# Research Papers — 2026-02 · bundle page 58 of 210 > Full-text markdown of papers #2851–2900 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/58 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/57.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/59.md) ### Stable Long-Horizon Spatiotemporal Prediction on Meshes Using Latent Multiscale Recurrent Graph Neural Networks Authors: Lionel Salesses, Larbi Arbaoui, Tariq Benamara, Arnaud Francois, Caroline Sainvitu Published: 2026-02-20 Categories: cs.LG, cond-mat.mtrl-sci, physics.app-ph arXiv: https://arxiv.org/abs/2602.18146v1 Accurate long-horizon prediction of spatiotemporal fields on complex geometries is a fundamental challenge in scientific machine learning, with applications such as additive manufacturing where temperature histories govern defect formation and mechanical properties. High-fidelity simulations are accurate but computationally costly, and despite recent advances, machine learning methods remain challenged by long-horizon temperature and gradient prediction. We propose a deep learning framework for predicting full temperature histories directly on meshes, conditioned on geometry and process parameters, while maintaining stability over thousands of time steps and generalizing across heterogeneous geometries. The framework adopts a temporal multiscale architecture composed of two coupled models operating at complementary time scales. Both models rely on a latent recurrent graph neural network to capture spatiotemporal dynamics on meshes, while a variational graph autoencoder provides a compact latent representation that reduces memory usage and improves training stability. Experiments on simulated powder bed fusion data demonstrate accurate and temporally stable long-horizon predictions across diverse geometries, outperforming existing baseline. Although evaluated in two dimensions, the framework is general and extensible to physics-driven systems with multiscale dynamics and to three-dimensional geometries. --- ### Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention Authors: Siya Qi, Yudong Chen, Runcong Zhao, Qinglin Zhu, Zhanghao Hu, Wei Liu, Yulan He, Zheng Yuan, Lin Gui Published: 2026-02-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.18145v1 Hallucination detection is critical for ensuring the reliability of large language models (LLMs) in context-based generation. Prior work has explored intrinsic signals available during generation, among which attention offers a direct view of grounding behavior. However, existing approaches typically rely on coarse summaries that fail to capture fine-grained instabilities in attention. Inspired by signal processing, we introduce a frequency-aware perspective on attention by analyzing its variation during generation. We model attention distributions as discrete signals and extract high-frequency components that reflect rapid local changes in attention. Our analysis reveals that hallucinated tokens are associated with high-frequency attention energy, reflecting fragmented and unstable grounding behavior. Based on this insight, we develop a lightweight hallucination detector using high-frequency attention features. Experiments on the RAGTruth and HalluRAG benchmarks show that our approach achieves performance gains over verification-based, internal-representation-based, and attention-based methods across models and tasks. --- ### Geometry-Induced Diffusion on Graphs: A Learnable Weighted Laplacian for Spectral GNNs Authors: Mia Zosso, Ali Hariri, Victor Kawasaki-Borruat, Pierre-Gabriel Berlureau, Pierre Vandergheynst Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18141v2 Long-range graph tasks are challenging for Graph Neural Networks (GNNs): global mechanisms such as attention or rewiring schemes can be computationally expensive, while deep local propagation is prone to vanishing gradients, oversmoothing, and oversquashing. The introduced mu-ChebNet architecture is a simple spectral GNN that learns a node-wise weight function mu before applying ChebNet-style filters. The learned weighting mu induces a modified graph Laplacian which effectively changes the propagation geometry without altering the graph topology. This task-dependent geometry promotes preferred routes for information propagation, thereby helping long-range signals avoid highly contractive bottlenecks, and obviating the need for repeated layer stacking. In practice, we replace the fixed graph Laplacian L by a learned operator L_mu, keeping the proposed mu-ChebNet architecture lightweight while making propagation task-adaptive. Furthermore, we provide a spectral analysis demonstrating how mu modulates propagation dynamics, and empirically observe improved performance on both synthetic long-range reasoning tasks and real-world graph benchmarks. The learned weight function is not only interpretable, but also offers a lightweight alternative to attention and rewiring for adaptive graph propagation. --- ### Flexi-NeurA: A Flexible Neuromorphic Accelerator with Adaptive Bit-Precision Exploration for Edge Devices Authors: Mohammad Farahani, Mohammad Rasoul Roshanshah, Saeed Safari Published: 2026-02-20 Categories: cs.AR, cs.NE arXiv: https://arxiv.org/abs/2602.18140v2 Neuromorphic accelerators promise unparalleled energy efficiency and computational density for spiking neural networks, especially in wearable biomedical devices and neural prosthetics where power constraints are stringent. However, most existing platforms exhibit rigid architectures with limited configurability, restricting their adaptability to heterogeneous biological signals and diverse design objectives. To address these limitations, we present Flexi-NeurA--a flexible neuromorphic accelerator that unifies configurability and efficiency. Flexi-NeurA allows users to customize neuron models, network structures, and precision settings at design time. By pairing these design-time configurability features with a time-multiplexed and event-driven processing approach, Flexi-NeurA reduces the required hardware resources and total power while preserving high efficiency and low inference latency. Complementing this, we introduce Flex-plorer, a design-space exploration tool that determines cost-effective fixed-point precisions for critical parameters--such as decay factors, synaptic weights, and membrane potentials--based on user-defined trade-offs between accuracy and resource usage. Based on the configuration selected through the Flex-plorer process, RTL code is configured to match the specified design. Comprehensive evaluations across distinct domains--biomedical auditory processing, dynamic vision sensor gesture recognition, and standard vision classification--demonstrate that the hardware/software co-framework successfully balances accuracy and power budgets for diverse applications. A 3-layer 256-128-10 fully connected network with LIF neurons mapped onto two processing cores achieves 96.23% accuracy on MNIST with 1.1 ms inference latency, utilizing only 1,623 logic cells, 7 BRAMs, and 111 mW of total power--demonstrating superior resource efficiency compared to SoTA hardware baselines. --- ### Agentic Adversarial QA for Improving Domain-Specific LLMs Authors: Vincent Grari, Ciprian Tomoiaga, Sylvain Lamprier, Tatsunori Hashimoto, Marcin Detyniecki Published: 2026-02-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18137v1 Large Language Models (LLMs), despite extensive pretraining on broad internet corpora, often struggle to adapt effectively to specialized domains. There is growing interest in fine-tuning these models for such domains; however, progress is constrained by the scarcity and limited coverage of high-quality, task-relevant data. To address this, synthetic data generation methods such as paraphrasing or knowledge extraction are commonly applied. Although these approaches excel at factual recall and conceptual knowledge, they suffer from two critical shortcomings: (i) they provide minimal support for interpretive reasoning capabilities in these specialized domains, and (ii) they often produce synthetic corpora that are excessively large and redundant, resulting in poor sample efficiency. To overcome these gaps, we propose an adversarial question-generation framework that produces a compact set of semantically challenging questions. These questions are constructed by comparing the outputs of the model to be adapted and a robust expert model grounded in reference documents, using an iterative, feedback-driven process designed to reveal and address comprehension gaps. Evaluation on specialized subsets of the LegalBench corpus demonstrates that our method achieves greater accuracy with substantially fewer synthetic samples. --- ### Learning Long-Range Dependencies with Temporal Predictive Coding Authors: Tom Potter, Oliver Rhodes Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18131v2 Temporal Predictive Coding provides a layer-local, parallelisable mechanism for learning in recurrent systems, making it an attractive candidate for online local learning on neuromorphic and edge hardware. However, its recurrent parameter update captures only local temporal relationships, neglecting the historic influence of parameters along the latent-state trajectory, and therefore struggles to assign credit over longer temporal horizons. This work combines for the first time Temporal Predictive Coding with Real-Time Recurrent Learning (tPC-RTRL), incorporating an online influence matrix that tracks this historic effect whilst preserving the spatial and temporal locality properties valued by neuromorphic implementations. Under explicit assumptions, we prove that tPC-RTRL recovers the gradients of backpropagation-through-time exactly. Empirically, a near-equivalence holds across several tasks of varying scale and complexity, including byte-level language modelling on WikiText-103 (tPC-RTRL vs. BPTT: 1.865 vs. 1.864 validation BPC), English--French translation on a CCMatrix subset (20.23 vs. 20.29 BLEU), and a realistic nanodrone system-identification benchmark (0.506m vs. 0.505m mean position error). Finally, we show that the iterative inference mechanism used during training can be reused at deployment time to incorporate intermittent state observations, halving final-position error relative to open-loop rollout on the nanodrone task (0.402m vs. 0.805m) and suggesting a path towards unifying learning and filtering within the same computational framework. --- ### RamanSeg: Interpretability-driven Deep Learning on Raman Spectra for Cancer Diagnosis Authors: Chris Tomy, Mo Vali, David Pertzborn, Tammam Alamatouri, Anna Mühlig, Orlando Guntinas-Lichius, Anna Xylander, Eric Michele Fantuzzi, Matteo Negro, Francesco Crisafi, Pietro Lio, Tiago Azevedo Published: 2026-02-20 Categories: eess.IV, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.18119v1 Histopathology, the current gold standard for cancer diagnosis, involves the manual examination of tissue samples after chemical staining, a time-consuming process requiring expert analysis. Raman spectroscopy is an alternative, stain-free method of extracting information from samples. Using nnU-Net, we trained a segmentation model on a novel dataset of spatial Raman spectra aligned with tumour annotations, achieving a mean foreground Dice score of 80.9%, surpassing previous work. Furthermore, we propose a novel, interpretable, prototype-based architecture called RamanSeg. RamanSeg classifies pixels based on discovered regions of the training set, generating a segmentation mask. Two variants of RamanSeg allow a trade-off between interpretability and performance: one with prototype projection and another projection-free version. The projection-free RamanSeg outperformed a U-Net baseline with a mean foreground Dice score of 67.3%, offering a meaningful improvement over a black-box training approach. --- ### Flow Matching with Injected Noise for Offline-to-Online Reinforcement Learning Authors: Yongjae Shin, Jongseong Chae, Jongeui Park, Youngchul Sung Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.18117v1 Generative models have recently demonstrated remarkable success across diverse domains, motivating their adoption as expressive policies in reinforcement learning (RL). While they have shown strong performance in offline RL, particularly where the target distribution is well defined, their extension to online fine-tuning has largely been treated as a direct continuation of offline pre-training, leaving key challenges unaddressed. In this paper, we propose Flow Matching with Injected Noise for Offline-to-Online RL (FINO), a novel method that leverages flow matching-based policies to enhance sample efficiency for offline-to-online RL. FINO facilitates effective exploration by injecting noise into policy training, thereby encouraging a broader range of actions beyond those observed in the offline dataset. In addition to exploration-enhanced flow policy training, we combine an entropy-guided sampling mechanism to balance exploration and exploitation, allowing the policy to adapt its behavior throughout online fine-tuning. Experiments across diverse, challenging tasks demonstrate that FINO consistently achieves superior performance under limited online budgets. --- ### Cut Less, Fold More: Model Compression through the Lens of Projection Geometry Authors: Olga Saukh, Dong Wang, Haris Šikić, Yun Cheng, Lothar Thiele Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.18116v1 Compressing neural networks without retraining is vital for deployment at scale. We study calibration-free compression through the lens of projection geometry: structured pruning is an axis-aligned projection, whereas model folding performs a low-rank projection via weight clustering. We formalize both as orthogonal operators and show that, within a rank distance of one, folding provably yields smaller parameter reconstruction error, and under mild smoothness assumptions, smaller functional perturbations than pruning. At scale, we evaluate >1000 checkpoints spanning ResNet18, PreActResNet18, ViT-B/32, and CLIP ViT-B/32 on CIFAR-10 and ImageNet-1K, covering diverse training hyperparameters (optimizers, learning rates, augmentations, regularization, sharpness-aware training), as well as multiple LLaMA-family 60M and 130M parameter models trained on C4. We show that folding typically achieves higher post-compression accuracy, with the largest gains at moderate-high compression. The gap narrows and occasionally reverses at specific training setups. Our results position folding as a geometry-aware, calibration-free alternative to pruning that is often superior in practice and principled in theory. --- ### Non-Stationary Online Resource Allocation: Learning from a Single Sample Authors: Yiding Feng, Jiashuo Jiang, Yige Wang Published: 2026-02-20 Categories: cs.LG, cs.DS, math.OC arXiv: https://arxiv.org/abs/2602.18114v1 We study online resource allocation under non-stationary demand with a minimum offline data requirement. In this problem, a decision-maker must allocate multiple types of resources to sequentially arriving queries over a finite horizon. Each query belongs to a finite set of types with fixed resource consumption and a stochastic reward drawn from an unknown, type-specific distribution. Critically, the environment exhibits arbitrary non-stationarity -- arrival distributions may shift unpredictably-while the algorithm requires only one historical sample per period to operate effectively. We distinguish two settings based on sample informativeness: (i) reward-observed samples containing both query type and reward realization, and (ii) the more challenging type-only samples revealing only query type information. We propose a novel type-dependent quantile-based meta-policy that decouples the problem into modular components: reward distribution estimation, optimization of target service probabilities via fluid relaxation, and real-time decisions through dynamic acceptance thresholds. For reward-observed samples, our static threshold policy achieves $\tilde{O}(\sqrt{T})$ regret. For type-only samples, we first establish that sublinear regret is impossible without additional structure; under a mild minimum-arrival-probability assumption, we design both a partially adaptive policy attaining the same $\tilde{O}({T})$ bound and, more significantly, a fully adaptive resolving policy with careful rounding that achieves the first poly-logarithmic regret guarantee of $O((\log T)^3)$ for non-stationary multi-resource allocation. Our framework advances prior work by operating with minimal offline data (one sample per period), handling arbitrary non-stationarity without variation-budget assumptions, and supporting multiple resource constraints. --- ### TempoNet: Slack-Quantized Transformer-Guided Reinforcement Scheduler for Adaptive Deadline-Centric Real-Time Dispatchs Authors: Rong Fu, Yibo Meng, Zeyu Zhang, Ziming Guo, Jia Yee Tan, Xiaojing Du, Simon James Fong Published: 2026-02-20 Categories: cs.LG, cs.OS, eess.SY arXiv: https://arxiv.org/abs/2602.18109v4 Real-time schedulers must reason about tight deadlines under strict compute budgets. We present TempoNet, a reinforcement learning scheduler that pairs a permutation-invariant Transformer with a deep Q-approximation. An Urgency Tokenizer discretizes temporal slack into learnable embeddings, stabilizing value learning and capturing deadline proximity. A latency-aware sparse attention stack with blockwise top-k selection and locality-sensitive chunking enables global reasoning over unordered task sets with near-linear scaling and sub-millisecond inference. A multicore mapping layer converts contextualized Q-scores into processor assignments through masked-greedy selection or differentiable matching. Extensive evaluations on industrial mixed-criticality traces and large multiprocessor settings show consistent gains in deadline fulfillment over analytic schedulers and neural baselines, together with improved optimization stability. Diagnostics include sensitivity analyses for slack quantization, attention-driven policy interpretation, hardware-in-the-loop and kernel micro-benchmarks, and robustness under stress with simple runtime mitigations; we also report sample-efficiency benefits from behavioral-cloning pretraining and compatibility with an actor-critic variant without altering the inference pipeline. These results establish a practical framework for Transformer-based decision making in high-throughput real-time scheduling. --- ### MeanVoiceFlow: One-step Nonparallel Voice Conversion with Mean Flows Authors: Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo Published: 2026-02-20 Categories: cs.SD, cs.AI, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2602.18104v1 In voice conversion (VC) applications, diffusion and flow-matching models have exhibited exceptional speech quality and speaker similarity performances. However, they are limited by slow conversion owing to their iterative inference. Consequently, we propose MeanVoiceFlow, a novel one-step nonparallel VC model based on mean flows, which can be trained from scratch without requiring pretraining or distillation. Unlike conventional flow matching that uses instantaneous velocity, mean flows employ average velocity to more accurately compute the time integral along the inference path in a single step. However, training the average velocity requires its derivative to compute the target velocity, which can cause instability. Therefore, we introduce a structural margin reconstruction loss as a zero-input constraint, which moderately regularizes the input-output behavior of the model without harmful statistical averaging. Furthermore, we propose conditional diffused-input training in which a mixture of noise and source data is used as input to the model during both training and inference. This enables the model to effectively leverage source information while maintaining consistency between training and inference. Experimental results validate the effectiveness of these techniques and demonstrate that MeanVoiceFlow achieves performance comparable to that of previous multi-step and distillation-based models, even when trained from scratch. Audio samples are available at https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/meanvoiceflow/. --- ### Interacting safely with cyclists using Hamilton-Jacobi reachability and reinforcement learning Authors: Aarati Andrea Noronha, Jean Oh Published: 2026-02-20 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.18097v1 In this paper, we present a framework for enabling autonomous vehicles to interact with cyclists in a manner that balances safety and optimality. The approach integrates Hamilton-Jacobi reachability analysis with deep Q-learning to jointly address safety guarantees and time-efficient navigation. A value function is computed as the solution to a time-dependent Hamilton-Jacobi-Bellman inequality, providing a quantitative measure of safety for each system state. This safety metric is incorporated as a structured reward signal within a reinforcement learning framework. The method further models the cyclist's latent response to the vehicle, allowing disturbance inputs to reflect human comfort and behavioral adaptation. The proposed framework is evaluated through simulation and comparison with human driving behavior and an existing state-of-the-art method. --- ### Neurosymbolic Language Reasoning as Satisfiability Modulo Theory Authors: Hyunseok Oh, Sam Stern, Youngki Lee, Matthai Philipose Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.18095v1 Natural language understanding requires interleaving textual and logical reasoning, yet large language models often fail to perform such reasoning reliably. Existing neurosymbolic systems combine LLMs with solvers but remain limited to fully formalizable tasks such as math or program synthesis, leaving natural documents with only partial logical structure unaddressed. We introduce Logitext, a neurosymbolic language that represents documents as natural language text constraints (NLTCs), making partial logical structure explicit. We develop an algorithm that integrates LLM-based constraint evaluation with satisfiability modulo theory (SMT) solving, enabling joint textual-logical reasoning. Experiments on a new content moderation benchmark, together with LegalBench and Super-Natural Instructions, show that Logitext improves both accuracy and coverage. This work is the first that treats LLM-based reasoning as an SMT theory, extending neurosymbolic methods beyond fully formalizable domains. --- ### OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models Authors: Ling Lin, Yang Bai, Heng Su, Congcong Zhu, Yaoxing Wang, Yang Zhou, Huazhu Fu, Jingrun Chen Published: 2026-02-20 Categories: cs.CV, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2602.18094v2 Existing Visual-Language Models (VLMs) have achieved significant progress by being trained on massive-scale datasets, typically under the assumption that data are independent and identically distributed (IID). However, in real-world scenarios, it is often impractical to expect that all data processed by an AI system satisfy this assumption. Furthermore, failure to appropriately handle out-of-distribution (OOD) objects may introduce safety risks in real-world applications (e.g., autonomous driving or medical assistance). Unfortunately, current research has not yet provided valid benchmarks that can comprehensively assess the performance of VLMs in response to OOD data. Therefore, we propose OODBench, a predominantly automated method with minimal human verification, for constructing new benchmarks and evaluating the ability of VLMs to process OOD data. OODBench contains 40K instance-level OOD instance-category pairs, and we show that current VLMs still exhibit notable performance degradation on OODBench, even when the underlying image categories are common. In addition, we propose a reliable automated assessment metric that employs a Basic-to-Advanced Progression of prompted questions to assess the impact of OOD data on questions of varying difficulty more fully. Lastly, we summarize substantial findings and insights to facilitate future research in the acquisition and evaluation of OOD data. --- ### OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models Authors: Ling Lin, Yang Bai, Heng Su, Congcong Zhu, Yaoxing Wang, Yang Zhou, Huazhu Fu, Jingrun Chen Published: 2026-02-20 Categories: cs.CV, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2602.18094v1 Existing Visual-Language Models (VLMs) have achieved significant progress by being trained on massive-scale datasets, typically under the assumption that data are independent and identically distributed (IID). However, in real-world scenarios, it is often impractical to expect that all data processed by an AI system satisfy this assumption. Furthermore, failure to appropriately handle out-of-distribution (OOD) objects may introduce safety risks in real-world applications (e.g., autonomous driving or medical assistance). Unfortunately, current research has not yet provided valid benchmarks that can comprehensively assess the performance of VLMs in response to OOD data. Therefore, we propose OODBench, a predominantly automated method with minimal human verification, for constructing new benchmarks and evaluating the ability of VLMs to process OOD data. OODBench contains 40K instance-level OOD instance-category pairs, and we show that current VLMs still exhibit notable performance degradation on OODBench, even when the underlying image categories are common. In addition, we propose a reliable automated assessment metric that employs a Basic-to-Advanced Progression of prompted questions to assess the impact of OOD data on questions of varying difficulty more fully. Lastly, we summarize substantial findings and insights to facilitate future research in the acquisition and evaluation of OOD data. --- ### Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers Authors: Hanshuai Cui, Zhiqing Tang, Qianli Ma, Zhi Yao, Weijia Jia, Wei Zhao Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18093v2 Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on feature caching and reuse under the assumption of temporal stability. However, reusing features for multiple steps may lead to latent drift and visual degradation. We observe that model outputs evolve smoothly along much of the diffusion trajectory, enabling principled predictions rather than naive reuse. Based on this insight, we propose \textbf{PrediT}, a training-free acceleration framework that formulates feature prediction as a linear multistep problem. We employ classical linear multistep methods to forecast future model outputs from historical information, combined with a corrector that activates in high-dynamics regions to prevent error accumulation. A dynamic step modulation mechanism adaptively adjusts the prediction horizon by monitoring the feature change rate. Together, these components enable substantial acceleration while preserving generation fidelity. Extensive experiments validate that our method achieves up to $5.54\times$ latency reduction across various DiT-based image and video generation models, while incurring negligible quality degradation. --- ### Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers Authors: Hanshuai Cui, Zhiqing Tang, Qianli Ma, Zhi Yao, Weijia Jia Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18093v1 Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on feature caching and reuse under the assumption of temporal stability. However, reusing features for multiple steps may lead to latent drift and visual degradation. We observe that model outputs evolve smoothly along much of the diffusion trajectory, enabling principled predictions rather than naive reuse. Based on this insight, we propose \textbf{PrediT}, a training-free acceleration framework that formulates feature prediction as a linear multistep problem. We employ classical linear multistep methods to forecast future model outputs from historical information, combined with a corrector that activates in high-dynamics regions to prevent error accumulation. A dynamic step modulation mechanism adaptively adjusts the prediction horizon by monitoring the feature change rate. Together, these components enable substantial acceleration while preserving generation fidelity. Extensive experiments validate that our method achieves up to $5.54\times$ latency reduction across various DiT-based image and video generation models, while incurring negligible quality degradation. --- ### Perceived Political Bias in LLMs Reduces Persuasive Abilities Authors: Matthew DiGiuseppe, Joshua Robison Published: 2026-02-20 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2602.18092v1 Conversational AI has been proposed as a scalable way to correct public misconceptions and spread misinformation. Yet its effectiveness may depend on perceptions of its political neutrality. As LLMs enter partisan conflict, elites increasingly portray them as ideologically aligned. We test whether these credibility attacks reduce LLM-based persuasion. In a preregistered U.S. survey experiment (N=2144), participants completed a three-round conversation with ChatGPT about a personally held economic policy misconception. Compared to a neutral control, a short message indicating that the LLM was biased against the respondent's party attenuated persuasion by 28%. Transcript analysis indicates that the warnings alter the interaction: respondents push back more and engage less receptively. These findings suggest that the persuasive impact of conversational AI is politically contingent, constrained by perceptions of partisan alignment. --- ### DohaScript: A Large-Scale Multi-Writer Dataset for Continuous Handwritten Hindi Text Authors: Kunwar Arpit Singh, Ankush Prakash, Haroon R Lone Published: 2026-02-20 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18089v1 Despite having hundreds of millions of speakers, handwritten Devanagari text remains severely underrepresented in publicly available benchmark datasets. Existing resources are limited in scale, focus primarily on isolated characters or short words, and lack controlled lexical content and writer level diversity, which restricts their utility for modern data driven handwriting analysis. As a result, they fail to capture the continuous, fused, and structurally complex nature of Devanagari handwriting, where characters are connected through a shared shirorekha (horizontal headline) and exhibit rich ligature formations. We introduce DohaScript, a large scale, multi writer dataset of handwritten Hindi text collected from 531 unique contributors. The dataset is designed as a parallel stylistic corpus, in which all writers transcribe the same fixed set of six traditional Hindi dohas (couplets). This controlled design enables systematic analysis of writer specific variation independent of linguistic content, and supports tasks such as handwriting recognition, writer identification, style analysis, and generative modeling. The dataset is accompanied by non identifiable demographic metadata, rigorous quality curation based on objective sharpness and resolution criteria, and page level layout difficulty annotations that facilitate stratified benchmarking. Baseline experiments demonstrate clear quality separation and strong generalization to unseen writers, highlighting the dataset's reliability and practical value. DohaScript is intended to serve as a standardized and reproducible benchmark for advancing research on continuous handwritten Devanagari text in low resource script settings. --- ### Balancing Symmetry and Efficiency in Graph Flow Matching Authors: Benjamin Honoré, Alba Carballo-Castro, Yiming Qin, Pascal Frossard Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18084v2 Equivariance is central to graph generative models, as it ensures the model respects the permutation symmetry of graphs. However, strict equivariance can increase computational cost due to added architectural constraints, and can slow down convergence because the model must be consistent across a large space of possible node permutations. We study this trade-off for graph generative models. Specifically, we start from an equivariant discrete flow-matching model, and relax its equivariance during training via a controllable symmetry modulation scheme based on sinusoidal positional encodings and node permutations. Experiments first show that symmetry-breaking can accelerate early training by providing an easier learning signal, but at the expense of encouraging shortcut solutions that can cause overfitting, where the model repeatedly generates graphs that are duplicates of the training set. On the contrary, properly modulating the symmetry signal can delay overfitting while accelerating convergence, allowing the model to reach stronger performance with $19\%$ of the baseline training epochs. --- ### Comparative Assessment of Multimodal Earth Observation Data for Soil Moisture Estimation Authors: Ioannis Kontogiorgakis, Athanasios Askitopoulos, Iason Tsardanidis, Dimitrios Bormpoudakis, Ilias Tsoumas, Fotios Balampanis, Charalampos Kontoes Published: 2026-02-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.18083v1 Accurate soil moisture (SM) estimation is critical for precision agriculture, water resources management and climate monitoring. Yet, existing satellite SM products are too coarse (>1km) for farm-level applications. We present a high-resolution (10m) SM estimation framework for vegetated areas across Europe, combining Sentinel-1 SAR, Sentinel-2 optical imagery and ERA-5 reanalysis data through machine learning. Using 113 International Soil Moisture Network (ISMN) stations spanning diverse vegetated areas, we compare modality combinations with temporal parameterizations, using spatial cross-validation, to ensure geographic generalization. We also evaluate whether foundation model embeddings from IBM-NASA's Prithvi model improve upon traditional hand-crafted spectral features. Results demonstrate that hybrid temporal matching - Sentinel-2 current-day acquisitions with Sentinel-1 descending orbit - achieves R^2=0.514, with 10-day ERA5 lookback window improving performance to R^2=0.518. Foundation model (Prithvi) embeddings provide negligible improvement over hand-crafted features (R^2=0.515 vs. 0.514), indicating traditional feature engineering remains highly competitive for sparse-data regression tasks. Our findings suggest that domain-specific spectral indices combined with tree-based ensemble methods offer a practical and computationally efficient solution for operational pan-European field-scale soil moisture monitoring. --- ### HiAER-Spike Software-Hardware Reconfigurable Platform for Event-Driven Neuromorphic Computing at Scale Authors: Gwenevere Frank, Gopabandhu Hota, Keli Wang, Christopher Deng, Krish Arora, Diana Vins, Abhinav Uppal, Omowuyi Olajide, Kenneth Yoshimoto, Qingbo Wang, Mari Yamaoka, Johannes Leugering et al. Published: 2026-02-20 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2602.18072v1 In this work, we present HiAER-Spike, a modular, reconfigurable, event-driven neuromorphic computing platform designed to execute large spiking neural networks with up to 160 million neurons and 40 billion synapses - roughly twice the neurons of a mouse brain at faster than real time. This system, assembled at the UC San Diego Supercomputer Center, comprises a co-designed hard- and software stack that is optimized for run-time massively parallel processing and hierarchical address-event routing (HiAER) of spikes while promoting memory-efficient network storage and execution. The architecture efficiently handles both sparse connectivity and sparse activity for robust and low-latency event-driven inference for both edge and cloud computing. A Python programming interface to HiAER-Spike, agnostic to hardware-level detail, shields the user from complexity in the configuration and execution of general spiking neural networks with minimal constraints in topology. The system is made easily available over a web portal for use by the wider community. In the following, we provide an overview of the hard- and software stack, explain the underlying design principles, demonstrate some of the system's capabilities and solicit feedback from the broader neuromorphic community. Examples are shown demonstrating HiAER-Spike's capabilities for event-driven vision on benchmark CIFAR-10, DVS event-based gesture, MNIST, and Pong tasks. --- ### Faster Training, Fewer Labels: Self-Supervised Pretraining for Fine-Grained BEV Segmentation Authors: Daniel Busch, Christian Bohn, Thomas Kurbiel, Klaus Friedrichs, Richard Meyes, Tobias Meisen Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18066v1 Dense Bird's Eye View (BEV) semantic maps are central to autonomous driving, yet current multi-camera methods depend on costly, inconsistently annotated BEV ground truth. We address this limitation with a two-phase training strategy for fine-grained road marking segmentation that removes full supervision during pretraining and halves the amount of training data during fine-tuning while still outperforming the comparable supervised baseline model. During the self-supervised pretraining, BEVFormer predictions are differentiably reprojected into the image plane and trained against multi-view semantic pseudo-labels generated by the widely used semantic segmentation model Mask2Former. A temporal loss encourages consistency across frames. The subsequent supervised fine-tuning phase requires only 50% of the dataset and significantly less training time. With our method, the fine-tuning benefits from rich priors learned during pretraining boosting the performance and BEV segmentation quality (up to +2.5pp mIoU over the fully supervised baseline) on nuScenes. It simultaneously halves the usage of annotation data and reduces total training time by up to two thirds. The results demonstrate that differentiable reprojection plus camera perspective pseudo labels yields transferable BEV features and a scalable path toward reduced-label autonomous perception. --- ### 3DMedAgent: Unified Perception-to-Understanding for 3D Medical Analysis Authors: Ziyue Wang, Linghan Cai, Chang Han Low, Haofeng Liu, Junde Wu, Jingyu Wang, Rui Wang, Lei Song, Jiang Bian, Jingjing Fu, Yueming Jin Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18064v2 3D CT analysis spans a continuum from low-level perception to high-level clinical understanding. Existing 3D-oriented analysis methods adopt either isolated task-specific modeling or task-agnostic end-to-end paradigms to produce one-hop outputs, impeding the systematic accumulation of perceptual evidence for downstream reasoning. In parallel, recent multimodal large language models (MLLMs) exhibit improved visual perception and can integrate visual and textual information effectively, yet their predominantly 2D-oriented designs fundamentally limit their ability to perceive and analyze volumetric medical data. To bridge this gap, we propose 3DMedAgent, a unified agent that enables 2D MLLMs to perform general 3D CT analysis without 3D-specific fine-tuning. 3DMedAgent coordinates heterogeneous visual and textual tools through a flexible MLLM agent, progressively decomposing complex 3D analysis into tractable subtasks that transition from global to regional views, from 3D volumes to informative 2D slices, and from visual evidence to structured textual representations. Central to this design, 3DMedAgent maintains a long-term structured memory that aggregates intermediate tool outputs and supports query-adaptive, evidence-driven multi-step reasoning. We further introduce the DeepChestVQA benchmark for evaluating unified perception-to-understanding capabilities in 3D thoracic imaging. Experiments across over 40 tasks demonstrate that 3DMedAgent consistently outperforms general, medical, and 3D-specific MLLMs, highlighting a scalable path toward general-purpose 3D clinical assistants.Code and data are available at \href{https://github.com/jinlab-imvr/3DMedAgent}{https://github.com/jinlab-imvr/3DMedAgent}. --- ### Deepmechanics Authors: Abhay Shinde, Aryan Amit Barsainyan, Jose Siguenza, Ankita Vaishnobi Bisoi, Rakshit Kr. Singh, Bharath Ramsundar Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18060v1 Physics-informed deep learning models have emerged as powerful tools for learning dynamical systems. These models directly encode physical principles into network architectures. However, systematic benchmarking of these approaches across diverse physical phenomena remains limited, particularly in conservative and dissipative systems. In addition, benchmarking that has been done thus far does not integrate out full trajectories to check stability. In this work, we benchmark three prominent physics-informed architectures such as Hamiltonian Neural Networks (HNN), Lagrangian Neural Networks (LNN), and Symplectic Recurrent Neural Networks (SRNN) using the DeepChem framework, an open-source scientific machine learning library. We evaluate these models on six dynamical systems spanning classical conservative mechanics (mass-spring system, simple pendulum, double pendulum, and three-body problem, spring-pendulum) and non-conservative systems with contact (bouncing ball). We evaluate models by computing error on predicted trajectories and evaluate error both quantitatively and qualitatively. We find that all benchmarked models struggle to maintain stability for chaotic or nonconservative systems. Our results suggest that more research is needed for physics-informed deep learning models to learn robust models of classical mechanical systems. --- ### Temporal Consistency-Aware Text-to-Motion Generation Authors: Hongsong Wang, Wenjing Yan, Qiuxia Lai, Xin Geng Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18057v1 Text-to-Motion (T2M) generation aims to synthesize realistic human motion sequences from natural language descriptions. While two-stage frameworks leveraging discrete motion representations have advanced T2M research, they often neglect cross-sequence temporal consistency, i.e., the shared temporal structures present across different instances of the same action. This leads to semantic misalignments and physically implausible motions. To address this limitation, we propose TCA-T2M, a framework for temporal consistency-aware T2M generation. Our approach introduces a temporal consistency-aware spatial VQ-VAE (TCaS-VQ-VAE) for cross-sequence temporal alignment, coupled with a masked motion transformer for text-conditioned motion generation. Additionally, a kinematic constraint block mitigates discretization artifacts to ensure physical plausibility. Experiments on HumanML3D and KIT-ML benchmarks demonstrate that TCA-T2M achieves state-of-the-art performance, highlighting the importance of temporal consistency in robust and coherent T2M generation. --- ### Continual-NExT: A Unified Comprehension And Generation Continual Learning Framework Authors: Jingyang Qiao, Zhizhong Zhang, Xin Tan, Jingyu Gong, Yanyun Qu, Yuan Xie Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18055v1 Dual-to-Dual MLLMs refer to Multimodal Large Language Models, which can enable unified multimodal comprehension and generation through text and image modalities. Although exhibiting strong instantaneous learning and generalization capabilities, Dual-to-Dual MLLMs still remain deficient in lifelong evolution, significantly affecting continual adaptation to dynamic real-world scenarios. One of the challenges is that learning new tasks inevitably destroys the learned knowledge. Beyond traditional catastrophic forgetting, Dual-to-Dual MLLMs face other challenges, including hallucination, instruction unfollowing, and failures in cross-modal knowledge transfer. However, no standardized continual learning framework for Dual-to-Dual MLLMs has been established yet, leaving these challenges unexplored. Thus, in this paper, we establish Continual-NExT, a continual learning framework for Dual-to-Dual MLLMs with deliberately-architected evaluation metrics. To improve the continual learning capability of Dual-to-Dual MLLMs, we propose an efficient MAGE (Mixture and Aggregation of General LoRA and Expert LoRA) method to further facilitate knowledge transfer across modalities and mitigate forgetting. Extensive experiments demonstrate that MAGE outperforms other continual learning methods and achieves state-of-the-art performance. --- ### On the Generalization and Robustness in Conditional Value-at-Risk Authors: Dinesh Karthik Mulumudi, Piyushi Manupriya, Gholamali Aminian, Anant Raj Published: 2026-02-20 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2602.18053v1 Conditional Value-at-Risk (CVaR) is a widely used risk-sensitive objective for learning under rare but high-impact losses, yet its statistical behavior under heavy-tailed data remains poorly understood. Unlike expectation-based risk, CVaR depends on an endogenous, data-dependent quantile, which couples tail averaging with threshold estimation and fundamentally alters both generalization and robustness properties. In this work, we develop a learning-theoretic analysis of CVaR-based empirical risk minimization under heavy-tailed and contaminated data. We establish sharp, high-probability generalization and excess risk bounds under minimal moment assumptions, covering fixed hypotheses, finite and infinite classes, and extending to $β$-mixing dependent data; we further show that these rates are minimax optimal. To capture the intrinsic quantile sensitivity of CVaR, we derive a uniform Bahadur-Kiefer type expansion that isolates a threshold-driven error term absent in mean-risk ERM and essential in heavy-tailed regimes. We complement these results with robustness guarantees by proposing a truncated median-of-means CVaR estimator that achieves optimal rates under adversarial contamination. Finally, we show that CVaR decisions themselves can be intrinsically unstable under heavy tails, establishing a fundamental limitation on decision robustness even when the population optimum is well separated. Together, our results provide a principled characterization of when CVaR learning generalizes and is robust, and when instability is unavoidable due to tail scarcity. --- ### CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras Authors: Rong Fu, Yibo Meng, Rui Lu, Jiekai Wu, Simon Fong Published: 2026-02-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.18047v6 City-scale person re-identification across distributed cameras must handle severe appearance changes from viewpoint, occlusion, and domain shift while complying with data protection rules that prevent sharing raw imagery. We introduce CityGuard, a topology-aware transformer for privacy-preserving identity retrieval in decentralized surveillance. The framework integrates three components. A dispersion-adaptive metric learner adjusts instance-level margins according to feature spread, increasing intra-class compactness. Spatially conditioned attention injects coarse geometry, such as GPS or deployment floor plans, into graph-based self-attention to enable projectively consistent cross-view alignment using only coarse geometric priors without requiring survey-grade calibration. Differentially private embedding maps are coupled with compact approximate indexes to support secure and cost-efficient deployment. Together these designs produce descriptors robust to viewpoint variation, occlusion, and domain shifts, and they enable a tunable balance between privacy and utility under rigorous differential-privacy accounting. Experiments on Market-1501 and additional public benchmarks, complemented by database-scale retrieval studies, show consistent gains in retrieval precision and query throughput over strong baselines, confirming the practicality of the framework for privacy-critical urban identity matching. --- ### CityGuard: Graph-Aware Private Descriptors for Bias-Resilient Identity Search Across Urban Cameras Authors: Rong Fu, Yibo Meng, Jia Yee Tan, Rui Lu, Jiekai Wu, Simon Fong Published: 2026-02-20 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.18047v5 City-scale person re-identification across distributed cameras must handle severe appearance changes from viewpoint, occlusion, and domain shift while complying with data protection rules that prevent sharing raw imagery. We introduce CityGuard, a topology-aware transformer for privacy-preserving identity retrieval in decentralized surveillance. The framework integrates three components. A dispersion-adaptive metric learner adjusts instance-level margins according to feature spread, increasing intra-class compactness. Spatially conditioned attention injects coarse geometry, such as GPS or deployment floor plans, into graph-based self-attention to enable projectively consistent cross-view alignment using only coarse geometric priors without requiring survey-grade calibration. Differentially private embedding maps are coupled with compact approximate indexes to support secure and cost-efficient deployment. Together these designs produce descriptors robust to viewpoint variation, occlusion, and domain shifts, and they enable a tunable balance between privacy and utility under rigorous differential-privacy accounting. Experiments on Market-1501 and additional public benchmarks, complemented by database-scale retrieval studies, show consistent gains in retrieval precision and query throughput over strong baselines, confirming the practicality of the framework for privacy-critical urban identity matching. --- ### Conformal Tradeoffs: Operational Profiles Beyond Coverage Authors: Petrus H. Zwart Published: 2026-02-20 Categories: stat.ME, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18045v3 Conformal prediction gives exact finite-sample coverage guarantees under exchangeability, but deployed systems are judged by more than coverage alone. For a fixed calibrated rule reused over a finite operational window, stakeholders also care about deployment-facing quantities such as commitment frequency, deferral, and decisive error exposure. These are not determined by coverage: calibration choices with similar coverage can still induce materially different operational profiles. We study this characterization gap in a scoped setting: binary split conformal prediction under exchangeability with a fixed deployed rule. We introduce the Small-Sample Beta Correction (SSBC) which gives finite-sample coverage semantics for the deployed rule: it inverts the Beta/Beta--Binomial law governing calibration-conditional coverage to map a user request $(α^\star,δ)$ to the least conservative calibration grid point with calibration-conditional PAC semantics for the realized deployed rule. Calibrate-and-Audit then fixes the rule by calibration and uses an independent audit split to estimate the induced region--class label table, a reusable summary from which deployment-facing Key Performance Indicators (KPIs) follow by projection. Under this design, fixed operational rates admit exact finite-sample Binomial inference, while Beta--Binomial envelopes serve as practical predictive summaries for future windows. The induced partition also exposes regime boundaries, Pareto-relevant tradeoffs, and inverse-pricing questions for fixed downstream conventions. Simulations validate the SSBC semantics and compare audit-based summaries with leave-one-out planning proxies; molecular toxicity data provide an audit-based empirical example, and a solubility case study illustrates scenario planning once coverage semantics are fixed. --- ### Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition Authors: Hongyu Qu, Xiangbo Shu, Rui Yan, Hailiang Gao, Wenguan Wang, Jinhui Tang Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18043v1 Few-Shot Action Recognition (FSAR) is a challenging task that requires recognizing novel action categories with a few labeled videos. Recent works typically apply semantically coarse category names as auxiliary contexts to guide the learning of discriminative visual features. However, such context provided by the action names is too limited to provide sufficient background knowledge for capturing novel spatial and temporal concepts in actions. In this paper, we propose DiST, an innovative Decomposition-incorporation framework for FSAR that makes use of decoupled Spatial and Temporal knowledge provided by large language models to learn expressive multi-granularity prototypes. In the decomposition stage, we decouple vanilla action names into diverse spatio-temporal attribute descriptions (action-related knowledge). Such commonsense knowledge complements semantic contexts from spatial and temporal perspectives. In the incorporation stage, we propose Spatial/Temporal Knowledge Compensators (SKC/TKC) to discover discriminative object-level and frame-level prototypes, respectively. In SKC, object-level prototypes adaptively aggregate important patch tokens under the guidance of spatial knowledge. Moreover, in TKC, frame-level prototypes utilize temporal attributes to assist in inter-frame temporal relation modeling. These learned prototypes thus provide transparency in capturing fine-grained spatial details and diverse temporal patterns. Experimental results show DiST achieves state-of-the-art results on five standard FSAR datasets. --- ### PINEAPPLE: Physics-Informed Neuro-Evolution Algorithm for Prognostic Parameter Inference in Lithium-Ion Battery Electrodes Authors: Karkulali Pugalenthi, Jian Cheng Wong, Qizheng Yang, Pao-Hsiung Chiu, My Ha Dao, Nagarajan Raghavan, Chinchun Ooi Published: 2026-02-20 Categories: cs.CE, cs.NE, physics.comp-ph arXiv: https://arxiv.org/abs/2602.18042v1 Accurate, real-time, yet non-destructive estimation of internal states in lithium-ion batteries is critical for predicting degradation, optimizing usage strategies, and extending operational lifespan. Here, we introduce PINEAPPLE (Physics-Informed Neuro-Evolution Algorithm for Prognostic Parameter inference in Lithium-ion battery Electrodes), a novel framework that integrates physics-informed neural networks (PINNs) with an evolutionary search algorithm to enable rapid, scalable, and interpretable parameter inference with potential for application to next-generation batteries. The meta-learned PINN utilizes fundamental physics principles to achieve accurate zero-shot prediction of electrode behavior with test errors below 0.1$\%$ while maintaining an order-of-magnitude speed-up over conventional solvers. PINEAPPLE demonstrates robust parameter inference solely from voltage-time discharge curves across multiple batteries from the open-source CALCE repository, recovering the evolution of key internal state parameters such as Li-ion diffusion coefficients across usage cycles. Notably, the inferred cycle-dependent evolution of these parameters exhibit consistent trends across different batteries without any customized degradation physics-embedded heuristic, highlighting the effective regularizing effect and robustness that can be conferred through incorporation of fundamental physics in PINEAPPLE. By enabling computationally efficient, real-time parameter estimation, PINEAPPLE offers a promising route towards the non-destructive, physics-based characterization of inter-cell and intra-cell variability of battery modules and battery packs, thereby unlocking new opportunities for downstream on-the-fly needs in next-generation battery management systems such as individual cell-scale state-of-health diagnostics. --- ### Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards Authors: Johannes Ackermann, Michael Noukhovitch, Takashi Ishida, Masashi Sugiyama Published: 2026-02-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.18037v2 Reinforcement Learning from Human Feedback (RLHF) or Verifiable Rewards (RLVR) are two key steps in the post-training of modern Language Models (LMs). A common problem is reward hacking, where the policy may exploit inaccuracies of the reward and learn an unintended behavior. Most previous works address this by limiting the policy update with a Kullback-Leibler (KL) penalty towards a reference model. We propose a different framing: Train the LM in a way that biases policy updates towards regions in which the reward is more accurate. First, we derive a theoretical connection between the accuracy of a reward model and the flatness of an optimum at convergence. Gradient regularization (GR) can then be used to bias training to flatter regions and thereby maintain reward model accuracy. We confirm these results by showing that the gradient norm and reward accuracy are empirically correlated in RLHF. We then empirically show that Reference Resets of the KL penalty find flatter regions with a higher reward accuracy. We further improve on this by proposing to use explicit GR with an efficient finite-difference estimate. Empirically, GR performs better than a KL penalty across a diverse set of RL experiments with LMs. GR achieves a higher GPT-judged win-rate in RLHF, avoids overly focusing on the format in rule-based math rewards, and prevents hacking the judge in LLM-as-a-Judge math tasks. --- ### Towards More Standardized AI Evaluation: From Models to Agents Authors: Ali El Filali, Inès Bedar Published: 2026-02-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.18029v1 Evaluation is no longer a final checkpoint in the machine learning lifecycle. As AI systems evolve from static models to compound, tool-using agents, evaluation becomes a core control function. The question is no longer "How good is the model?" but "Can we trust the system to behave as intended, under change, at scale?". Yet most evaluation practices remain anchored in assumptions inherited from the model-centric era: static benchmarks, aggregate scores, and one-off success criteria. This paper argues that such approaches are increasingly obscure rather than illuminating system behavior. We examine how evaluation pipelines themselves introduce silent failure modes, why high benchmark scores routinely mislead teams, and how agentic systems fundamentally alter the meaning of performance measurement. Rather than proposing new metrics or harder benchmarks, we aim to clarify the role of evaluation in the AI era, and especially for agents: not as performance theater, but as a measurement discipline that conditions trust, iteration, and governance in non-deterministic systems. --- ### Mean-Field Reinforcement Learning without Synchrony Authors: Shan Yang Published: 2026-02-20 Categories: cs.MA, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18026v1 Mean-field reinforcement learning (MF-RL) scales multi-agent RL to large populations by reducing each agent's dependence on others to a single summary statistic -- the mean action. However, this reduction requires every agent to act at every time step; when some agents are idle, the mean action is simply undefined. Addressing asynchrony therefore requires a different summary statistic -- one that remains defined regardless of which agents act. The population distribution $μ\in Δ(\mathcal{O})$ -- the fraction of agents at each observation -- satisfies this requirement: its dimension is independent of $N$, and under exchangeability it fully determines each agent's reward and transition. Existing MF-RL theory, however, is built on the mean action and does not extend to $μ$. We therefore construct the Temporal Mean Field (TMF) framework around the population distribution $μ$ from scratch, covering the full spectrum from fully synchronous to purely sequential decision-making within a single theory. We prove existence and uniqueness of TMF equilibria, establish an $O(1/\sqrt{N})$ finite-population approximation bound that holds regardless of how many agents act per step, and prove convergence of a policy gradient algorithm (TMF-PG) to the unique equilibrium. Experiments on a resource selection game and a dynamic queueing game confirm that TMF-PG achieves near-identical performance whether one agent or all $N$ act per step, with approximation error decaying at the predicted $O(1/\sqrt{N})$ rate. --- ### Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets Authors: Haruki Abe, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada Published: 2026-02-20 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2602.18025v1 Scalable robot policy pre-training has been hindered by the high cost of collecting high-quality demonstrations for each platform. In this study, we address this issue by uniting offline reinforcement learning (offline RL) with cross-embodiment learning. Offline RL leverages both expert and abundant suboptimal data, and cross-embodiment learning aggregates heterogeneous robot trajectories across diverse morphologies to acquire universal control priors. We perform a systematic analysis of this offline RL and cross-embodiment paradigm, providing a principled understanding of its strengths and limitations. To evaluate this offline RL and cross-embodiment paradigm, we construct a suite of locomotion datasets spanning 16 distinct robot platforms. Our experiments confirm that this combined approach excels at pre-training with datasets rich in suboptimal trajectories, outperforming pure behavior cloning. However, as the proportion of suboptimal data and the number of robot types increase, we observe that conflicting gradients across morphologies begin to impede learning. To mitigate this, we introduce an embodiment-based grouping strategy in which robots are clustered by morphological similarity and the model is updated with a group gradient. This simple, static grouping substantially reduces inter-robot conflicts and outperforms existing conflict-resolution methods. --- ### Dual-Channel Attention Guidance for Training-Free Image Editing Control in Diffusion Transformers Authors: Guandong Li Published: 2026-02-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.18022v2 Training-free control over editing intensity is a critical requirement for diffusion-based image editing models built on the Diffusion Transformer (DiT) architecture. Existing attention manipulation methods focus exclusively on the Key space to modulate attention routing, leaving the Value space -- which governs feature aggregation -- entirely unexploited. In this paper, we first reveal that both Key and Value projections in DiT's multi-modal attention layers exhibit a pronounced bias-delta structure, where token embeddings cluster tightly around a layer-specific bias vector. Building on this observation, we propose Dual-Channel Attention Guidance (DCAG), a training-free framework that simultaneously manipulates both the Key channel (controlling where to attend) and the Value channel (controlling what to aggregate). We provide a theoretical analysis showing that the Key channel operates through the nonlinear softmax function, acting as a coarse control knob, while the Value channel operates through linear weighted summation, serving as a fine-grained complement. Together, the two-dimensional parameter space $(δ_k, δ_v)$ enables more precise editing-fidelity trade-offs than any single-channel method. Extensive experiments on the PIE-Bench benchmark (700 images, 10 editing categories) demonstrate that DCAG consistently outperforms Key-only guidance across all fidelity metrics, with the most significant improvements observed in localized editing tasks such as object deletion (4.9% LPIPS reduction) and object addition (3.2% LPIPS reduction). --- ### UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models Authors: Jiabing Yang, Yixiang Chen, Yuan Xu, Peiyan Li, Zichen Wen, Bowen Fang, Tao Yu, Xiangnan Wu, Qisen Ma, Kai Wang, Ziheng He, Yingda Li et al. Published: 2026-02-20 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2602.18020v2 Vision-Language-Action (VLA) models leverage pretrained Vision-Language Models (VLMs) as backbones to map images and instructions to actions, demonstrating remarkable potential for generalizable robotic manipulation. To enhance performance, existing methods often incorporate extra observation cues (e.g., depth maps, point clouds) or auxiliary modules (e.g., object detectors, encoders) to enable more precise and reliable task execution, yet these typically require costly data collection and additional training. Inspired by the finding that Feed-Forward Network (FFN) in language models can act as "key-value memory", we propose Uncertainty-aware Observation Reinjection (UAOR), an effective, training-free and plug-and-play module for VLA models. Specifically, when the current language model layer exhibits high uncertainty, measured by Action Entropy, it reinjects key observation information into the next layer's Feed-Forward Network (FFN) through attention retrieval. This mechanism directly augments the hidden states with observation evidence at high-uncertainty layers, enabling more accurate and reliable action generation. Comprehensive experiments show that our method consistently improves diverse VLA models across simulation and real-world tasks with minimal overhead. Notably, UAOR eliminates the need for additional observation cues or modules, making it a versatile and practical plug-in for existing VLA pipelines. The project page is at https://uaor.jiabingyang.cn. --- ### DeepSVU: Towards In-depth Security-oriented Video Understanding via Unified Physical-world Regularized MoE Authors: Yujie Jin, Wenxin Zhang, Jingjing Wang, Guodong Zhou Published: 2026-02-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.18019v1 In the literature, prior research on Security-oriented Video Understanding (SVU) has predominantly focused on detecting and localize the threats (e.g., shootings, robberies) in videos, while largely lacking the effective capability to generate and evaluate the threat causes. Motivated by these gaps, this paper introduces a new chat paradigm SVU task, i.e., In-depth Security-oriented Video Understanding (DeepSVU), which aims to not only identify and locate the threats but also attribute and evaluate the causes threatening segments. Furthermore, this paper reveals two key challenges in the proposed task: 1) how to effectively model the coarse-to-fine physical-world information (e.g., human behavior, object interactions and background context) to boost the DeepSVU task; and 2) how to adaptively trade off these factors. To tackle these challenges, this paper proposes a new Unified Physical-world Regularized MoE (UPRM) approach. Specifically, UPRM incorporates two key components: the Unified Physical-world Enhanced MoE (UPE) Block and the Physical-world Trade-off Regularizer (PTR), to address the above two challenges, respectively. Extensive experiments conduct on our DeepSVU instructions datasets (i.e., UCF-C instructions and CUVA instructions) demonstrate that UPRM outperforms several advanced Video-LLMs as well as non-VLM approaches. Such information.These justify the importance of the coarse-to-fine physical-world information in the DeepSVU task and demonstrate the effectiveness of our UPRM in capturing such information. --- ### Towards LLM-centric Affective Visual Customization via Efficient and Precise Emotion Manipulating Authors: Jiamin Luo, Xuqian Gu, Jingjing Wang, Jiahong Lu Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18016v1 Previous studies on visual customization primarily rely on the objective alignment between various control signals (e.g., language, layout and canny) and the edited images, which largely ignore the subjective emotional contents, and more importantly lack general-purpose foundation models for affective visual customization. With this in mind, this paper proposes an LLM-centric Affective Visual Customization (L-AVC) task, which focuses on generating images within modifying their subjective emotions via Multimodal LLM. Further, this paper contends that how to make the model efficiently align emotion conversion in semantics (named inter-emotion semantic conversion) and how to precisely retain emotion-agnostic contents (named exter-emotion semantic retaining) are rather important and challenging in this L-AVC task. To this end, this paper proposes an Efficient and Precise Emotion Manipulating approach for editing subjective emotions in images. Specifically, an Efficient Inter-emotion Converting (EIC) module is tailored to make the LLM efficiently align emotion conversion in semantics before and after editing, followed by a Precise Exter-emotion Retaining (PER) module to precisely retain the emotion-agnostic contents. Comprehensive experimental evaluations on our constructed L-AVC dataset demonstrate the great advantage of the proposed EPEM approach to the L-AVC task over several state-of-the-art baselines. This justifies the importance of emotion information for L-AVC and the effectiveness of EPEM in efficiently and precisely manipulating such information. --- ### Flow Actor-Critic for Offline Reinforcement Learning Authors: Jongseong Chae, Jongeui Park, Yongjae Shin, Gyeongmin Kim, Seungyul Han, Youngchul Sung Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.18015v1 The dataset distributions in offline reinforcement learning (RL) often exhibit complex and multi-modal distributions, necessitating expressive policies to capture such distributions beyond widely-used Gaussian policies. To handle such complex and multi-modal datasets, in this paper, we propose Flow Actor-Critic, a new actor-critic method for offline RL, based on recent flow policies. The proposed method not only uses the flow model for actor as in previous flow policies but also exploits the expressive flow model for conservative critic acquisition to prevent Q-value explosion in out-of-data regions. To this end, we propose a new form of critic regularizer based on the flow behavior proxy model obtained as a byproduct of flow-based actor design. Leveraging the flow model in this joint way, we achieve new state-of-the-art performance for test datasets of offline RL including the D4RL and recent OGBench benchmarks. --- ### Quasi-Periodic Gaussian Process Predictive Iterative Learning Control Authors: Unnati Nigam, Radhendushka Srivastava, Faezeh Marzbanrad, Michael Burke Published: 2026-02-20 Categories: cs.RO, eess.SY, stat.ML arXiv: https://arxiv.org/abs/2602.18014v1 Repetitive motion tasks are common in robotics, but performance can degrade over time due to environmental changes and robot wear and tear. Iterative learning control (ILC) improves performance by using information from previous iterations to compensate for expected errors in future iterations. This work incorporates the use of Quasi-Periodic Gaussian Processes (QPGPs) into a predictive ILC framework to model and forecast disturbances and drift across iterations. Using a recent structural equation formulation of QPGPs, the proposed approach enables efficient inference with complexity $\mathcal{O}(p^3)$ instead of $\mathcal{O}(i^2p^3)$, where $p$ denotes the number of points within an iteration and $i$ represents the total number of iterations, specially for larger $i$. This formulation also enables parameter estimation without loss of information, making continual GP learning computationally feasible within the control loop. By predicting next-iteration error profiles rather than relying only on past errors, the controller achieves faster convergence and maintains this under time-varying disturbances. We benchmark the method against both standard ILC and conventional Gaussian Process (GP)-based predictive ILC on three tasks, autonomous vehicle trajectory tracking, a three-link robotic manipulator, and a real-world Stretch robot experiment. Across all cases, the proposed approach converges faster and remains robust under injected and natural disturbances while reducing computational cost. This highlights its practicality across a range of repetitive dynamical systems. --- ### Are LLMs Ready for Neural-integrated Mechanistic Modeling? A Benchmark and Agentic Framework Authors: Zihan Guan, Rituparna Datta, Mengxuan Hu, Shunshun Liu, Aiying Zhang, Prasanna Balachandran, Sheng Li, Anil Vullikanti Published: 2026-02-20 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2602.18008v2 Large language models (LLMs) have shown promise in constructing mechanistic models from data. However, existing evaluations largely focus on simplified settings and fail to capture the complexity of real-world scientific modeling. In practice, such modeling often involves neural-integrated formulations, where a mechanistic model component and a neural network component are jointly constructed, leading to a significantly more complex search space. Motivated by this gap, we introduce the Neural-Integrated Mechanistic Modeling (NIMM) benchmark, which evaluates LLM-generated neural-integrated mechanistic models across three scientific domains. Experiments on NIMM reveal that existing LLM-based approaches struggle to effectively explore this complex space, resulting in limited search stability and solution quality. To address this challenge, we propose NIMMGen, a tree-guided agentic framework that enables diversified exploration via branch-level search and improves solutions through atomic model refinement. Extensive experiments demonstrate that NIMMGen achieves state-of-the-art performance on NIMM, significantly improving search stability and solution quality. --- ### MUOT_3M: A 3 Million Frame Multimodal Underwater Benchmark and the MUTrack Tracking Method Authors: Ahsan Baidar Bakht, Mohamad Alansari, Muhayy Ud Din, Muzammal Naseer, Sajid Javed, Irfan Hussain, Jiri Matas, Arif Mahmood Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18006v1 Underwater Object Tracking (UOT) is crucial for efficient marine robotics, large scale ecological monitoring, and ocean exploration; however, progress has been hindered by the scarcity of large, multimodal, and diverse datasets. Existing benchmarks remain small and RGB only, limiting robustness under severe color distortion, turbidity, and low visibility conditions. We introduce MUOT_3M, the first pseudo multimodal UOT benchmark comprising 3 million frames from 3,030 videos (27.8h) annotated with 32 tracking attributes, 677 fine grained classes, and synchronized RGB, estimated enhanced RGB, estimated depth, and language modalities validated by a marine biologist. Building upon MUOT_3M, we propose MUTrack, a SAM-based multimodal to unimodal tracker featuring visual geometric alignment, vision language fusion, and four level knowledge distillation that transfers multimodal knowledge into a unimodal student model. Extensive evaluations across five UOT benchmarks demonstrate that MUTrack achieves up to 8.40% higher AUC and 7.80% higher precision than the strongest SOTA baselines while running at 24 FPS. MUOT_3M and MUTrack establish a new foundation for scalable, multimodally trained yet practically deployable underwater tracking. --- ### Preconditioned Robust Neural Posterior Estimation for Misspecified Simulators Authors: Ryan P. Kelly, David T. Frazier, David J. Warne, Christopher C. Drovandi Published: 2026-02-20 Categories: stat.ME, stat.CO, stat.ML arXiv: https://arxiv.org/abs/2602.18004v1 Simulation-based inference (SBI) enables parameter estimation for complex stochastic models with intractable likelihoods when model simulation is feasible. Neural posterior estimation (NPE) is a popular SBI approach that often achieves accurate inference with far fewer simulations than classical approaches. But in practice, neural approaches can be unreliable for two reasons: incompatible data summaries arising from model misspecification yield unreliable posteriors due to extrapolation, and prior-predictive draws can produce extreme summaries that lead to difficulties in obtaining an accurate posterior for the observed data of interest. Existing preconditioning schemes target well-specified settings, and their behaviour under misspecification remains unexplored. We study preconditioning under misspecification and propose preconditioned robust neural posterior estimation, which computes data-dependent weights that focus training near the observed summaries and fits a robust neural posterior approximation. We also introduce a forest-proximity preconditioning approach that uses tree-based proximity scores to down-weight outlying simulations and concentrate computation around the observed dataset. Across two synthetic examples and one real example with incompatible summaries and extreme prior-predictive behaviour, we demonstrate that preconditioning combined with robust NPE increases stability and improves accuracy, calibration, and posterior-predictive fit over standard baseline methods. --- ### Asynchronous Heavy-Tailed Optimization Authors: Junfei Sun, Dixi Yao, Xuchen Gong, Tahseen Rabbani, Manzil Zaheer, Tian Li Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18002v1 Heavy-tailed stochastic gradient noise, commonly observed in transformer models, can destabilize the optimization process. Recent works mainly focus on developing and understanding approaches to address heavy-tailed noise in the centralized or distributed, synchronous setting, leaving the interactions between such noise and asynchronous optimization underexplored. In this work, we investigate two communication schemes that handle stragglers with asynchronous updates in the presence of heavy-tailed gradient noise. We propose and theoretically analyze algorithmic modifications based on delay-aware learning rate scheduling and delay compensation to enhance the performance of asynchronous algorithms. Our convergence guarantees under heavy-tailed noise match the rate of the synchronous counterparts and improve delay tolerance compared with existing asynchronous approaches. Empirically, our approaches outperform prior synchronous and asynchronous methods in terms of accuracy/runtime trade-offs and are more robust to hyperparameters in both image and language tasks. --- ### Image Quality Assessment: Exploring Quality Awareness via Memory-driven Distortion Patterns Matching Authors: Xuting Lan, Mingliang Zhou, Xuekai Wei, Jielu Yan, Yueting Huang, Huayan Pu, Jun Luo, Weijia Jia Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18000v1 Existing full-reference image quality assessment (FR-IQA) methods achieve high-precision evaluation by analysing feature differences between reference and distorted images. However, their performance is constrained by the quality of the reference image, which limits real-world applications where ideal reference sources are unavailable. Notably, the human visual system has the ability to accumulate visual memory, allowing image quality assessment on the basis of long-term memory storage. Inspired by this biological memory mechanism, we propose a memory-driven quality-aware framework (MQAF), which establishes a memory bank for storing distortion patterns and dynamically switches between dual-mode quality assessment strategies to reduce reliance on high-quality reference images. When reference images are available, MQAF obtains reference-guided quality scores by adaptively weighting reference information and comparing the distorted image with stored distortion patterns in the memory bank. When the reference image is absent, the framework relies on distortion patterns in the memory bank to infer image quality, enabling no-reference quality assessment (NR-IQA). The experimental results show that our method outperforms state-of-the-art approaches across multiple datasets while adapting to both no-reference and full-reference tasks. --- ### Aurora: Neuro-Symbolic AI Driven Advising Agent Authors: Lorena Amanda Quincoso Lugones, Christopher Kverne, Nityam Sharadkumar Bhimani, Ana Carolina Oliveira, Agoritsa Polyzou, Christine Lisetti, Janki Bhimani Published: 2026-02-20 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.17999v1 Academic advising in higher education is under severe strain, with advisor-to-student ratios commonly exceeding 300:1. These structural bottlenecks limit timely access to guidance, increase the risk of delayed graduation, and contribute to inequities in student support. We introduce Aurora, a modular neuro-symbolic advising agent that unifies retrieval-augmented generation (RAG), symbolic reasoning, and normalized curricular databases to deliver policy-compliant, verifiable recommendations at scale. Aurora integrates three components: (i) a Boyce-Codd Normal Form (BCNF) catalog schema for consistent program rules, (ii) a Prolog engine for prerequisite and credit enforcement, and (iii) an instruction-tuned large language model for natural-language explanations of its recommendations. To assess performance, we design a structured evaluation suite spanning common and edge-case advising scenarios, including short-term scheduling, long-term roadmapping, skill-aligned pathways, and out-of-scope requests. Across this diverse set, Aurora improves semantic alignment with expert-crafted answers from 0.68 (Raw LLM baseline) to 0.93 (+36%), achieves perfect precision and recall in nearly half of in-scope cases, and consistently produces correct fallbacks for unanswerable prompts. On commodity hardware, Aurora delivers sub-second mean latency (0.71s across 20 queries), approximately 83X faster than a Raw LLM baseline (59.2s). By combining symbolic rigor with neural fluency, Aurora advances a paradigm for accurate, explainable, and scalable AI-driven advising. ---