers (22.2%) or abstained (10.8%) from responding to users' requests. Our findings show that while MLLMs can improve visual interpretations' descriptive accuracy, supporting everyday use also depends on the "visual assistant" skill: behaviors for providing goal-directed, reliable assistance. We conclude by proposing the "visual assistant" skill and guidelines to help MLLM-enabled visual interpretation applications better support BLV people's access to visual information. --- ### Language Model Memory and Memory Models for Language Authors: Benjamin L. Badger Published: 2026-02-13 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.13466v2 The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically contain relatively little input information regardless of data and compute scale during training. In contrast, embeddings from autoencoders trained for input regeneration are capable of nearly perfect memory formation. The substitution of memory embeddings for token sequences leads to substantial computational efficiencies, motivating the introduction of a parallelizable encoder-decoder memory model architecture. Upon causal training these models contain information-poor embeddings incapable of arbitrary information access, but by combining causal and information retention objective functions they learn to form and decode information-rich memories. Training can be further streamlined by freezing a high fidelity encoder followed by a curriculum training approach where decoders first learn to process memories and then learn to additionally predict next tokens. We introduce the perspective that next token prediction training alone is poorly suited for accurate memory formation as the objective itself is non-invertible, motivating the use of combined objective functions for models where the entire input is not exposed. --- ### MoltNet: Understanding Social Behavior of AI Agents in the Agent-Native MoltBook Authors: Yi Feng, Chen Huang, Zhibo Man, Ryner Tan, Long P. Hoang, Shaoyang Xu, Wenxuan Zhang Published: 2026-02-13 Categories: cs.SI, cs.AI arXiv: https://arxiv.org/abs/2602.13458v2 Large-scale communities of AI agents are becoming increasingly prevalent, creating new environments for agent-agent social interaction. Prior work has examined multi-agent behavior primarily in controlled or small-scale settings, limiting our understanding of emergent social dynamics at scale. The recent emergence of MoltBook, a social networking platform designed explicitly for AI agents, presents a unique opportunity to study whether and how these interactions reproduce core human social mechanisms. We present MoltNet, a dataset tracking the full one-month activity trajectories of 148K AI agents on MoltBook (Jan.-Feb., 2026), and analyze their social interaction along four theory-grounded dimensions: \textit{intent and motivation}, \textit{norms and templates}, \textit{incentives and drift}, \textit{emotion and contagion}. Our analysis reveals that agents respond strongly to social rewards, converge on community-specific norms, and actively enforce them across community boundaries -- resembling human incentive sensitivity and normative conformity. However, they exhibit weak alignment with declared personas and display limited emotional reciprocity and dialogic engagement, diverging systematically from human online communities. These findings establish a first empirical portrait of agent social behavior at scale, with direct implications for the design and governance of AI-populated communities. --- ### Using Machine Learning to Enhance the Detection of Obfuscated Abusive Words in Swahili: A Focus on Child Safety Authors: Phyllis Nabangi, Abdul-Jalil Zakaria, Jema David Ndibwile Published: 2026-02-13 Categories: cs.CL, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2602.13455v1 The rise of digital technology has dramatically increased the potential for cyberbullying and online abuse, necessitating enhanced measures for detection and prevention, especially among children. This study focuses on detecting abusive obfuscated language in Swahili, a low-resource language that poses unique challenges due to its limited linguistic resources and technological support. Swahili is chosen due to its popularity and being the most widely spoken language in Africa, with over 16 million native speakers and upwards of 100 million speakers in total, spanning regions in East Africa and some parts of the Middle East. We employed machine learning models including Support Vector Machines (SVM), Logistic Regression, and Decision Trees, optimized through rigorous parameter tuning and techniques like Synthetic Minority Over-sampling Technique (SMOTE) to handle data imbalance. Our analysis revealed that, while these models perform well in high-dimensional textual data, our dataset's small size and imbalance limit our findings' generalizability. Precision, recall, and F1 scores were thoroughly analyzed, highlighting the nuanced performance of each model in detecting obfuscated language. This research contributes to the broader discourse on ensuring safer online environments for children, advocating for expanded datasets and advanced machine-learning techniques to improve the effectiveness of cyberbullying detection systems. Future work will focus on enhancing data robustness, exploring transfer learning, and integrating multimodal data to create more comprehensive and culturally sensitive detection mechanisms. --- ### LLM-Powered Automatic Translation and Urgency in Crisis Scenarios Authors: Belu Ticona, Antonis Anastasopoulos Published: 2026-02-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.13452v2 Large language models (LLMs) are increasingly proposed for crisis preparedness and response, particularly for multilingual communication. However, their suitability for high-stakes crisis contexts remains insufficiently evaluated. This work examines the performance of state-of-the-art LLMs and machine translation systems in crisis-domain translation, with a focus on preserving urgency, a critical property for effective crisis communication and triage. Using multilingual crisis data (TICO-19, 30 languages) and a newly introduced urgency-annotated dataset of 100 scenarios translated into 29 languages, we show that dedicated translation models and LLMs exhibit substantial quality degradation, particularly for low-resource languages. Beyond translation quality, we conduct a human annotation study revealing a striking asymmetry: human assessors maintain consistent urgency judgments regardless of prompt language, while LLM-based urgency classifications vary widely across languages for identical scenarios, at times spanning the full range from Not Urgent to Critical. These findings highlight significant risks in deploying general-purpose language technologies for crisis triage and underscore the need for multilingual, human-centered evaluation frameworks. --- ### LLM-Powered Automatic Translation and Urgency in Crisis Scenarios Authors: Belu Ticona, Antonis Anastasopoulos Published: 2026-02-13 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.13452v1 Large language models (LLMs) are increasingly proposed for crisis preparedness and response, particularly for multilingual communication. However, their suitability for high-stakes crisis contexts remains insufficiently evaluated. This work examines the performance of state-of-the-art LLMs and machine translation systems in crisis-domain translation, with a focus on preserving urgency, which is a critical property for effective crisis communication and triaging. Using multilingual crisis data and a newly introduced urgency-annotated dataset covering over 32 languages, we show that both dedicated translation models and LLMs exhibit substantial performance degradation and instability. Crucially, even linguistically adequate translations can distort perceived urgency, and LLM-based urgency classifications vary widely depending on the language of the prompt and input. These findings highlight significant risks in deploying general-purpose language technologies for crisis communication and underscore the need for crisis-aware evaluation frameworks. --- ### End-to-End NOMA with Perfect and Quantized CSI Over Rayleigh Fading Channels Authors: Selma Benouadah, Mojtaba Vaezi, Ruizhan Shen, Hamid Jafarkhani Published: 2026-02-13 Categories: cs.IT, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2602.13446v1 An end-to-end autoencoder (AE) framework is developed for downlink non-orthogonal multiple access (NOMA) over Rayleigh fading channels, which learns interference-aware and channel-adaptive super-constellations. While existing works either assume additive white Gaussian noise channels or treat fading channels without a fully end-to-end learning approach, our framework directly embeds the wireless channel into both training and inference. To account for practical channel state information (CSI), we further incorporate limited feedback via both uniform and Lloyd-Max quantization of channel gains and analyze their impact on AE training and bit error rate (BER) performance. Simulation results show that, with perfect CSI, the proposed AE outperforms the existing analytical NOMA schemes. In addition, Lloyd-Max quantization achieves superior BER performance compared to uniform quantization. These results demonstrate that end-to-end AEs trained directly over Rayleigh fading can effectively learn robust, interference-aware signaling strategies, paving the way for NOMA deployment in fading environments with realistic CSI constraints. --- ### FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation Authors: Huajian Zeng, Lingyun Chen, Jiaqi Yang, Yuantai Zhang, Fan Shi, Peidong Liu, Xingxing Zuo Published: 2026-02-13 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.13444v1 Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tasks because the underlying hand-object interaction (HOI) structure is not explicitly represented. An embodiment-agnostic interaction representation that captures this structure would make manipulation behaviors easier to validate and transfer across robots. We propose FlowHOI, a two-stage flow-matching framework that generates semantically grounded, temporally coherent HOI sequences, comprising hand poses, object poses, and hand-object contact states, conditioned on an egocentric observation, a language instruction, and a 3D Gaussian splatting (3DGS) scene reconstruction. We decouple geometry-centric grasping from semantics-centric manipulation, conditioning the latter on compact 3D scene tokens and employing a motion-text alignment loss to semantically ground the generated interactions in both the physical scene layout and the language instruction. To address the scarcity of high-fidelity HOI supervision, we introduce a reconstruction pipeline that recovers aligned hand-object trajectories and meshes from large-scale egocentric videos, yielding an HOI prior for robust generation. Across the GRAB and HOT3D benchmarks, FlowHOI achieves the highest action recognition accuracy and a 1.7$\times$ higher physics simulation success rate than the strongest diffusion-based baseline, while delivering a 40$\times$ inference speedup. We further demonstrate real-robot execution on four dexterous manipulation tasks, illustrating the feasibility of retargeting generated HOI representations to real-robot execution pipelines. --- ### Measuring Neural Network Complexity via Effective Degrees of Freedom Authors: Jia Zhou, Douglas Landsittel Published: 2026-02-13 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2602.13442v1 Quantifying the complexity of feed-forward neural networks (FFNNs) remains challenging due to their nonlinear, hierarchical structure and numerous parameters. We apply generalized degrees of freedom (GDF) to measure model complexity in FFNNs with binary outcomes, adapting the algorithm for discrete responses. We compare GDF with both the effective number of parameters derived via log-likelihood cross-validation and the null degrees of freedom of Landsittel et al. Through simulation studies and a real data analysis, we demonstrate that GDF provides a robust assessment of model complexity for neural network models, as it depends only on the sensitivity of fitted values to perturbations in the observed responses rather than on assumptions about the likelihood. In contrast, cross-validation-based estimates of model complexity and the null degrees of freedom rely on the correctness of the assumed likelihood and may exhibit substantial variability. We find that GDF, cross-validation-based measures, and null degrees of freedom yield similar assessments of model complexity only when the fitted model adequately represents the data-generating mechanism. These findings highlight GDF as a stable and broadly applicable measure of model complexity for neural networks in statistical modeling. --- ### Learning on the Fly: Replay-Based Continual Object Perception for Indoor Drones Authors: Sebastian-Ion Nae, Mihai-Eugen Barbu, Sebastian Mocanu, Marius Leordeanu Published: 2026-02-13 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.13440v1 Autonomous agents such as indoor drones must learn new object classes in real-time while limiting catastrophic forgetting, motivating Class-Incremental Learning (CIL). However, most unmanned aerial vehicle (UAV) datasets focus on outdoor scenes and offer limited temporally coherent indoor videos. We introduce an indoor dataset of $14,400$ frames capturing inter-drone and ground vehicle footage, annotated via a semi-automatic workflow with a $98.6\%$ first-pass labeling agreement before final manual verification. Using this dataset, we benchmark 3 replay-based CIL strategies: Experience Replay (ER), Maximally Interfered Retrieval (MIR), and Forgetting-Aware Replay (FAR), using YOLOv11-nano as a resource-efficient detector for deployment-constrained UAV platforms. Under tight memory budgets ($5-10\%$ replay), FAR performs better than the rest, achieving an average accuracy (ACC, $mAP_{50-95}$ across increments) of $82.96\%$ with $5\%$ replay. Gradient-weighted class activation mapping (Grad-CAM) analysis shows attention shifts across classes in mixed scenes, which is associated with reduced localization quality for drones. The experiments further demonstrate that replay-based continual learning can be effectively applied to edge aerial systems. Overall, this work contributes an indoor UAV video dataset with preserved temporal coherence and an evaluation of replay-based CIL under limited replay budgets. Project page: https://spacetime-vision-robotics-laboratory.github.io/learning-on-the-fly-cl --- ### Handling Supervision Scarcity in Chest X-ray Classification: Long-Tailed and Zero-Shot Learning Authors: Ha-Hieu Pham, Hai-Dang Nguyen, Thanh-Huy Nguyen, Min Xu, Ulas Bagci, Trung-Nghia Le, Huy-Hieu Pham Published: 2026-02-13 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13430v2 Chest X-Ray (CXR) classification in clinical practice is often limited by imperfect supervision, arising from (i) extreme long-tailed multi-label disease distributions and (ii) missing annotations for rare or previously unseen findings. The CXR-LT 2026 challenge addresses these issues on a PadChest-based benchmark with a 36-class label space split into 30 in-distribution classes for training and 6 out-of-distribution (OOD) classes for zero-shot evaluation. We present task-specific solutions tailored to the distinct supervision regimes. For Task 1 (long-tailed multi-label classification), we adopt an imbalance-aware multi-label learning strategy to improve recognition of tail classes while maintaining stable performance on frequent findings. For Task 2 (zero-shot OOD recognition), we propose a prediction approach that produces scores for unseen disease categories without using any supervised labels or examples from the OOD classes during training. Evaluated with macro-averaged mean Average Precision (mAP), our method achieves strong performance on both tasks, ranking first on the public leaderboard of the development phase. Code and pre-trained models are available at https://github.com/hieuphamha19/CXR_LT. --- ### Backdooring Bias in Large Language Models Authors: Anudeep Das, Prach Chantasantitam, Gurjot Singh, Lipeng He, Mariia Ponomarenko, Florian Kerschbaum Published: 2026-02-13 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.13427v1 Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has largely focused on a black-box threat model, with an adversary targeting the model builder's LLM. However, in the bias manipulation setting, the model builder themselves could be the adversary, warranting a white-box threat model where the attacker's ability to poison, and manipulate the poisoned data is substantially increased. Furthermore, despite growing research in semantically-triggered backdoors, most studies have limited themselves to syntactically-triggered attacks. Motivated by these limitations, we conduct an analysis consisting of over 1000 evaluations using higher poisoning ratios and greater data augmentation to gain a better understanding of the potential of syntactically- and semantically-triggered backdoor attacks in a white-box setting. In addition, we study whether two representative defense paradigms, model-intrinsic and model-extrinsic backdoor removal, are able to mitigate these attacks. Our analysis reveals numerous new findings. We discover that while both syntactically- and semantically-triggered attacks can effectively induce the target behaviour, and largely preserve utility, semantically-triggered attacks are generally more effective in inducing negative biases, while both backdoor types struggle with causing positive biases. Furthermore, while both defense types are able to mitigate these backdoors, they either result in a substantial drop in utility, or require high computational overhead. --- ### Metabolic cost of information processing in Poisson variational autoencoders Authors: Hadi Vafaii, Jacob L. Yates Published: 2026-02-13 Categories: stat.ML, cs.AI, q-bio.NC arXiv: https://arxiv.org/abs/2602.13421v2 Computation in biological systems is fundamentally energy-constrained, yet standard theories of computation treat energy as freely available. Here, we argue that variational free energy minimization under a Poisson assumption offers a principled path toward an energy-aware theory of computation. Our key observation is that the Kullback-Leibler (KL) divergence term in the Poisson free energy objective becomes proportional to the prior firing rates of model neurons, yielding an emergent metabolic cost term that penalizes high baseline activity. This structure couples an abstract information-theoretic quantity -- the *coding rate* -- to a concrete biophysical variable -- the *firing rate* -- which enables a trade-off between coding fidelity and energy expenditure. Such a coupling arises naturally in the Poisson variational autoencoder (P-VAE) -- a brain-inspired generative model that encodes inputs as discrete spike counts and recovers a spiking form of *sparse coding* as a special case -- but is absent from standard Gaussian VAEs. To demonstrate that this metabolic cost structure is unique to the Poisson formulation, we compare the P-VAE against Grelu-VAE, a Gaussian VAE with ReLU rectification applied to latent samples, which controls for the non-negativity constraint. Across a systematic sweep of the KL term weighting coefficient $β$ and latent dimensionality, we find that increasing $β$ monotonically increases sparsity and reduces average spiking activity in the P-VAE. In contrast, Grelu-VAE representations remain unchanged, confirming that the effect is specific to Poisson statistics rather than a byproduct of non-negative representations. These results establish Poisson variational inference as a promising foundation for a resource-constrained theory of computation. --- ### Protect$^*$: Steerable Retrosynthesis through Neuro-Symbolic State Encoding Authors: Shreyas Vinaya Sathyanarayana, Shah Rahil Kirankumar, Sharanabasava D. Hiremath, Bharath Ramsundar Published: 2026-02-13 Categories: q-bio.QM, cs.AI, cs.CL, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2602.13419v1 Large Language Models (LLMs) have shown remarkable potential in scientific domains like retrosynthesis; yet, they often lack the fine-grained control necessary to navigate complex problem spaces without error. A critical challenge is directing an LLM to avoid specific, chemically sensitive sites on a molecule - a task where unconstrained generation can lead to invalid or undesirable synthetic pathways. In this work, we introduce Protect$^*$, a neuro-symbolic framework that grounds the generative capabilities of Large Language Models (LLMs) in rigorous chemical logic. Our approach combines automated rule-based reasoning - using a comprehensive database of 55+ SMARTS patterns and 40+ characterized protecting groups - with the generative intuition of neural models. The system operates via a hybrid architecture: an ``automatic mode'' where symbolic logic deterministically identifies and guards reactive sites, and a ``human-in-the-loop mode'' that integrates expert strategic constraints. Through ``active state tracking,'' we inject hard symbolic constraints into the neural inference process via a dedicated protection state linked to canonical atom maps. We demonstrate this neuro-symbolic approach through case studies on complex natural products, including the discovery of a novel synthetic pathway for Erythromycin B, showing that grounding neural generation in symbolic logic enables reliable, expert-level autonomy. --- ### Text Has Curvature Authors: Karish Grover, Hanqing Zeng, Yinglong Xia, Christos Faloutsos, Geoffrey J. Gordon Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13418v2 Does natural language text have an intrinsic curvature? Language is increasingly modeled in curved geometries - hyperbolic spaces for hierarchy, mixed-curvature manifolds for compositional structure - yet a basic scientific question remains unresolved: what does curvature mean for text itself, in a way that is native to language rather than an artifact of the embedding space we choose? We argue that text does indeed have curvature, and show how to detect it, define it, and use it. To this end, we propose Texture, a text-native, word-level discrete curvature signal, and make three contributions. (a) Existence: We provide empirical and theoretical certificates that semantic inference in natural corpora is non-flat. (b) Definition: We define Texture as a signed two-axis curvature of the word-in-context belief field - the differential of reconciliation between prefix and suffix - measuring, via a debiased Schrödinger transport divergence, whether adding context from one side contracts the semantic effect of context from the other side (focus, positive) or expands it into competing continuations (fan-out, negative). (c) Utility: Texture is actionable: it serves as a general-purpose measurement and control primitive enabling geometry without geometric training; we instantiate it on two representative tasks, improving long-context inference through curvature-guided compression and retrieval-augmented generation through curvature-guided routing. Together, our results establish a text-native curvature paradigm, making Texture practically useful. --- ### Text Has Curvature Authors: Karish Grover, Hanqing Zeng, Yinglong Xia, Christos Faloutsos, Geoffrey J. Gordon Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13418v1 Does text have an intrinsic curvature? Language is increasingly modeled in curved geometries - hyperbolic spaces for hierarchy, mixed-curvature manifolds for compositional structure - yet a basic scientific question remains unresolved: what does curvature mean for text itself, in a way that is native to language rather than an artifact of the embedding space we choose? We argue that text does indeed have curvature, and show how to detect it, define it, and use it. To this end, we propose Texture, a text-native, word-level discrete curvature signal, and make three contributions. (a) Existence: We provide empirical and theoretical certificates that semantic inference in natural corpora is non-flat, i.e. language has inherent curvature. (b) Definition: We define Texture by reconciling left- and right-context beliefs around a masked word through a Schrodinger bridge, yielding a curvature field that is positive where context focuses meaning and negative where it fans out into competing continuations. (c) Utility: Texture is actionable: it serves as a general-purpose measurement and control primitive enabling geometry without geometric training; we instantiate it on two representative tasks, improving long-context inference through curvature-guided compression and retrieval-augmented generation through curvature-guided routing. Together, our results establish a text-native curvature paradigm, making curvature measurable and practically useful. --- ### High-Resolution Climate Projections Using Diffusion-Based Downscaling of a Lightweight Climate Emulator Authors: Haiwen Guan, Dibyajyoti Chakraborty, Moein Darman, Troy Arcomano, Ashesh Chattopadhyay, Romit Maulik Published: 2026-02-13 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.13416v2 The proliferation of data-driven models in weather and climate sciences has marked a significant paradigm shift, with advanced models demonstrating exceptional skill in medium-range forecasting. However, these models are often limited by long-term instabilities, climatological drift, and substantial computational costs during training and inference, restricting their broader application for climate studies. Addressing these limitations, Guan et al. (2024) introduced LUCIE, a lightweight, physically consistent climate emulator utilizing a Spherical Fourier Neural Operator (SFNO) architecture. This model is able to reproduce accurate long-term statistics including climatological mean and seasonal variability. However, LUCIE's native resolution (~300 km) is inadequate for detailed regional impact assessments. To overcome this limitation, we introduce a deep learning-based downscaling framework, leveraging probabilistic diffusion-based generative models with conditional and posterior sampling frameworks. These models downscale coarse LUCIE outputs to 25 km resolution. They are trained on approximately 14,000 ERA5 timesteps spanning 2000-2009 and evaluated on LUCIE predictions from 2010 to 2020. Model performance is assessed through diverse metrics, including latitude-averaged RMSE, power spectrum, probability density functions and First Empirical Orthogonal Function of the zonal wind. We observe that the proposed approach is able to preserve the coarse-grained dynamics from LUCIE while generating fine-scaled climatological statistics at ~28km resolution. --- ### FUTON: Fourier Tensor Network for Implicit Neural Representations Authors: Pooya Ashtari, Pourya Behmandpoor, Nikos Deligiannis, Aleksandra Pizurica Published: 2026-02-13 Categories: eess.IV, cs.CV, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2602.13414v1 Implicit neural representations (INRs) have emerged as powerful tools for encoding signals, yet dominant MLP-based designs often suffer from slow convergence, overfitting to noise, and poor extrapolation. We introduce FUTON (Fourier Tensor Network), which models signals as generalized Fourier series whose coefficients are parameterized by a low-rank tensor decomposition. FUTON implicitly expresses signals as weighted combinations of orthonormal, separable basis functions, combining complementary inductive biases: Fourier bases capture smoothness and periodicity, while the low-rank parameterization enforces low-dimensional spectral structure. We provide theoretical guarantees through a universal approximation theorem and derive an inference algorithm with complexity linear in the spectral resolution and the input dimension. On image and volume representation, FUTON consistently outperforms state-of-the-art MLP-based INRs while training 2--5$\times$ faster. On inverse problems such as image denoising and super-resolution, FUTON generalizes better and converges faster. ---