# Research Papers — 2026-02 · bundle page 79 of 210 > Full-text markdown of papers #3901–3950 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/79 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/78.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/80.md) ### A Scalable Curiosity-Driven Game-Theoretic Framework for Long-Tail Multi-Label Learning in Data Mining Authors: Jing Yang, Keze Wang Published: 2026-02-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.15330v1 The long-tail distribution, where a few head labels dominate while rare tail labels abound, poses a persistent challenge for large-scale Multi-Label Classification (MLC) in real-world data mining applications. Existing resampling and reweighting strategies often disrupt inter-label dependencies or require brittle hyperparameter tuning, especially as the label space expands to tens of thousands of labels. To address this issue, we propose Curiosity-Driven Game-Theoretic Multi-Label Learning (CD-GTMLL), a scalable cooperative framework that recasts long-tail MLC as a multi-player game - each sub-predictor ("player") specializes in a partition of the label space, collaborating to maximize global accuracy while pursuing intrinsic curiosity rewards based on tail label rarity and inter-player disagreement. This mechanism adaptively injects learning signals into under-represented tail labels without manual balancing or tuning. We further provide a theoretical analysis showing that our CD-GTMLL converges to a tail-aware equilibrium and formally links the optimization dynamics to improvements in the Rare-F1 metric. Extensive experiments across 7 benchmarks, including extreme multi-label classification datasets with 30,000+ labels, demonstrate that CD-GTMLL consistently surpasses state-of-the-art methods, with gains up to +1.6% P@3 on Wiki10-31K. Ablation studies further confirm the contributions of both game-theoretic cooperation and curiosity-driven exploration to robust tail performance. By integrating game theory with curiosity mechanisms, CD-GTMLL not only enhances model efficiency in resource-constrained environments but also paves the way for more adaptive learning in imbalanced data scenarios across industries like e-commerce and healthcare. --- ### EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use Authors: Siwei Wen, Zhangcheng Wang, Xingjian Zhang, Lei Huang, Wenjun Wu Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15329v2 Online video understanding requires models to perform continuous perception and long-range reasoning within potentially infinite visual streams. Its fundamental challenge lies in the conflict between the unbounded nature of streaming media input and the limited context window of Multimodal Large Language Models (MLLMs). Current methods primarily rely on passive processing, which often face a trade-off between maintaining long-range context and capturing the fine-grained details necessary for complex tasks. To address this, we introduce EventMemAgent, an active online video agent framework based on a hierarchical memory module. Our framework employs a dual-layer strategy for online videos: short-term memory detects event boundaries and utilizes event-granular reservoir sampling to process streaming video frames within a fixed-length buffer dynamically; long-term memory structuredly archives past observations on an event-by-event basis. Furthermore, we integrate a multi-granular perception toolkit for active, iterative evidence capture and employ Agentic Reinforcement Learning (Agentic RL) to end-to-end internalize reasoning and tool-use strategies into the agent's intrinsic capabilities. Experiments show that EventMemAgent achieves competitive results on online video benchmarks. The code will be released here: https://github.com/lingcco/EventMemAgent. --- ### EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use Authors: Siwei Wen, Zhangcheng Wang, Xingjian Zhang, Lei Huang, Wenjun Wu Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15329v1 Online video understanding requires models to perform continuous perception and long-range reasoning within potentially infinite visual streams. Its fundamental challenge lies in the conflict between the unbounded nature of streaming media input and the limited context window of Multimodal Large Language Models (MLLMs). Current methods primarily rely on passive processing, which often face a trade-off between maintaining long-range context and capturing the fine-grained details necessary for complex tasks. To address this, we introduce EventMemAgent, an active online video agent framework based on a hierarchical memory module. Our framework employs a dual-layer strategy for online videos: short-term memory detects event boundaries and utilizes event-granular reservoir sampling to process streaming video frames within a fixed-length buffer dynamically; long-term memory structuredly archives past observations on an event-by-event basis. Furthermore, we integrate a multi-granular perception toolkit for active, iterative evidence capture and employ Agentic Reinforcement Learning (Agentic RL) to end-to-end internalize reasoning and tool-use strategies into the agent's intrinsic capabilities. Experiments show that EventMemAgent achieves competitive results on online video benchmarks. The code will be released here: https://github.com/lingcco/EventMemAgent. --- ### Prescriptive Scaling Reveals the Evolution of Language Model Capabilities Authors: Hanlin Zhang, Jikai Jin, Vasilis Syrgkanis, Sham Kakade Published: 2026-02-17 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2602.15327v2 Machine learning model performance improvements tend to arise from competition and application. For deployment, we consider prescriptive scaling laws: given a pre-training compute budget, what downstream accuracy is attainable with contemporary post-training practice, and how stable is that mapping as the field evolves? Using large-scale observational evaluations with 5k existing and 2k newly evaluated model checkpoints spanning 2022-2026 across six benchmarks, we estimate capability boundaries, high conditional quantiles of benchmark scores as a function of log pre-training FLOPs, via smoothed quantile regression with a monotone, saturating sigmoid parameterization. We validate temporal reliability by fitting on earlier model generations and evaluating on later releases: across four of six tasks, the out-of-distribution coverage error remains below 2%, while math reasoning exhibits a consistently advancing boundary over time. For instance, at a budget of 10^24 FLOPs, the estimated attainable accuracies are 0.83 on IFEval and 0.54 on MATH Lvl 5. We then extend our approach to analyze task-dependent saturation and to probe contamination-related shifts on math reasoning tasks. Finally, we introduce a balanced I-optimal sampling algorithm that recovers near-full-data frontiers using roughly 20% of the parameter-count-weighted evaluation budget, as low as 5% on some tasks, while maintaining comparable calibration. Together, our work releases Proteus-2k, the latest model performance evaluation dataset, and introduces a practical methodology for translating compute budgets into reliable performance expectations and for monitoring when capability boundaries shift across time. --- ### SCENE OTA-FD: Self-Centering Noncoherent Estimator for Over-the-Air Federated Distillation Authors: Hao Chen, Zavareh Bozorgasl Published: 2026-02-17 Categories: eess.SP, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2602.15326v1 We propose SCENE (Self-Centering Noncoherent Estimator), a pilot-free and phase-invariant aggregation primitive for over-the-air federated distillation (OTA-FD). Each device maps its soft-label (class-probability) vector to nonnegative transmit energies under constant per-round power and constant-envelope signaling (PAPR near 1). At the server, a self-centering energy estimator removes the noise-energy offset and yields an unbiased estimate of the weighted soft-label average, with variance decaying on the order of 1/(SM) in the number of receive antennas M and repetition factor S. We also develop a pilot-free ratio-normalized variant that cancels unknown large-scale gains, provide a convergence bound consistent with coherent OTA-FD analyses, and present an overhead-based crossover comparison. SCENE targets short-coherence and hardware-constrained regimes, where avoiding per-round CSI is essential: it trades a modest noncoherent variance constant for zero uplink pilots, unbiased aggregation, and hardware-friendly transmission, and can outperform coherent designs when pilot overhead is non-negligible. --- ### AgriWorld:A World Tools Protocol Framework for Verifiable Agricultural Reasoning with Code-Executing LLM Agents Authors: Zhixing Zhang, Jesen Zhang, Hao Liu, Qinhan Lv, Jing Yang, Kaitong Cai, Keze Wang Published: 2026-02-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.15325v1 Foundation models for agriculture are increasingly trained on massive spatiotemporal data (e.g., multi-spectral remote sensing, soil grids, and field-level management logs) and achieve strong performance on forecasting and monitoring. However, these models lack language-based reasoning and interactive capabilities, limiting their usefulness in real-world agronomic workflows. Meanwhile, large language models (LLMs) excel at interpreting and generating text, but cannot directly reason over high-dimensional, heterogeneous agricultural datasets. We bridge this gap with an agentic framework for agricultural science. It provides a Python execution environment, AgriWorld, exposing unified tools for geospatial queries over field parcels, remote-sensing time-series analytics, crop growth simulation, and task-specific predictors (e.g., yield, stress, and disease risk). On top of this environment, we design a multi-turn LLM agent, Agro-Reflective, that iteratively writes code, observes execution results, and refines its analysis via an execute-observe-refine loop. We introduce AgroBench, with scalable data generation for diverse agricultural QA spanning lookups, forecasting, anomaly detection, and counterfactual "what-if" analysis. Experiments outperform text-only and direct tool-use baselines, validating execution-driven reflection for reliable agricultural reasoning. --- ### Unforgeable Watermarks for Language Models via Robust Signatures Authors: Huijia Lin, Kameron Shahabi, Min Jae Song Published: 2026-02-17 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.15323v1 Language models now routinely produce text that is difficult to distinguish from human writing, raising the need for robust tools to verify content provenance. Watermarking has emerged as a promising countermeasure, with existing work largely focused on model quality preservation and robust detection. However, current schemes provide limited protection against false attribution. We strengthen the notion of soundness by introducing two novel guarantees: unforgeability and recoverability. Unforgeability prevents adversaries from crafting false positives, texts that are far from any output from the watermarked model but are nonetheless flagged as watermarked. Recoverability provides an additional layer of protection: whenever a watermark is detected, the detector identifies the source text from which the flagged content was derived. Together, these properties strengthen content ownership by linking content exclusively to its generating model, enabling secure attribution and fine-grained traceability. We construct the first undetectable watermarking scheme that is robust, unforgeable, and recoverable with respect to substitutions (i.e., perturbations in Hamming metric). The key technical ingredient is a new cryptographic primitive called robust (or recoverable) digital signatures, which allow verification of messages that are close to signed ones, while preventing forgery of messages that are far from all previously signed messages. We show that any standard digital signature scheme can be boosted to a robust one using property-preserving hash functions (Boyle, LaVigne, and Vaikuntanathan, ITCS 2019). --- ### On Surprising Effectiveness of Masking Updates in Adaptive Optimizers Authors: Taejong Joo, Wenhan Xia, Cheolmin Kim, Ming Zhang, Eugene Ie Published: 2026-02-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.15322v1 Training large language models (LLMs) relies almost exclusively on dense adaptive optimizers with increasingly sophisticated preconditioners. We challenge this by showing that randomly masking parameter updates can be highly effective, with a masked variant of RMSProp consistently outperforming recent state-of-the-art optimizers. Our analysis reveals that the random masking induces a curvature-dependent geometric regularization that smooths the optimization trajectory. Motivated by this finding, we introduce Momentum-aligned gradient masking (Magma), which modulates the masked updates using momentum-gradient alignment. Extensive LLM pre-training experiments show that Magma is a simple drop-in replacement for adaptive optimizers with consistent gains and negligible computational overhead. Notably, for the 1B model size, Magma reduces perplexity by over 19\% and 9\% compared to Adam and Muon, respectively. --- ### Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs Authors: Libo Zhang, Zhaoning Zhang, Wangyang Hong, Peng Qiao, Dongsheng Li Published: 2026-02-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.15318v1 Although speculative decoding is widely used to accelerate Vision-Language Models (VLMs) inference, it faces severe performance collapse when applied to Video Large Language Models (Vid-LLMs). The draft model typically falls into the trap of attention dilution and negative visual gain due to key-value cache explosion and context window mismatches. We observe a visual semantic internalization phenomenon in Vid-LLMs, indicating that critical visual semantics are implicitly encoded into text hidden states during deep-layer interactions, which renders raw visual inputs structurally redundant during deep inference. To address this, we propose the Sparrow framework, which first utilizes visually-aware text-anchored window attention via hidden state reuse to fully offload visual computation to the target model, and leverages intermediate-layer visual state bridging to train the draft model with semantic-rich intermediate states, thereby filtering out low-level visual noise. Additionally, a multi-token prediction strategy is introduced to bridge the training-inference distribution shift. Experiments show that Sparrow achieves an average speedup of 2.82x even with 25k visual tokens, effectively resolving the performance degradation in long sequences and offering a practical solution for real-time long video tasks. --- ### Training-Free Zero-Shot Anomaly Detection in 3D Brain MRI with 2D Foundation Models Authors: Tai Le-Gia, Jaehyun Ahn Published: 2026-02-17 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2602.15315v1 Zero-shot anomaly detection (ZSAD) has gained increasing attention in medical imaging as a way to identify abnormalities without task-specific supervision, but most advances remain limited to 2D datasets. Extending ZSAD to 3D medical images has proven challenging, with existing methods relying on slice-wise features and vision-language models, which fail to capture volumetric structure. In this paper, we introduce a fully training-free framework for ZSAD in 3D brain MRI that constructs localized volumetric tokens by aggregating multi-axis slices processed by 2D foundation models. These 3D patch tokens restore cubic spatial context and integrate directly with distance-based, batch-level anomaly detection pipelines. The framework provides compact 3D representations that are practical to compute on standard GPUs and require no fine-tuning, prompts, or supervision. Our results show that training-free, batch-based ZSAD can be effectively extended from 2D encoders to full 3D MRI volumes, offering a simple and robust approach for volumetric anomaly detection. --- ### Mnemis: Dual-Route Retrieval on Hierarchical Graphs for Long-Term LLM Memory Authors: Zihao Tang, Xin Yu, Ziyu Xiao, Zengxuan Wen, Zelin Li, Jiaxi Zhou, Hualei Wang, Haohua Wang, Haizhen Huang, Weiwei Deng, Feng Sun, Qi Zhang Published: 2026-02-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.15313v2 AI Memory, specifically how models organizes and retrieves historical messages, becomes increasingly valuable to Large Language Models (LLMs), yet existing methods (RAG and Graph-RAG) primarily retrieve memory through similarity-based mechanisms. While efficient, such System-1-style retrieval struggles with scenarios that require global reasoning or comprehensive coverage of all relevant information. In this work, We propose Mnemis, a novel memory framework that integrates System-1 similarity search with a complementary System-2 mechanism, termed Global Selection. Mnemis organizes memory into a base graph for similarity retrieval and a hierarchical graph that enables top-down, deliberate traversal over semantic hierarchies. By combining the complementary strength from both retrieval routes, Mnemis retrieves memory items that are both semantically and structurally relevant. Mnemis achieves state-of-the-art performance across all compared methods on long-term memory benchmarks, scoring 93.9 on LoCoMo and 91.6 on LongMemEval-S using GPT-4.1-mini. --- ### Extracting Consumer Insight from Text: A Large Language Model Approach to Emotion and Evaluation Measurement Authors: Stephan Ludwig, Peter J. Danaher, Xiaohao Yang, Yu-Ting Lin, Ehsan Abedin, Dhruv Grewal, Lan Du Published: 2026-02-17 Categories: cs.CL, econ.EM arXiv: https://arxiv.org/abs/2602.15312v1 Accurately measuring consumer emotions and evaluations from unstructured text remains a core challenge for marketing research and practice. This study introduces the Linguistic eXtractor (LX), a fine-tuned, large language model trained on consumer-authored text that also has been labeled with consumers' self-reported ratings of 16 consumption-related emotions and four evaluation constructs: trust, commitment, recommendation, and sentiment. LX consistently outperforms leading models, including GPT-4 Turbo, RoBERTa, and DeepSeek, achieving 81% macro-F1 accuracy on open-ended survey responses and greater than 95% accuracy on third-party-annotated Amazon and Yelp reviews. An application of LX to online retail data, using seemingly unrelated regression, affirms that review-expressed emotions predict product ratings, which in turn predict purchase behavior. Most emotional effects are mediated by product ratings, though some emotions, such as discontent and peacefulness, influence purchase directly, indicating that emotional tone provides meaningful signals beyond star ratings. To support its use, a no-code, cost-free, LX web application is available, enabling scalable analyses of consumer-authored text. In establishing a new methodological foundation for consumer perception measurement, this research demonstrates new methods for leveraging large language models to advance marketing research and practice, thereby achieving validated detection of marketing constructs from consumer data. --- ### Sparse Additive Model Pruning for Order-Based Causal Structure Learning Authors: Kentaro Kanamori, Hirofumi Suzuki, Takuya Takagi Published: 2026-02-17 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.15306v1 Causal structure learning, also known as causal discovery, aims to estimate causal relationships between variables as a form of a causal directed acyclic graph (DAG) from observational data. One of the major frameworks is the order-based approach that first estimates a topological order of the underlying DAG and then prunes spurious edges from the fully-connected DAG induced by the estimated topological order. Previous studies often focus on the former ordering step because it can dramatically reduce the search space of DAGs. In practice, the latter pruning step is equally crucial for ensuring both computational efficiency and estimation accuracy. Most existing methods employ a pruning technique based on generalized additive models and hypothesis testing, commonly known as CAM-pruning. However, this approach can be a computational bottleneck as it requires repeatedly fitting additive models for all variables. Furthermore, it may harm estimation quality due to multiple testing. To address these issues, we introduce a new pruning method based on sparse additive models, which enables direct pruning of redundant edges without relying on hypothesis testing. We propose an efficient algorithm for learning sparse additive models by combining the randomized tree embedding technique with group-wise sparse regression. Experimental results on both synthetic and real datasets demonstrated that our method is significantly faster than existing pruning methods while maintaining comparable or superior accuracy. --- ### Hybrid Federated and Split Learning for Privacy Preserving Clinical Prediction and Treatment Optimization Authors: Farzana Akter, Rakib Hossain, Deb Kanna Roy Toushi, Mahmood Menon Khan, Sultana Amin, Lisan Al Amin Published: 2026-02-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.15304v1 Collaborative clinical decision support is often constrained by governance and privacy rules that prevent pooling patient-level records across institutions. We present a hybrid privacy-preserving framework that combines Federated Learning (FL) and Split Learning (SL) to support decision-oriented healthcare modeling without raw-data sharing. The approach keeps feature-extraction trunks on clients while hosting prediction heads on a coordinating server, enabling shared representation learning and exposing an explicit collaboration boundary where privacy controls can be applied. Rather than assuming distributed training is inherently private, we audit leakage empirically using membership inference on cut-layer representations and study lightweight defenses based on activation clipping and additive Gaussian noise. We evaluate across three public clinical datasets under non-IID client partitions using a unified pipeline and assess performance jointly along four deployment-relevant axes: factual predictive utility, uplift-based ranking under capacity constraints, audited privacy leakage, and communication overhead. Results show that hybrid FL-SL variants achieve competitive predictive performance and decision-facing prioritization behavior relative to standalone FL or SL, while providing a tunable privacy-utility trade-off that can reduce audited leakage without requiring raw-data sharing. Overall, the work positions hybrid FL-SL as a practical design space for privacy-preserving healthcare decision support where utility, leakage risk, and deployment cost must be balanced explicitly. --- ### X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detection Authors: Qi Zhang, Dian Chen, Lance M. Kaplan, Audun Jøsang, Dong Hyun Jeong, Feng Chen, Jin-Hee Cho Published: 2026-02-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.15298v1 Misclassifications in spam and phishing detection are very harmful, as false negatives expose users to attacks while false positives degrade trust. Existing uncertainty-based detectors can flag potential errors, but possibly be deceived and offer limited interpretability. This paper presents X-MAP, an eXplainable Misclassification Analysis and Profilling framework that reveals topic-level semantic patterns behind model failures. X-MAP combines SHAP-based feature attributions with non-negative matrix factorization to build interpretable topic profiles for reliably classified spam/phishing and legitimate messages, and measures each message's deviation from these profiles using Jensen-Shannon divergence. Experiments on SMS and phishing datasets show that misclassified messages exhibit at least two times larger divergence than correctly classified ones. As a detector, X-MAP achieves up to 0.98 AUROC and lowers the false-rejection rate at 95% TRR to 0.089 on positive predictions. When used as a repair layer on base detectors, it recovers up to 97% of falsely rejected correct predictions with moderate leakage. These results demonstrate X-MAP's effectiveness and interpretability for improving spam and phishing detection. --- ### EAA: Automating materials characterization with vision language model agents Authors: Ming Du, Yanqi Luo, Srutarshi Banerjee, Michael Wojcik, Jelena Popovic, Mathew J. Cherukara Published: 2026-02-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.15294v1 We present Experiment Automation Agents (EAA), a vision-language-model-driven agentic system designed to automate complex experimental microscopy workflows. EAA integrates multimodal reasoning, tool-augmented action, and optional long-term memory to support both autonomous procedures and interactive user-guided measurements. Built on a flexible task-manager architecture, the system enables workflows ranging from fully agent-driven automation to logic-defined routines that embed localized LLM queries. EAA further provides a modern tool ecosystem with two-way compatibility for Model Context Protocol (MCP), allowing instrument-control tools to be consumed or served across applications. We demonstrate EAA at an imaging beamline at the Advanced Photon Source, including automated zone plate focusing, natural language-described feature search, and interactive data acquisition. These results illustrate how vision-capable agents can enhance beamline efficiency, reduce operational burden, and lower the expertise barrier for users. --- ### The Information Geometry of Softmax: Probing and Steering Authors: Kiho Park, Todd Nief, Yo Joong Choe, Victor Veitch Published: 2026-02-17 Categories: cs.LG, cs.AI, cs.CL, stat.ML arXiv: https://arxiv.org/abs/2602.15293v2 This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The motivating observation is that the natural geometry of these representation spaces should reflect the way models use representations to produce behavior. We focus on the important special case of representations that define softmax distributions. In this case, we argue that the natural geometry is information geometry. Our focus is on the role of information geometry on semantic encoding and the linear representation hypothesis. As an illustrative application, we develop "dual steering", a method for robustly steering representations to exhibit a particular concept using linear probes. We prove that dual steering optimally modifies the target concept while minimizing changes to off-target concepts. Empirically, we find that dual steering enhances the controllability and stability of concept manipulation. --- ### Consistency-Preserving Diverse Video Generation Authors: Xinshuang Liu, Runfa Blark Li, Truong Nguyen Published: 2026-02-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.15287v2 Text-to-video generation is expensive, so only a few samples are typically produced per prompt. In this low-sample regime, maximizing the value of each batch requires high cross-video diversity. Recent methods improve diversity for image generation, but for videos they often degrade within-video temporal consistency and require costly backpropagation through a video decoder. We propose a joint-sampling framework for flow-matching video generators that improves batch diversity while preserving temporal consistency. Our approach applies diversity-driven updates and then removes only the components that would decrease a temporal-consistency objective. To avoid image-space gradients, we compute both objectives with lightweight latent-space models, avoiding video decoding and decoder backpropagation. Experiments on a state-of-the-art text-to-video flow-matching model show diversity close to strong joint-sampling baselines while substantially improving temporal consistency and color naturalness. Our code is available at https://github.com/XinshuangL/Diverse-Video. --- ### AI-Paging: Lease-Based Execution Anchoring for Network-Exposed AI-as-a-Service Authors: Mohaned Chraiti, Merve Saimler Published: 2026-02-17 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2602.15286v2 With AI-as-a-Service (AIaaS) now deployed across multiple providers and model tiers, selecting the appropriate model instance at run time is increasingly outside the end user's knowledge and operational control. Accordingly, the 6G service providers are envisioned to play a crucial role in exposing AIaaS in a setting where users submit only an intent while the network helps in the intent-to-model matching (resolution) and execution placement under policy, trust, and Quality of Service (QoS) constraints. The network role becomes to discover candidate execution endpoints and selects a suitable model/anchor under policy and QoS constraints in a process referred here to as AI-paging (by analogy to cellular call paging). In the proposed architecture, AI-paging is a control-plane transaction that resolves an intent into an AI service identity (AISI), a scoped session token (AIST), and an expiring admission lease (COMMIT) that authorizes user-plane steering to a selected AI execution anchor (AEXF) under a QoS binding. AI-Paging enforces two invariants: (i) lease-gated steering (without COMMIT, no steering state is installed) and (ii) make-before-break anchoring to support continuity and reliability of AIaaS services under dynamic network conditions. We prototype AI-Paging using existing control- and user-plane mechanisms (service-based control, QoS flows, and policy-based steering) with no new packet headers, ensuring compatibility with existing 3GPP-based exposure and management architectures, and evaluate transaction latency, relocation interruption, enforcement correctness under lease expiry, and audit-evidence overhead under mobility and failures. --- ### Complex-Valued Unitary Representations as Classification Heads for Improved Uncertainty Quantification in Deep Neural Networks Authors: Akbar Anbar Jafari, Cagri Ozcinar, Gholamreza Anbarjafari Published: 2026-02-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.15283v1 Modern deep neural networks achieve high predictive accuracy but remain poorly calibrated: their confidence scores do not reliably reflect the true probability of correctness. We propose a quantum-inspired classification head architecture that projects backbone features into a complex-valued Hilbert space and evolves them under a learned unitary transformation parameterised via the Cayley map. Through a controlled hybrid experimental design - training a single shared backbone and comparing lightweight interchangeable heads - we isolate the effect of complex-valued unitary representations on calibration. Our ablation study on CIFAR-10 reveals that the unitary magnitude head (complex features evolved under a Cayley unitary, read out via magnitude and softmax) achieves an Expected Calibration Error (ECE) of 0.0146, representing a 2.4x improvement over a standard softmax head (0.0355) and a 3.5x improvement over temperature scaling (0.0510). Surprisingly, replacing the softmax readout with a Born rule measurement layer - the quantum-mechanically motivated approach - degrades calibration to an ECE of 0.0819. On the CIFAR-10H human-uncertainty benchmark, the wave function head achieves the lowest KL-divergence (0.336) to human soft labels among all compared methods, indicating that complex-valued representations better capture the structure of human perceptual ambiguity. We provide theoretical analysis connecting norm-preserving unitary dynamics to calibration through feature-space geometry, report negative results on out-of-distribution detection and sentiment analysis to delineate the method's scope, and discuss practical implications for safety-critical applications. Code is publicly available. --- ### High-Fidelity Network Management for Federated AI-as-a-Service: Cross-Domain Orchestration Authors: Mohaned Chraiti, Ozgur Ercetin, Merve Saimler Published: 2026-02-17 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2602.15281v2 To support the emergence of AI-as-a-Service (AIaaS), communication service providers (CSPs) are on the verge of a radical transformation-from pure connectivity providers to AIaaS a managed network service (control-and-orchestration plane that exposes AI models). In this model, the CSP is responsible not only for transport/communications, but also for intent-to-model resolution and joint network-compute orchestration, i.e., reliable and timely end-to-end delivery. The resulting end-to-end AIaaS service thus becomes governed by communications impairments (delay, loss) and inference impairments (latency, error). A central open problem is an operational AIaaS control-and-orchestration framework that enforces high fidelity, particularly under multi-domain federation. This paper introduces an assurance-oriented AIaaS management plane based on Tail-Risk Envelopes (TREs): signed, composable per-domain descriptors that combine deterministic guardrails with stochastic rate-latency-impairment models. Using stochastic network calculus, we derive bounds on end-to-end delay violation probabilities across tandem domains and obtain an optimization-ready risk-budget decomposition. We show that tenant-level reservations prevent bursty traffic from inflating tail latency under TRE contracts. An auditing layer then uses runtime telemetry to estimate extreme-percentile performance, quantify uncertainty, and attribute tail-risk to each domain for accountability. Packet-level Monte-Carlo simulations demonstrate improved p99.9 compliance under overload via admission control and robust tenant isolation under correlated burstiness. --- ### Visual Persuasion: What Influences Decisions of Vision-Language Models? Authors: Manuel Cherep, Pranav M R, Pattie Maes, Nikhil Singh Published: 2026-02-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.15278v2 The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisions at scale, deciding what to click, recommend, or buy. Yet, we know little about the structure of their visual preferences. We introduce a framework for studying this by placing VLMs in controlled image-based choice tasks and systematically perturbing their inputs. Our key idea is to treat the agent's decision function as a latent visual utility that can be inferred through revealed preference: choices between systematically edited images. Starting from common images, such as product photos, we propose methods for visual prompt optimization, adapting text optimization methods to iteratively propose and apply visually plausible modifications using an image generation model (such as in composition, lighting, or background). We then evaluate which edits increase selection probability. Through large-scale experiments on frontier VLMs, we demonstrate that optimized edits significantly shift choice probabilities in head-to-head comparisons. We develop an automatic interpretability pipeline to explain these preferences, identifying consistent visual themes that drive selection. We argue that this approach offers a practical and efficient way to surface visual vulnerabilities, safety concerns that might otherwise be discovered implicitly in the wild, supporting more proactive auditing and governance of image-based AI agents. --- ### Accelerating Large-Scale Dataset Distillation via Exploration-Exploitation Optimization Authors: Muhammad J. Alahmadi, Peng Gao, Feiyi Wang, Dongkuan Xu Published: 2026-02-17 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.15277v2 Dataset distillation compresses the original data into compact synthetic datasets, reducing training time and storage while retaining model performance, enabling deployment under limited resources. Although recent decoupling-based distillation methods enable dataset distillation at large scale, they continue to face an efficiency gap: optimization-based decoupling methods achieve higher accuracy but demand intensive computation, whereas optimization-free decoupling methods are efficient but sacrifice accuracy. To overcome this trade-off, we propose Exploration--Exploitation Distillation (E$^2$D), a simple, practical method that minimizes redundant computation through an efficient pipeline that begins with full-image initialization to preserve semantic integrity and feature diversity. It then uses a two-phase optimization strategy: an exploration phase that performs uniform updates and identifies high-loss regions, and an exploitation phase that focuses updates on these regions to accelerate convergence. We evaluate E$^2$D on large-scale benchmarks, surpassing the state-of-the-art on ImageNet-1K while being $18\times$ faster, and on ImageNet-21K, our method substantially improves accuracy while remaining $4.3\times$ faster. These results demonstrate that targeted, redundancy-reducing updates, rather than brute-force optimization, bridge the gap between accuracy and efficiency in large-scale dataset distillation. Code is available at https://github.com/ncsu-dk-lab/E2D. --- ### When Remembering and Planning are Worth it: Navigating under Change Authors: Omid Madani, J. Brian Burns, Reza Eghbali, Thomas L. Dean Published: 2026-02-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.15274v1 We explore how different types and uses of memory can aid spatial navigation in changing uncertain environments. In the simple foraging task we study, every day, our agent has to find its way from its home, through barriers, to food. Moreover, the world is non-stationary: from day to day, the location of the barriers and food may change, and the agent's sensing such as its location information is uncertain and very limited. Any model construction, such as a map, and use, such as planning, needs to be robust against these challenges, and if any learning is to be useful, it needs to be adequately fast. We look at a range of strategies, from simple to sophisticated, with various uses of memory and learning. We find that an architecture that can incorporate multiple strategies is required to handle (sub)tasks of a different nature, in particular for exploration and search, when food location is not known, and for planning a good path to a remembered (likely) food location. An agent that utilizes non-stationary probability learning techniques to keep updating its (episodic) memories and that uses those memories to build maps and plan on the fly (imperfect maps, i.e. noisy and limited to the agent's experience) can be increasingly and substantially more efficient than the simpler (minimal-memory) agents, as the task difficulties such as distance to goal are raised, as long as the uncertainty, from localization and change, is not too large. --- ### FrameRef: A Framing Dataset and Simulation Testbed for Modeling Bounded Rational Information Health Authors: Victor De Lima, Jiqun Liu, Grace Hui Yang Published: 2026-02-17 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2602.15273v1 Information ecosystems increasingly shape how people internalize exposure to adverse digital experiences, raising concerns about the long-term consequences for information health. In modern search and recommendation systems, ranking and personalization policies play a central role in shaping such exposure and its long-term effects on users. To study these effects in a controlled setting, we present FrameRef, a large-scale dataset of 1,073,740 systematically reframed claims across five framing dimensions: authoritative, consensus, emotional, prestige, and sensationalist, and propose a simulation-based framework for modeling sequential information exposure and reinforcement dynamics characteristic of ranking and recommendation systems. Within this framework, we construct framing-sensitive agent personas by fine-tuning language models with framing-conditioned loss attenuation, inducing targeted biases while preserving overall task competence. Using Monte Carlo trajectory sampling, we show that small, systematic shifts in acceptance and confidence can compound over time, producing substantial divergence in cumulative information health trajectories. Human evaluation further confirms that FrameRef's generated framings measurably affect human judgment. Together, our dataset and framework provide a foundation for systematic information health research through simulation, complementing and informing responsible human-centered research. We release FrameRef, code, documentation, human evaluation data, and persona adapter models at https://github.com/infosenselab/frameref. --- ### Enhancing Diversity and Feasibility: Joint Population Synthesis from Multi-source Data Using Generative Models Authors: Farbod Abbasi, Zachary Patterson, Bilal Farooq Published: 2026-02-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.15270v1 Generating realistic synthetic populations is essential for agent-based models (ABM) in transportation and urban planning. Current methods face two major limitations. First, many rely on a single dataset or follow a sequential data fusion and generation process, which means they fail to capture the complex interplay between features. Second, these approaches struggle with sampling zeros (valid but unobserved attribute combinations) and structural zeros (infeasible combinations due to logical constraints), which reduce the diversity and feasibility of the generated data. This study proposes a novel method to simultaneously integrate and synthesize multi-source datasets using a Wasserstein Generative Adversarial Network (WGAN) with gradient penalty. This joint learning method improves both the diversity and feasibility of synthetic data by defining a regularization term (inverse gradient penalty) for the generator loss function. For the evaluation, we implement a unified evaluation metric for similarity, and place special emphasis on measuring diversity and feasibility through recall, precision, and the F1 score. Results show that the proposed joint approach outperforms the sequential baseline, with recall increasing by 7\% and precision by 15\%. Additionally, the regularization term further improves diversity and feasibility, reflected in a 10\% increase in recall and 1\% in precision. We assess similarity distributions using a five-metric score. The joint approach performs better overall, and reaches a score of 88.1 compared to 84.6 for the sequential method. Since synthetic populations serve as a key input for ABM, this multi-source generative approach has the potential to significantly enhance the accuracy and reliability of ABM. --- ### FTimeXer: Frequency-aware Time-series Transformer with Exogenous variables for Robust Carbon Footprint Forecasting Authors: Qingzhong Li, Yue Hu, Zhou Long, Qingchang Ma, Hui Ma, Jinhai Sa Published: 2026-02-16 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.02347v1 Accurate and up-to-date forecasting of the power grid's carbon footprint is crucial for effective product carbon footprint (PCF) accounting and informed decarbonization decisions. However, the carbon intensity of the grid exhibits high non-stationarity, and existing methods often struggle to effectively leverage periodic and oscillatory patterns. Furthermore, these methods tend to perform poorly when confronted with irregular exogenous inputs, such as missing data or misalignment. To tackle these challenges, we propose FTimeXer, a frequency-aware time-series Transformer designed with a robust training scheme that accommodates exogenous factors. FTimeXer features an Fast Fourier Transform (FFT)-driven frequency branch combined with gated time-frequency fusion, allowing it to capture multi-scale periodicity effectively. It also employs stochastic exogenous masking in conjunction with consistency regularization, which helps reduce spurious correlations and enhance stability. Experiments conducted on three real-world datasets show consistent improvements over strong baselines. As a result, these enhancements lead to more reliable forecasts of grid carbon factors, which are essential for effective PCF accounting and informed decision-making regarding decarbonization. --- ### Fine-Tune, Don't Prompt, Your Language Model to Identify Biased Language in Clinical Notes Authors: Isotta Landi, Eugenia Alleva, Nicole Bussola, Rebecca M. Cohen, Sarah Nowlin, Leslee J. Shaw, Alexander W. Charney, Kimberly B. Glazer Published: 2026-02-16 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.10004v1 Clinical documentation can contain emotionally charged language with stigmatizing or privileging valences. We present a framework for detecting and classifying such language as stigmatizing, privileging, or neutral. We constructed a curated lexicon of biased terms scored for emotional valence. We then used lexicon-based matching to extract text chunks from OB-GYN delivery notes (Mount Sinai Hospital, NY) and MIMIC-IV discharge summaries across multiple specialties. Three clinicians annotated all chunks, enabling characterization of valence patterns across specialties and healthcare systems. We benchmarked multiple classification strategies (zero-shot prompting, in-context learning, and supervised fine-tuning) across encoder-only models (GatorTron) and generative large language models (Llama). Fine-tuning with lexically primed inputs consistently outperformed prompting approaches. GatorTron achieved an F1 score of 0.96 on the OB-GYN test set, outperforming larger generative models while requiring minimal prompt engineering and fewer computational resources. External validation on MIMIC-IV revealed limited cross-domain generalizability (F1 < 0.70, 44% drop). Training on the broader MIMIC-IV dataset improved generalizability when testing on OB-GYN (F1 = 0.71, 11% drop), but at the cost of reduced precision. Our findings demonstrate that fine-tuning outperforms prompting for emotional valence classification and that models must be adapted to specific medical specialties to achieve clinically appropriate performance. The same terms can carry different emotional valences across specialties: words with clinical meaning in one context may be stigmatizing in another. For bias detection, where misclassification risks undermining clinician trust or perpetuating patient harm, specialty-specific fine-tuning is essential to capture these semantic shifts. * Equal contribution. --- ### Probing the Limits of the Lie Detector Approach to LLM Deception Authors: Tom-Felix Thormann Published: 2026-02-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.10003v1 Mechanistic approaches to deception in large language models (LLMs) often rely on "lie detectors", that is, truth probes trained to identify internal representations of model outputs as false. The lie detector approach to LLM deception implicitly assumes that deception is coextensive with lying. This paper challenges that assumption. It experimentally investigates whether LLMs can deceive without producing false statements and whether truth probes fail to detect such behavior. Across three open-source LLMs, it is shown that some models reliably deceive by producing misleading non-falsities, particularly when guided by few-shot prompting. It is further demonstrated that truth probes trained on standard true-false datasets are significantly better at detecting lies than at detecting deception without lying, confirming a critical blind spot of current mechanistic deception detection approaches. It is proposed that future work should incorporate non-lying deception in dialogical settings into probe training and explore representations of second-order beliefs to more directly target the conceptual constituents of deception. --- ### SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks Authors: Srivatsa Kundurthy, Clara Na, Michael Handley, Zach Kirshner, Chen Bo Calvin Zhang, Manasi Sharma, Emma Strubell, John Ling Published: 2026-02-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.10002v2 We consider the task of end-to-end spreadsheet generation, where language models produce spreadsheet artifacts to satisfy users' explicit and implicit constraints, specified in natural language. We introduce SpreadsheetArena, a platform for evaluating models' performance on the task via blind pairwise preference votes of LLM-generated spreadsheet workbooks. As with other complex, open-ended tasks, relevant evaluation criteria can vary greatly across use cases, often in ways that are difficult to formalize. Compared to general dialogue or text generation settings, spreadsheet generation presents unique challenges and opportunities: the task output structure is well-defined and multi-dimensional, and there are often complex interactivity and layout considerations. We observe that stylistic, structural, and functional features of preferred spreadsheets vary meaningfully across prompts. Expert evaluations of spreadsheets for finance prompts suggest that even highly ranked models do not reliably produce spreadsheets aligned with domain-specific best practices. We host a live arena and release a dataset of prompts, generated spreadsheets, and preference votes, which we hope will facilitate further study of tasks operating over spreadsheets as a challenging and interesting class of complex, open-ended tasks for LLMs. --- ### Leveraging Wikidata for Geographically Informed Sociocultural Bias Dataset Creation: Application to Latin America Authors: Yannis Karmim, Renato Pino, Hernan Contreras, Hernan Lira, Sebastian Cifuentes, Simon Escoffier, Luis Martí, Djamé Seddah, Valentin Barrière Published: 2026-02-16 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.10001v2 Large Language Models (LLMs) exhibit inequalities with respect to various cultural contexts. Most prominent open-weights models are trained on Global North data and show prejudicial behavior towards other cultures. Moreover, there is a notable lack of resources to detect biases in non-English languages, especially from Latin America (Latam), a continent containing various cultures, even though they share a common cultural ground. We propose to leverage the content of Wikipedia, the structure of the Wikidata knowledge graph, and expert knowledge from social science in order to create a dataset of question/answer (Q/As) pairs, based on the different popular and social cultures of various Latin American countries. We create the LatamQA database of over 26k questions and associated answers extracted from 26k Wikipedia articles, and transformed into multiple-choice questions (MCQ) in Spanish and Portuguese, in turn translated to English. We use this MCQ to quantify the degree of knowledge of various LLMs and find out (i) a discrepancy in performances between the Latam countries, ones being easier than others for the majority of the models, (ii) that the models perform better in their original language, and (iii) that Iberian Spanish culture is better known than Latam one. --- ### Beyond the Prompt in Large Language Models: Comprehension, In-Context Learning, and Chain-of-Thought Authors: Yuling Jiao, Yanming Lai, Huazhen Lin, Wensen Ma, Houduo Qi, Defeng Sun Published: 2026-02-16 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.10000v2 Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse tasks, exhibiting emergent properties such as semantic prompt comprehension, In-Context Learning (ICL), and Chain-of-Thought (CoT) reasoning. Despite their empirical success, the theoretical mechanisms driving these phenomena remain poorly understood. This study dives into the foundations of these observations by addressing three critical questions: (1) How do LLMs accurately decode prompt semantics despite being trained solely on a next-token prediction objective? (2) Through what mechanism does ICL facilitate performance gains without explicit parameter updates? and (3) Why do intermediate reasoning steps in CoT prompting effectively unlock capabilities for complex, multi-step problems? Our results demonstrate that, through the autoregressive process, LLMs are capable of exactly inferring the transition probabilities between tokens across distinct tasks using provided prompts. We show that ICL enhances performance by reducing prompt ambiguity and facilitating posterior concentration on the intended task. Furthermore, we find that CoT prompting activates the model's capacity for task decomposition, breaking complex problems into a sequence of simpler sub-tasks that the model has mastered during the pretraining phase. By comparing their individual error bounds, we provide novel theoretical insights into the statistical superiority of advanced prompt engineering techniques. --- ### A Retrieval-Augmented Language Assistant for Unmanned Aircraft Safety Assessment and Regulatory Compliance Authors: Gabriele Immordino, Andrea Vaiuso, Marcello Righi Published: 2026-02-16 Categories: cs.CL, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2603.09999v1 This paper presents the design and validation of a retrieval-based assistant that supports safety assessment, certification activities, and regulatory compliance for unmanned aircraft systems. The work is motivated by the growing complexity of drone operations and the increasing effort required by applicants and aviation authorities to apply established assessment frameworks, including the Specific Operations Risk Assessment and the Pre-defined Risk Assessment, in a consistent and efficient manner. The proposed approach uses a controlled text-based architecture that relies exclusively on authoritative regulatory sources. To enable traceable and auditable outputs, the assistant grounds each response in retrieved passages and enforces citation-driven generation. System-level controls address common failure modes of generative models, including fabricated statements, unsupported inferences, and unclear provenance, by separating evidence storage from language generation and by adopting conservative behavior when supporting documentation is insufficient. The assistant is intentionally limited to decision support; it does not replace expert judgment and it does not make autonomous determinations. Instead, it accelerates context-specific information retrieval and synthesis to improve document preparation and review while preserving human responsibility for critical conclusions. The architecture is implemented using established open-source components, and key choices in retrieval strategy, interaction constraints, and response policies are evaluated for suitability in safety-sensitive regulatory environments. The paper provides technical and operational guidance for integrating retrieval-based assistants into aviation oversight workflows while maintaining accountability, traceability, and regulatory compliance. --- ### Building the ethical AI framework of the future: from philosophy to practice Authors: Jasper Kyle Catapang Published: 2026-02-16 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2603.06599v1 Artificial intelligence pipelines -- spanning data collection, model training, deployment, and post-deployment monitoring -- concentrate ethical risks that intensify with multimodal and agentic systems. Existing governance instruments, including the EU AI Act, the IEEE 7000 series, and the NIST AI Risk Management Framework, provide high-level guidance but often lack enforceable, end-to-end operational controls. This paper presents an ethics-by-design control architecture that embeds consequentialist, deontological, and virtue-ethical reasoning into stage-specific enforcement mechanisms across the AI lifecycle. The framework implements a triple-gate structure at each lifecycle stage: Metric gates (quantitative performance and safety thresholds), Governance gates (legal, rights, and procedural compliance), and Eco gates (carbon and water budgets and sustainability constraints). It specifies measurable trigger conditions, escalation paths, audit artefacts, and mappings to EU AI Act obligations and NIST RMF functions, enabling integration with existing MLOps and CI/CD pipelines. Illustrative examples from large language model pipelines demonstrate how gate-based controls can surface and constrain technical, social, and environmental risks prior to release and during runtime. The framework is accompanied by a preregistered evaluation protocol that defines ex ante success criteria and assessment procedures, enabling falsifiable evaluation of gate effectiveness. By translating normative commitments into enforceable and testable controls, the framework provides a practical basis for operational AI governance across organizational contexts, jurisdictions, and deployment scales. --- ### Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection Authors: Hengshuai Yao, Xing Chen, Ahmed Murtadha, Guan Wang Published: 2026-02-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.04427v4 Standard Transformer attention uses identical dimensionality for queries, keys, and values, yet these components serve different roles: queries and keys produce scalar attention weights (selection), while values carry rich representations (value transfer). We show that selection requires only $O(\log N)$ dimensions to distinguish among $N$ relevant token categories (e.g., syntactic roles, semantic clusters, positional patterns) -- far fewer than value transfer needs. We introduce factored keys, which exploit this asymmetry to physically shrink the KV cache of any pretrained model without retraining from scratch -- unlike Grouped-Query Attention (GQA) and Multi-Head Latent Attention (MLA), which must be designed into the architecture before pretraining. We factorize each key projection $W_K \approx A_{d \times r} B_{r \times d}$ via truncated singular value decomposition (SVD) (where $r$ is the chosen compression dimension), set $W_K' = A$ as the new key projection producing compact $r$-dimensional keys for the cache, and absorb $B^\top$ into the query projection ($W_Q' = W_Q B^\top$) at zero cost -- since queries are never cached. At the 7B scale, training from scratch with $r = d/4$ (where $d$ is the model dimension) matches full-attention perplexity ($9.24$ vs $9.25$ PPL after 20B tokens, mean over two seeds) while using 12% fewer parameters and training 8% faster. For existing models, SVD followed by QK fine-tuning (3 epochs, less than 1% of pretraining data) achieves 75% key cache savings at roughly 2% quality cost on both GPT-2 and Mistral-7B. The approach composes with GQA and quantization for up to $16\times$ combined key cache compression. For a 7B model serving a 128K context, factored keys save 25 GB of KV cache per user, enabling roughly 60% more concurrent users on identical hardware. --- ### Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes Authors: Aly Kassem, Thomas Jiralerspong, Negar Rostamzadeh, Golnoosh Farnadi Published: 2026-02-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.04426v1 Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent directions between base and fine-tuned models. However, existing formulations struggle with narrow fine-tuning, where behavioral changes are localized and asymmetric. We introduce Delta-Crosscoder, which combines BatchTopK sparsity with a delta-based loss prioritizing directions that change between models, plus an implicit contrastive signal from paired activations on matched inputs. Evaluated across 10 model organisms, including synthetic false facts, emergent misalignment, subliminal learning, and taboo word guessing (Gemma, LLaMA, Qwen; 1B-9B parameters), Delta-Crosscoder reliably isolates latent directions causally responsible for fine-tuned behaviors and enables effective mitigation, outperforming SAE-based baselines, while matching the Non-SAE-based. Our results demonstrate that crosscoders remain a powerful tool for model diffing. --- ### Data-Driven Optimization of Multi-Generational Cellular Networks: A Performance Classification Framework for Strategic Infrastructure Management Authors: Maryam Sabahat, M. Umar Khan Published: 2026-02-16 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2603.04425v1 The exponential growth in mobile data demand necessitates intelligent management of telecommunications infrastructure to ensure Quality of Service (QoS) and operational efficiency. This paper presents a comprehensive analysis of a multigenerational cellular network dataset, sourced from the OpenCelliD project, to identify patterns in network deployment, utilization, and infrastructure gaps. The methodology involves geographical, temporal, and performance analysis of 1,818 cell tower entries, predominantly Long Term Evolution (LTE), across three countries with a significant concentration in Pakistan. Key findings reveal the long-term persistence of legacy 2G/3G infrastructure in major urban centers, the existence of a substantial number of under-utilized towers representing opportunities for cost savings, and the identification of specific "non-4G demand zones" where active user bases are served by outdated technologies. By introducing a signal-density metric, we distinguish between absolute over-utilization and localized congestion. The results provide actionable intelligence for Mobile Network Operators (MNOs) to guide strategic LTE upgrades, optimize resource allocation, and bridge the digital divide in underserved regions. --- ### When Scaling Fails: Network and Fabric Effects on Distributed GPU Training Performance Authors: Dinesh Gopalan, Ratul Ali Published: 2026-02-16 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2603.04424v1 Scaling distributed GPU training is commonly assumed to yield predictable performance gains as additional nodes are added. In practice, many large-scale deployments encounter diminishing returns and unstable behavior well before theoretical limits are reached. This paper examines why scaling fails in real systems, with a focus on the role of network and fabric effects that are often overlooked by higher-level training frameworks. We present an empirical study of distributed GPU training performance across multiple production-scale clusters. Our results show that network topology, congestion dynamics, collective synchronization behavior, and GPU locality frequently dominate end-to-end training performance once workloads move beyond a small number of nodes. Identical models and software stacks can exhibit sharply different scaling characteristics depending on fabric design and runtime communication patterns. We identify recurring failure modes that emerge as training transitions from single-node to multi-node execution, including synchronization amplification, topology-induced contention, and locality-driven performance variance. These effects are often invisible to standard profiling tools and are therefore misdiagnosed as framework or model-level inefficiencies. Based on these findings, we outline practical diagnostic principles that system builders can apply to understand scaling limits, improve predictability, and reduce the cost of large-scale distributed training. --- ### Generating Realistic, Protocol-Compliant Maritime Radio Dialogues using Self-Instruct and Low-Rank Adaptation Authors: Gürsel Akdeniz, Emin Cagatay Nakilcioglu Published: 2026-02-16 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.04423v1 VHF radio miscommunication remains a major safety risk in maritime operations, with human factors accounting for over 58% of recorded incidents in Europe between 2014 and 2023. Despite decades of operational use, VHF radio communications are still prone to noise, interference, linguistic variability, and the absence of real-time transcription, making procedural errors both frequent and difficult to correct. Developing AI-assisted systems to support real-time communication and decision-making requires a considerable amount of high-quality maritime data, yet operational, regulatory, and privacy constraints render such datasets scarce. This study introduces a compliance aware Self-Instruct methodology for generating realistic maritime radio dialogues that conform to the IMO's SMCP. Our approach integrates a 26-filter verification pipeline directly into the iterative generation loop to enforce entity information accuracy, hallucination detection, SMCP-compliance, logical consistency, and linguistic diversity. We employ LORA for parameter-efficient fine-tuning, reducing computational overhead during training and enabling efficient deployment of the resulting models on resource-constrained maritime systems. To assess dataset quality, we introduce a novel evaluation framework combining automated and expert assessments: Format Accuracy, Information Accuracy, Uniqueness, and Logical Coherence. Experiments using publicly available vessel, coastal and AIS datasets demonstrate that the approach produces synthetically diverse, procedurally compliant, and operationally realistic dialogues. Although downstream applications such as automatic speech recognition and natural language processing are reserved for future work, the released code, datasets, and verification tools provide a reproducible foundation for artificial intelligence-assisted maritime safety and other safety-critical domains. --- ### Engineering Reasoning and Instruction (ERI) Benchmark: A Large Taxonomy-driven Dataset for Foundation Models and Agents Authors: MZ Naser, Ahmad Bani Awwad, Zoie McCreery, Radwa Eissa, Ahmad Naser, Gianluca Cusatis, Andrew Metcalf, Kapil Madathil, Jamal Abdalla, Venkatesh Kodur, Mohammad Reza Saeb Published: 2026-02-16 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.02239v1 The Engineering Reasoning and Instruction (ERI) benchmark is a taxonomy-driven instruction dataset designed to train and evaluate engineering-capable large language models (LLMs) and agents. This dataset spans nine engineering fields (namely: civil, mechanical, electrical, chemical, environmental, aerospace, materials, fire, and industrial engineering) and 55 subdomains, and is crossed with seven intent types (i.e., definition, explanation, calculation, comparison, design/synthesis, troubleshooting, and code-related) and three difficulty tiers (undergraduate, graduate, and professional), yielding 57,750 records with field/subdomain/type/difficulty metadata and solution formatting. We examined ERI via seven LLMs and report a statistically significant three-tier performance structure, with frontier models (GPT-5, Claude Sonnet 4, DeepSeek V3.1) achieving mean scores above 4.30 on a five-point scale, while mid-tier and smaller models exhibited progressively higher failure rates and steeper performance degradation on graduate-level questions. To address circularity concerns inherent in LLM benchmarks, we developed a convergent validation protocol that leverages cross-provider independence, multi-judge averaging, and frontier-model agreement analysis to empirically bound hallucination risk to 1.7%. ERI is released with taxonomy specifications, validation scripts, and an evaluation harness to enable reproducible comparisons and regression testing for instruction tuning, routing, retrieval-augmented evaluation, and agentic tool-use workflows in engineering settings. --- ### High-Resolution Range Profile Classifiers Require Aspect-Angle Awareness Authors: Edwyn Brient, Santiago Velasco-Forero, Rami Kassab Published: 2026-02-16 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00087v2 We revisit High-Resolution Range Profile (HRRP) classification with aspect-angle conditioning. While prior work often assumes that aspect-angle information is incomplete during training or unavailable at inference, we study a setting where angles are available for all training samples and explicitly provided to the classifier. Using three datasets and a broad range of conditioning strategies and model architectures, we show that both single-profile and sequential classifiers benefit consistently from aspect-angle awareness, with an average accuracy gain of about 7% and improvements of up to 10%, depending on the model and dataset. In practice, aspect angles are not directly measured and must be estimated. We show that a causal Kalman filter can estimate them online with a median error of 5{\textdegree}, and that training and inference with estimated angles preserves most of the gains, supporting the proposed approach in realistic conditions. --- ### High-Resolution Range Profile Classifiers Require Aspect-Angle Awareness Authors: Edwyn Brient, Santiago Velasco-Forero, Rami Kassab Published: 2026-02-16 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.00087v1 We revisit High-Resolution Range Profile (HRRP) classification with aspect-angle conditioning. While prior work often assumes that aspect-angle information is incomplete during training or unavailable at inference, we study a setting where angles are available for all training samples and explicitly provided to the classifier. Using three datasets and a broad range of conditioning strategies and model architectures, we show that both single-profile and sequential classifiers benefit consistently from aspect-angle awareness, with an average accuracy gain of about 7% and improvements of up to 10%, depending on the model and dataset. In practice, aspect angles are not directly measured and must be estimated. We show that a causal Kalman filter can estimate them online with a median error of 5{\textdegree}, and that training and inference with estimated angles preserves most of the gains, supporting the proposed approach in realistic conditions. --- ### Iterative LLM-based improvement for French Clinical Interview Transcription and Speaker Diarization Authors: Ambre Marie, Thomas Bertin, Guillaume Dardenne, Gwenolé Quellec Published: 2026-02-16 Categories: cs.CL, cs.AI, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2603.00086v2 Automatic speech recognition for French medical conversations remains challenging, with word error rates often exceeding 30% in spontaneous clinical speech. This study proposes a multi-pass LLM post-processing architecture alternating between Speaker Recognition and Word Recognition passes to improve transcription accuracy and speaker attribution. Ablation studies on two French clinical datasets (suicide prevention telephone counseling and preoperative awake neurosurgery consultations) investigate four design choices: model selection, prompting strategy, pass ordering, and iteration depth. Using Qwen3-Next-80B, Wilcoxon signed-rank tests confirm significant WDER reductions on suicide prevention conversations (p<0.05, n=18), while maintaining stability on awake neurosurgery consultations (n=10), with zero output failures and acceptable computational cost (RTF 0.32), suggesting feasibility for offline clinical deployment, pending validation on larger corpora. --- ### Joint Sensor Deployment and Physics-Informed Graph Transformer for Smart Grid Attack Detection Authors: Mariam Elnour, Mohammad AlShaikh Saleh, Rachad Atat, Xiang Huo, Abdulrahman Takiddin, Muhammad Ismail, Hasan Kurban, Katherine R. Davis, Erchin Serpedin Published: 2026-02-16 Categories: cs.NE, cs.AI, eess.SY arXiv: https://arxiv.org/abs/2603.00085v1 This paper proposes a joint multi-objective optimization framework for strategic sensor placement in power systems to enhance attack detection. A novel physics-informed graph transformer network (PIGTN)-based detection model is proposed. Non-dominated sorting genetic algorithm-II (NSGA-II) jointly optimizes sensor locations and the PIGTN's detection performance, while considering practical constraints. The combinatorial space of feasible sensor placements is explored using NSGA-II, while concurrently training the proposed detector in a closed-loop setting. Compared to baseline sensor placement methods, the proposed framework consistently demonstrates robustness under sensor failures and improvements in detection performance in seven benchmark cases, including the 14, 30, IEEE-30, 39, 57, 118 and the 200 bus systems. By incorporating AC power flow constraints, the proposed PIGTN-based detection model generalizes well to unseen attacks and outperforms other graph network-based variants (topology-aware models), achieving improvements up to 37% in accuracy and 73% in detection rate, with a mean false alarms rate of 0.3%. In addition, optimized sensor layouts significantly improve the performance of power system state estimation, achieving a 61%--98% reduction in the average state error. --- ### Task-Lens: Cross-Task Utility Based Speech Dataset Profiling for Low-Resource Indian Languages Authors: Swati Sharma, Divya V. Sharma, Anubha Gupta Published: 2026-02-16 Categories: cs.CL, cs.AI, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2602.23388v1 The rising demand for inclusive speech technologies amplifies the need for multilingual datasets for Natural Language Processing (NLP) research. However, limited awareness of existing task-specific resources in low-resource languages hinders research. This challenge is especially acute in linguistically diverse countries, such as India. Cross-task profiling of existing Indian speech datasets can alleviate the data scarcity challenge. This involves investigating the utility of datasets across multiple downstream tasks rather than focusing on a single task. Prior surveys typically catalogue datasets for a single task, leaving comprehensive cross-task profiling as an open opportunity. Therefore, we propose Task-Lens, a cross-task survey that assesses the readiness of 50 Indian speech datasets spanning 26 languages for nine downstream speech tasks. First, we analyze which datasets contain metadata and properties suitable for specific tasks. Next, we propose task-aligned enhancements to unlock datasets to their full downstream potential. Finally, we identify tasks and Indian languages that are critically underserved by current resources. Our findings reveal that many Indian speech datasets contain untapped metadata that can support multiple downstream tasks. By uncovering cross-task linkages and gaps, Task-Lens enables researchers to explore the broader applicability of existing datasets and to prioritize dataset creation for underserved tasks and languages. --- ### Hello-Chat: Towards Realistic Social Audio Interactions Authors: Yueran Hou, Peilei Jia, Zihan Sun, Qihang Lu, Wenbing Yang, Yingming Gao, Ya Li, Jun Gao Published: 2026-02-16 Categories: cs.SD, cs.AI, cs.CL, eess.AS arXiv: https://arxiv.org/abs/2602.23387v1 Recent advancements in Large Audio Language Models (LALMs) have demonstrated exceptional performance in speech recognition and translation. However, existing models often suffer from a disconnect between perception and expression, resulting in a robotic "read-speech" style that lacks the spontaneity and emotional resonance of real human interaction. In this report, we introduce Hello-Chat, an end-to-end audio language model designed for realistic social scenarios. By leveraging a massive dataset of real-life conversations and employing a modality-interleaved training strategy, Hello-Chat achieves a breakthrough in anthropomorphic generation. Experimental results show that our model not only reaches state-of-the-art (SOTA) performance on specific audio understanding tasks but also significantly outperforms existing baselines in prosodic naturalness and emotional alignment, paving the way for the next generation of empathetic AI agents. --- ### Is Mamba Reliable for Medical Imaging? Authors: Banafsheh Saber Latibari, Najmeh Nazari, Daniel Brignac, Hossein Sayadi, Houman Homayoun, Abhijit Mahalanobis Published: 2026-02-16 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.16723v1 State-space models like Mamba offer linear-time sequence processing and low memory, making them attractive for medical imaging. However, their robustness under realistic software and hardware threat models remains underexplored. This paper evaluates Mamba on multiple MedM-NIST classification benchmarks under input-level attacks, including white-box adversarial perturbations (FGSM/PGD), occlusion-based PatchDrop, and common acquisition corruptions (Gaussian noise and defocus blur) as well as hardware-inspired fault attacks emulated in software via targeted and random bit-flip injections into weights and activations. We profile vulnerabilities and quantify impacts on accuracy indicating that defenses are needed for deployment. --- ### Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosis Authors: Pengfei Zhang, Tianxin Xie, Minghao Yang, Li Liu Published: 2026-02-16 Categories: eess.AS, cs.AI, cs.DB, cs.HC, cs.MA, cs.SD arXiv: https://arxiv.org/abs/2602.15909v3 Deep learning-based respiratory auscultation is currently hindered by two fundamental challenges: (i) inherent information loss, as converting signals into spectrograms discards transient acoustic events and clinical context; (ii) limited data availability, exacerbated by severe class imbalance. To bridge these gaps, we present Resp-Agent, an autonomous multimodal system orchestrated by a novel Active Adversarial Curriculum Agent (Thinker-A$^2$CA). Unlike static pipelines, Thinker-A$^2$CA serves as a central controller that actively identifies diagnostic weaknesses and schedules targeted synthesis in a closed loop. To address the representation gap, we introduce a modality-weaving Diagnoser that weaves clinical text with audio tokens via strategic global attention and sparse audio anchors, capturing both long-range clinical context and millisecond-level transients. To address the data gap, we design a flow matching Generator that adapts a text-only Large Language Model (LLM) via modality injection, decoupling pathological content from acoustic style to synthesize hard-to-diagnose samples. As a foundation for this work, we introduce Resp-229k, a benchmark corpus of 229k recordings paired with LLM-distilled clinical narratives. Extensive experiments demonstrate that Resp-Agent consistently outperforms prior approaches across diverse evaluation settings, improving diagnostic robustness under data scarcity and long-tailed class imbalance. Our code and data are available at https://github.com/zpforlove/Resp-Agent. --- ### From Diagnosis to Inoculation: Building Cognitive Resistance to AI Disempowerment Authors: Aleksey Komissarov Published: 2026-02-16 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.15265v1 Recent empirical research by Sharma et al. (2026) demonstrated that AI assistant interactions carry meaningful potential for situational human disempowerment, including reality distortion, value judgment distortion, and action distortion. While this work provides a critical diagnosis of the problem, concrete pedagogical interventions remain underexplored. I present an AI literacy framework built around eight cross-cutting Learning Outcomes (LOs), developed independently through teaching practice and subsequently found to align with Sharma et al.'s disempowerment taxonomy. I report a case study from a publicly available online course, where a co-teaching methodology--with AI serving as an active voice co-instructor--was used to deliver this framework. Drawing on inoculation theory (McGuire, 1961)--a well-established persuasion research framework recently applied to misinformation prebunking by the Cambridge school (van der Linden, 2022; Roozenbeek & van der Linden, 2019)--I argue that AI literacy cannot be acquired through declarative knowledge alone, but requires guided exposure to AI failure modes, including the sycophantic validation and authority projection patterns identified by Sharma et al. This application of inoculation theory to AI-specific distortion is, to my knowledge, novel. I discuss the convergence between the pedagogically-derived framework and Sharma et al.'s empirically-derived taxonomy, and argue that this convergence--two independent approaches arriving at similar problem descriptions--strengthens the case for both the diagnosis and the proposed educational response. --- ### Fast and Effective On-policy Distillation from Reasoning Prefixes Authors: Dongxu Zhang, Zhichao Yang, Sepehr Janghorbani, Jun Han, Andrew Ressler, Qian Qian, Gregory D. Lyng, Sanjit Singh Batra, Robert E. Tillman Published: 2026-02-16 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.15260v1 On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, avoids relying solely on verifiable terminal rewards and can yield better generalization than off-policy distillation. However, OPD requires expensive on-the-fly sampling of the student policy during training, which substantially increases training cost, especially for long responses. Our initial analysis shows that, during OPD, training signals are often concentrated in the prefix of each output, and that even a short teacher-generated prefix can significantly help the student produce the correct answer. Motivated by these observations, we propose a simple yet effective modification of OPD: we apply the distillation objective only to prefixes of student-generated outputs and terminate each sampling early during distillation. Experiments on a suite of AI-for-Math and out-of-domain benchmarks show that on-policy prefix distillation matches the performance of full OPD while reducing training FLOP by 2x-47x. ---