# Research Papers — 2026-02 · bundle page 129 of 210 > Full-text markdown of papers #6401–6450 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/129 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/128.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/130.md) ### REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective Authors: Chenwei Wu, Zitao Shuai, Liyue Shen Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00046v1 Medical multi-modal learning is critical for integrating information from a large set of diverse modalities. However, when leveraging a high number of modalities in real clinical applications, it is often impractical to obtain full-modality observations for every patient due to data collection constraints, a problem we refer to as 'High-Modality Learning under Missingness'. In this study, we identify that such missingness inherently induces an exponential growth in possible modality combinations, followed by long-tail distributions of modality combinations due to varying modality availability. While prior work overlooked this critical phenomenon, we find this long-tailed distribution leads to significant underperformance on tail modality combination groups. Our empirical analysis attributes this problem to two fundamental issues: 1) gradient inconsistency, where tail groups' gradient updates diverge from the overall optimization direction; 2) concept shifts, where each modality combination requires distinct fusion functions. To address these challenges, we propose REMIND, a unified framework that REthinks MultImodal learNing under high-moDality missingness from a long-tail perspective. Our core idea is to propose a novel group-specialized Mixture-of-Experts architecture that scalably learns group-specific multi-modal fusion functions for arbitrary modality combinations, while simultaneously leveraging a group distributionally robust optimization strategy to upweight underrepresented modality combinations. Extensive experiments on real-world medical datasets show that our framework consistently outperforms state-of-the-art methods, and robustly generalizes across various medical multi-modal learning applications under high-modality missingness. --- ### Breaking the Factorization Barrier in Diffusion Language Models Authors: Ian Li, Zilei Shao, Benjie Wang, Rose Yu, Guy Van den Broeck, Anji Liu Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00045v3 Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the ``factorization barrier'': the assumption that simultaneously predicted tokens are independent. This limitation forces a trade-off: models must either sacrifice speed by resolving dependencies sequentially or suffer from incoherence due to factorization. We argue that this barrier arises not from limited backbone expressivity, but from a structural misspecification: models are restricted to fully factorized outputs because explicitly parameterizing a joint distribution would require the Transformer to output a prohibitively large number of parameters. We propose Coupled Discrete Diffusion (CoDD), a hybrid framework that breaks this barrier by replacing the fully-factorized output distribution with a lightweight, tractable probabilistic inference layer. This formulation yields a distribution family that is significantly more expressive than standard factorized priors, enabling the modeling of complex joint dependencies, yet remains compact enough to avoid the prohibitive parameter explosion associated with full joint modeling. Empirically, CoDD seamlessly enhances diverse diffusion language model architectures with negligible overhead, matching the reasoning performance of computationally intensive Reinforcement Learning baselines at a fraction of the training cost. Furthermore, it prevents performance collapse in few-step generation, enabling high-quality outputs at significantly reduced latencies. Code available at: https://github.com/liuanji/CoDD. --- ### Property-Driven Evaluation of GNN Expressiveness at Scale: Datasets, Framework, and Study Authors: Sicong Che, Jiayi Yang, Sarfraz Khurshid, Wenxi Wang Published: 2026-02-09 Categories: cs.LG, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.00044v1 Advancing trustworthy AI requires principled software engineering approaches to model evaluation. Graph Neural Networks (GNNs) have achieved remarkable success in processing graph-structured data, however, their expressiveness in capturing fundamental graph properties remains an open challenge. We address this by developing a property-driven evaluation methodology grounded in formal specification, systematic evaluation, and empirical study. Leveraging Alloy, a software specification language and analyzer, we introduce a configurable graph dataset generator that produces two dataset families: GraphRandom, containing diverse graphs that either satisfy or violate specific properties, and GraphPerturb, introducing controlled structural variations. Together, these benchmarks encompass 336 new datasets, each with at least 10,000 labeled graphs, covering 16 fundamental graph properties critical to distributed systems, knowledge graphs, and biological networks. We propose a general evaluation framework that assesses three key aspects of GNN expressiveness: generalizability, sensitivity, and robustness, with two novel quantitative metrics. Using this framework, we conduct the first comprehensive study on global pooling methods' impact on GNN expressiveness. Our findings reveal distinct trade-offs: attention-based pooling excels in generalization and robustness, while second-order pooling provides superior sensitivity, but no single approach consistently performs well across all properties. These insights highlight fundamental limitations and open research directions including adaptive property-aware pooling, scale-sensitive architectures, and robustness-oriented training. By embedding software engineering rigor into AI evaluation, this work establishes a principled foundation for developing expressive and reliable GNN architectures. --- ### Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample Approach Authors: Minghao Han, Lixian Zhang, Chenliang Liu, Zhipeng Zhou, Jun Wang, Wei Pan Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00043v1 This paper presents a novel approach to reinforcement learning (RL) for control systems that provides probabilistic stability guarantees using finite data. Leveraging Lyapunov's method, we propose a probabilistic stability theorem that ensures mean square stability using only a finite number of sampled trajectories. The probability of stability increases with the number and length of trajectories, converging to certainty as data size grows. Additionally, we derive a policy gradient theorem for stabilizing policy learning and develop an RL algorithm, L-REINFORCE, that extends the classical REINFORCE algorithm to stabilization problems. The effectiveness of L-REINFORCE is demonstrated through simulations on a Cartpole task, where it outperforms the baseline in ensuring stability. This work bridges a critical gap between RL and control theory, enabling stability analysis and controller design in a model-free framework with finite data. --- ### LittleBit-2: Maximizing the Spectral Energy Gain in Sub-1-Bit LLMs via Latent Geometry Alignment Authors: Banseok Lee, Youngmin Kim Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00042v2 We identify the Spectral Energy Gain in extreme model compression, where low-rank binary approximations outperform tiny-rank floating-point baselines for heavy-tailed spectra. However, prior attempts fail to realize this potential, trailing state-of-the-art 1-bit methods. We attribute this degradation to Latent Geometry Misalignment: standard singular vectors exhibit high coherence (spiky distribution), the worst-case geometry for binary quantization. To realize this gain, we propose LittleBit-2, a framework employing Internal Latent Rotation and Joint Iterative Quantization (Joint-ITQ). This approach acts as a geometric preconditioner, aligning coherent latent distributions with the binary hypercube with zero inference overhead. Empirically, LittleBit-2 establishes a new state-of-the-art in the sub-1-bit regime (1$\sim$0.1 bpp) on Llama-2 and Llama-3, matching the fidelity of leading 1-bit baselines. --- ### Econometric vs. Causal Structure-Learning for Time-Series Policy Decisions: Evidence from the UK COVID-19 Policies Authors: Bruno Petrungaro, Anthony C. Constantinou Published: 2026-02-09 Categories: cs.LG, cs.AI, econ.EM, stat.ME arXiv: https://arxiv.org/abs/2603.00041v2 Causal machine learning (ML) recovers graphical structures that inform us about potential cause-and-effect relationships. Most progress has focused on cross-sectional data with no explicit time order, whereas recovering causal structures from time series data remains the subject of ongoing research in causal ML. In addition to traditional causal ML, this study assesses econometric methods that some argue can recover causal structures from time series data. The use of these methods can be explained by the significant attention the field of econometrics has given to causality, and specifically to time series, over the years. This presents the possibility of comparing the causal discovery performance between econometric and traditional causal ML algorithms. We seek to understand if there are lessons to be incorporated into causal ML from econometrics, and provide code to translate the results of these econometric methods to the most widely used Bayesian Network R library, bnlearn. We investigate the benefits and challenges that these algorithms present in supporting policy decision-making, using the real-world case of COVID-19 in the UK as an example. Four econometric methods are evaluated in terms of graphical structure, model dimensionality, and their ability to recover causal effects, and these results are compared with those of eleven causal ML algorithms. Amongst our main results, we see that econometric methods provide clear rules for temporal structures, whereas causal-ML algorithms offer broader discovery by exploring a larger space of graph structures that tends to lead to denser graphs that capture more identifiable causal relationships. --- ### Attn-QAT: 4-Bit Attention With Quantization-Aware Training Authors: Peiyuan Zhang, Matthew Noto, Wenxuan Tan, Chengquan Jiang, Will Lin, Wei Zhou, Hao Zhang Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00040v3 Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle due to FP4's tiny dynamic range and attention's heavy-tailed activations. This paper presents the first systematic study of 4-bit quantization-aware training (QAT) for attention. We find ``drop-in'' QAT -- naively combining an FP4 forward pass with high-precision Flash Attention (FA)-style backward pass -- leads to training instability. We identify two key principles for stable FP4 attention: (1) matching low-precision recomputation of attention scores in the backward pass and (2) resolving implicit precision assumptions in FA's gradient calculation. Based on these insights, we propose Attn-QAT and implement fused Triton kernels for training and FP4 inference kernels. Across diffusion and language models, Attn-QAT recovers the quality drop from FP4 attention without explicit outlier-mitigation heuristics used in prior FP4 attention, and delivers up to a 1.5x speedup on an RTX 5090 over SageAttention3 and up to a 1.74x speedup over FA4 on a GB300. Video demos can be found at https://drive.google.com/drive/folders/190F6xbBDUF2kGQYIcXBt3ehSYij5jlim?usp=sharing. Code can be found at https://haoailab.com/FastVideo/training/attn_qat/. --- ### Attn-QAT: 4-Bit Attention With Quantization-Aware Training Authors: Peiyuan Zhang, Matthew Noto, Wenxuan Tan, Chengquan Jiang, Will Lin, Wei Zhou, Hao Zhang Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.00040v2 Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle due to FP4's tiny dynamic range and attention's heavy-tailed activations. This paper presents the first systematic study of 4-bit quantization-aware training (QAT) for attention. We find that "drop-in" QAT, which naively combines an FP4 forward pass with a high-precision Flash Attention (FA)-style backward pass, leads to training instability. We identify two key principles for stable FP4 attention: (1) matching low-precision recomputation of attention scores in the backward pass, and (2) resolving implicit precision assumptions in FA's gradient calculation. Based on these insights, we propose Attn-QAT and implement fused Triton kernels for training as well as FP4 inference kernels. Across diffusion and language models, Attn-QAT recovers the quality drop from FP4 attention without explicit outlier-mitigation heuristics used in prior FP4 attention, and delivers up to a 1.5x speedup on an RTX 5090. Video demos can be found at https://drive.google.com/drive/folders/190F6xbBDUF2kGQYIcXBt3ehSYij5jlim?usp=sharing. --- ### CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation Authors: Jitian Zhao, Changho Shin, Tzu-Heng Huang, Satya Sai Srinath Namburi GNVV, Frederic Sala Published: 2026-02-09 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.00039v2 LLM-as-a-judge ensembles are the standard paradigm for scalable evaluation, but their aggregation mechanisms suffer from a fundamental flaw: they implicitly assume that judges provide independent estimates of true quality. However, in practice, LLM judges exhibit correlated errors caused by shared latent confounders -- such as verbosity, stylistic preferences, or training artifacts -- causing standard aggregation rules like majority vote or averaging to provide little gain or even amplify systematic mistakes. To address this, we introduce CARE, a confounder-aware aggregation framework that explicitly models LLM judge scores as arising from both a latent true-quality signal and shared confounding factors. Rather than heuristically re-weighting judges, CARE separates quality from confounders without access to ground-truth labels. We provide theoretical guarantees for identifiability and finite-sample recovery under shared confounders, and we quantify the systematic bias incurred when aggregation models omit confounding latent factors. Across 12 public benchmarks spanning continuous scoring, binary classification, and pairwise preference settings, CARE improves aggregation accuracy, reducing error by up to 26.8\%. Code is released in \href{https://github.com/SprocketLab/CARE}{https://github.com/SprocketLab/CARE}. --- ### CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation Authors: Jitian Zhao, Changho Shin, Tzu-Heng Huang, Satya Sai Srinath Namburi GNVV, Frederic Sala Published: 2026-02-09 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.00039v1 LLM-as-a-judge ensembles are the standard paradigm for scalable evaluation, but their aggregation mechanisms suffer from a fundamental flaw: they implicitly assume that judges provide independent estimates of true quality. However, in practice, LLM judges exhibit correlated errors caused by shared latent confounders -- such as verbosity, stylistic preferences, or training artifacts -- causing standard aggregation rules like majority vote or averaging to provide little gain or even amplify systematic mistakes. To address this, we introduce CARE, a confounder-aware aggregation framework that explicitly models LLM judge scores as arising from both a latent true-quality signal and shared confounding factors. Rather than heuristically re-weighting judges, CARE separates quality from confounders without access to ground-truth labels. We provide theoretical guarantees for identifiability and finite-sample recovery under shared confounders, and we quantify the systematic bias incurred when aggregation models omit confounding latent factors. Across 12 public benchmarks spanning continuous scoring, binary classification, and pairwise preference settings, CARE improves aggregation accuracy, reducing error by up to 26.8\%. Code is released in \href{https://github.com/SprocketLab/CARE}{https://github.com/SprocketLab/CARE}. --- ### CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation Authors: Chaeyun Kim, YongTaek Lim, Kihyun Kim, Junghwan Kim, Minwoo Kim Published: 2026-02-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.20170v1 Existing red-teaming benchmarks, when adapted to new languages via direct translation, fail to capture socio-technical vulnerabilities rooted in local culture and law, creating a critical blind spot in LLM safety evaluation. To address this gap, we introduce CAGE (Culturally Adaptive Generation), a framework that systematically adapts the adversarial intent of proven red-teaming prompts to new cultural contexts. At the core of CAGE is the Semantic Mold, a novel approach that disentangles a prompt's adversarial structure from its cultural content. This approach enables the modeling of realistic, localized threats rather than testing for simple jailbreaks. As a representative example, we demonstrate our framework by creating KoRSET, a Korean benchmark, which proves more effective at revealing vulnerabilities than direct translation baselines. CAGE offers a scalable solution for developing meaningful, context-aware safety benchmarks across diverse cultures. Our dataset and evaluation rubrics are publicly available at https://github.com/selectstar-ai/CAGE-paper. (WARNING: This paper contains model outputs that can be offensive in nature.) --- ### Autonomous AI and Ownership Rules Authors: Frank Fagan Published: 2026-02-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.20169v1 This Article examines the circumstances in which AI-generated outputs remain linked to their creators and the points at which they lose that connection, whether through accident, deliberate design, or emergent behavior. In cases where AI is traceable to an originator, accession doctrine provides an efficient means of assigning ownership, preserving investment incentives while maintaining accountability. When AI becomes untraceable -- whether through carelessness, deliberate obfuscation, or emergent behavior -- first possession rules can encourage reallocation to new custodians who are incentivized to integrate AI into productive use. The analysis further explores strategic ownership dissolution, where autonomous AI is intentionally designed to evade attribution, creating opportunities for tax arbitrage and regulatory avoidance. To counteract these inefficiencies, bounty systems, private incentives, and government subsidies are proposed as mechanisms to encourage AI capture and prevent ownerless AI from distorting markets. --- ### Benchmarking Early Deterioration Prediction Across Hospital-Rich and MCI-Like Emergency Triage Under Constrained Sensing Authors: KMA Solaiman, Joshua Sebastian, Karma Tobden Published: 2026-02-09 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.20168v2 Emergency triage decisions are made under severe information constraints, yet most data-driven deterioration models are evaluated using signals unavailable during initial assessment. We present a leakage-aware benchmarking framework for early deterioration prediction that evaluates model performance under realistic, time-limited sensing conditions. Using a patient-deduplicated cohort derived from MIMIC-IV-ED, we compare hospital-rich triage with a vitals-only, MCI-like setting, restricting inputs to information available within the first hour of presentation. Across multiple modeling approaches, predictive performance declines only modestly when limited to vitals, indicating that early physiological measurements retain substantial clinical signal. Structured ablation and interpretability analyses identify respiratory and oxygenation measures as the most influential contributors to early risk stratification, with models exhibiting stable, graceful degradation as sensing is reduced. This work provides a clinically grounded benchmark to support the evaluation and design of deployable triage decision-support systems in resource-constrained settings. --- ### ConceptRM: The Quest to Mitigate Alert Fatigue through Consensus-Based Purity-Driven Data Cleaning for Reflection Modelling Authors: Yongda Yu, Lei Zhang, Xinxin Guo, Minghui Yu, Zhengqi Zhuang, Guoping Rong, Haifeng Shen, Zhengfeng Li, Boge Wang, Guoan Zhang, Bangyu Xiang, Xiaobin Xu Published: 2026-02-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.20166v1 In many applications involving intelligent agents, the overwhelming volume of alerts (mostly false) generated by the agents may desensitize users and cause them to overlook critical issues, leading to the so-called ''alert fatigue''. A common strategy is to train a reflection model as a filter to intercept false alerts with labelled data collected from user verification feedback. However, a key challenge is the noisy nature of such data as it is often collected in production environments. As cleaning noise via manual annotation incurs high costs, this paper proposes a novel method ConceptRM for constructing a high-quality corpus to train a reflection model capable of effectively intercepting false alerts. With only a small amount of expert annotations as anchors, ConceptRM creates perturbed datasets with varying noise ratios and utilizes co-teaching to train multiple distinct models for collaborative learning. By analyzing the consensus decisions of these models, it effectively identifies reliable negative samples from a noisy dataset. Experimental results demonstrate that ConceptRM significantly enhances the interception of false alerts with minimal annotation cost, outperforming several state-of-the-art LLM baselines by up to 53.31% on in-domain datasets and 41.67% on out-of-domain datasets. --- ### ZUNA: Flexible EEG Superresolution with Position-Aware Diffusion Autoencoders Authors: Christopher Warner, Jonas Mago, JR Huml, Mohamed Osman, Beren Millidge Published: 2026-02-09 Categories: eess.SP, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18478v1 We present \texttt{ZUNA}, a 380M-parameter masked diffusion autoencoder trained to perform masked channel infilling and superresolution for arbitrary electrode numbers and positions in EEG signals. The \texttt{ZUNA} architecture tokenizes multichannel EEG into short temporal windows and injects spatiotemporal structure via a 4D rotary positional encoding over (x,y,z,t), enabling inference on arbitrary channel subsets and positions. We train ZUNA on an aggregated and harmonized corpus spanning 208 public datasets containing approximately 2 million channel-hours using a combined reconstruction and heavy channel-dropout objective. We show that \texttt{ZUNA} substantially improves over ubiquitous spherical-spline interpolation methods, with the gap widening at higher dropout rates. Crucially, compared to other deep learning methods in this space, \texttt{ZUNA}'s performance \emph{generalizes} across datasets and channel positions allowing it to be applied directly to novel datasets and problems. Despite its generative capabilities, \texttt{ZUNA} remains computationally practical for deployment. We release Apache-2.0 weights and an MNE-compatible preprocessing/inference stack to encourage reproducible comparisons and downstream use in EEG analysis pipelines. --- ### BioLM-Score: Language-Prior Conditioned Probabilistic Geometric Potentials for Protein-Ligand Scoring Authors: Zhangfan Yang, Baoyun Chen, Dong Xu, Jia Wang, Ruibin Bai, Junkai Ji, Zexuan Zhu Published: 2026-02-09 Categories: q-bio.BM, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18476v1 Protein-ligand scoring is a central component of structure-based drug design, underpinning molecular docking, virtual screening, and pose optimization. Conventional physics-based energy functions are often computationally expensive, limiting their utility in large-scale screening. In contrast, deep learning-based scoring models offer improved computational efficiency but frequently suffer from limited cross-target generalization and poor interpretability, which restrict their practical applicability. Here we present BioLM-Score, a simple yet generalizable protein-ligand scoring model that couples geometric modeling with representation learning. Specifically, it employs modality-specific and structure-aware encoders for proteins and ligands, each augmented with biomolecular language models to enrich structural and chemical representations. Subsequently, these representations are integrated through a mixture density network to predict multimodal interatomic distance distributions, from which statistically grounded likelihood-based scores are derived. Evaluations on the CASF-2016 benchmark demonstrate that BioLM-Score achieves significant improvements across docking, scoring, ranking, and screening tasks. Moreover, the proposed scoring function serves as an effective optimization objective for guiding docking protocols and conformational search. In summary, BioLM-Score provides a principled and practical alternative to existing scoring functions, combining efficiency, generalization, and interpretability for structure-based drug discovery. --- ### Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series Authors: Guoqi Yu, Juncheng Wang, Chen Yang, Jing Qin, Angelica I. Aviles-Rivero, Shujun Wang Published: 2026-02-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.18473v2 Accurate analysis of medical time series (MedTS) data, such as electroencephalography (EEG) and electrocardiography (ECG), plays a pivotal role in healthcare applications, including the diagnosis of brain and heart diseases. MedTS data typically exhibit two critical patterns: temporal dependencies within individual channels and channel dependencies across multiple channels. While recent advances in deep learning have leveraged Transformer-based models to effectively capture temporal dependencies, they often struggle with modeling channel dependencies. This limitation stems from a structural mismatch: MedTS signals are inherently centralized, whereas the Transformer's attention mechanism is decentralized, making it less effective at capturing global synchronization and unified waveform patterns. To address this mismatch, we propose CoTAR (Core Token Aggregation-Redistribution), a centralized MLP-based module designed to replace decentralized attention. Instead of allowing all tokens to interact directly, as in standard attention, CoTAR introduces a global core token that serves as a proxy to facilitate inter-token interactions, thereby enforcing a centralized aggregation and redistribution strategy. This design not only better aligns with the centralized nature of MedTS signals but also reduces computational complexity from quadratic to linear. Experiments on five benchmarks validate the superiority of our method in both effectiveness and efficiency, achieving up to a 11.6% improvement on the APAVA dataset, while using only 33% of the memory and 20% of the inference time compared to the previous state of the art. Code and all training scripts are available at https://github.com/Levi-Ackman/TeCh. --- ### Physiologically Informed Deep Learning: A Multi-Scale Framework for Next-Generation PBPK Modeling Authors: Shunqi Liu, Han Qiu, Tong Wang Published: 2026-02-09 Categories: cs.LG, cs.AI, q-bio.QM arXiv: https://arxiv.org/abs/2602.18472v1 Physiologically Based Pharmacokinetic (PBPK) modeling is a cornerstone of model-informed drug development (MIDD), providing a mechanistic framework to predict drug absorption, distribution, metabolism, and excretion (ADME). Despite its utility, adoption is hindered by high computational costs for large-scale simulations, difficulty in parameter identification for complex biological systems, and uncertainty in interspecies extrapolation. In this work, we propose a unified Scientific Machine Learning (SciML) framework that bridges mechanistic rigor and data-driven flexibility. We introduce three contributions: (1) Foundation PBPK Transformers, which treat pharmacokinetic forecasting as a sequence modeling task; (2) Physiologically Constrained Diffusion Models (PCDM), a generative approach that uses a physics-informed loss to synthesize biologically compliant virtual patient populations; and (3) Neural Allometry, a hybrid architecture combining Graph Neural Networks (GNNs) with Neural ODEs to learn continuous cross-species scaling laws. Experiments on synthetic datasets show that the framework reduces physiological violation rates from 2.00% to 0.50% under constraints while offering a path to faster simulation. --- ### Charting the Future of AI-supported Science Education: A Human-Centered Vision Authors: Xiaoming Zhai, Kent Crippen Published: 2026-02-09 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2602.18471v1 This concluding chapter explores how artificial intelligence (AI) is reshaping the purposes, practices, and outcomes of science education, and proposes a human-centered framework for its responsible integration. Drawing on insights from international collaborations and the Advancing AI in Science Education (AASE) committee, the chapter synthesizes developments across five dimensions: educational goals, instructional procedures, learning materials, assessment, and outcomes. We argue that AI offers transformative potential to enrich inquiry, personalize learning, and support teacher practice, but only when guided by Responsible and Ethical Principles (REP). The REP framework, emphasizing fairness, transparency, privacy, accountability, and respect for human values, anchors our vision for AI-supported science education. Key discussions include the redefinition of scientific literacy to encompass AI literacy, the evolving roles of teachers and learners in AI-supported classrooms, and the design of adaptive learning materials and assessments that preserve authenticity and integrity. We highlight both opportunities and risks, stressing the need for critical engagement with AI to avoid reinforcing inequities or undermining human agency. Ultimately, this chapter advances a vision in which science education prepares learners to act as ethical investigators and responsible citizens, ensuring that AI innovation aligns with human dignity, equity, and the broader goals of scientific literacy. --- ### Learning to Drive in New Cities Without Human Demonstrations Authors: Zilin Wang, Saeed Rahmani, Daphne Cornelisse, Bidipta Sarkar, Alexander David Goldie, Jakob Nicolaus Foerster, Shimon Whiteson Published: 2026-02-09 Categories: cs.RO, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2602.15891v1 While autonomous vehicles have achieved reliable performance within specific operating regions, their deployment to new cities remains costly and slow. A key bottleneck is the need to collect many human demonstration trajectories when adapting driving policies to new cities that differ from those seen in training in terms of road geometry, traffic rules, and interaction patterns. In this paper, we show that self-play multi-agent reinforcement learning can adapt a driving policy to a substantially different target city using only the map and meta-information, without requiring any human demonstrations from that city. We introduce NO data Map-based self-play for Autonomous Driving (NOMAD), which enables policy adaptation in a simulator constructed based on the target-city map. Using a simple reward function, NOMAD substantially improves both task success rate and trajectory realism in target cities, demonstrating an effective and scalable alternative to data-intensive city-transfer methods. Project Page: https://nomaddrive.github.io/ --- ### Fine-Tuning a Large Vision-Language Model for Artwork's Scoring and Critique Authors: Zhehan Zhang, Meihua Qian, Li Luo, Siyu Huang, Chaoyi Zhou, Ripon Saha, Xinxin Song Published: 2026-02-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.13306v1 Assessing artistic creativity is foundational to creativity research and arts education, yet manual scoring (e.g., Torrance Tests of Creative Thinking) is labor-intensive at scale. Prior machine-learning approaches show promise for visual creativity scoring, but many rely mainly on image features and provide limited or no explanatory feedback. We propose a framework for automated creativity assessment of human paintings by fine-tuning the vision-language model Qwen2-VL-7B with multi-task learning. Our dataset contains 1000 human-created paintings scored on a 1-100 scale and paired with a short human-written description (content or artist explanation). Two expert raters evaluated each work using a five-dimension rubric (originality, color, texture, composition, content) and provided written critiques; we use an 80/20 train-test split. We add a lightweight regression head on the visual encoder output so the model can predict a numerical score and generate rubric-aligned feedback in a single forward pass. By embedding the structured rubric and the artwork description in the system prompt, we constrain the generated text to match the quantitative prediction. Experiments show strong accuracy, achieving Pearson r > 0.97 and MAE about 3.95 on the 100-point scale. Qualitative evaluation indicates the generated feedback is semantically close to expert critiques (average SBERT cosine similarity = 0.798). The proposed approach bridges computer vision and art assessment and offers a scalable tool for creativity research and classroom feedback. --- ### WildfireVLM: AI-powered Analysis for Early Wildfire Detection and Risk Assessment Using Satellite Imagery Authors: Aydin Ayanzadeh, Prakhar Dixit, Sadia Kamal, Milton Halem Published: 2026-02-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.13305v2 Wildfires are a growing threat to ecosystems, human lives, and infrastructure, with their frequency and intensity rising due to climate change and human activities. Early detection is critical, yet satellite-based monitoring remains challenging due to faint smoke signals, dynamic weather conditions, and the need for real-time analysis over large areas. We introduce WildfireVLM, an AI framework that combines satellite imagery wildfire detection with language-driven risk assessment. We construct a labeled wildfire and smoke dataset using imagery from Landsat-8/9, GOES-16, and other publicly available Earth observation sources, including harmonized products with aligned spectral bands. WildfireVLM employs YOLOv12 to detect fire zones and smoke plumes, leveraging its ability to detect small, complex patterns in satellite imagery. We integrate Multimodal Large Language Models (MLLMs) that convert detection outputs into contextualized risk assessments and prioritized response recommendations for disaster management. We validate the quality of risk reasoning using an LLM-as-judge evaluation with a shared rubric. The system is deployed using a service-oriented architecture that supports real-time processing, visual risk dashboards, and long-term wildfire tracking, demonstrating the value of combining computer vision with language-based reasoning for scalable wildfire monitoring. The code and dataset are publicly available on GitHub at https://github.com/Ayanzadeh93/_WildfireVLM_. --- ### PCReg-Net: Progressive Contrast-Guided Registration for Cross-Domain Image Alignment Authors: Jiahao Qin Published: 2026-02-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.13304v2 Deformable image registration across heterogeneous domains remains challenging because coupled appearance variation and geometric misalignment violate the brightness constancy assumption underlying conventional methods. We propose PCReg-Net, a progressive contrast-guided registration framework that performs coarse-to-fine alignment through four lightweight modules: (1)~a registration U-Net for initial coarse alignment, (2)~a reference feature extractor capturing multi-scale structural cues from the fixed image, (3)~a multi-scale contrast module that identifies residual misalignment by comparing coarse-registered and reference features, and (4)~a refinement U-Net with feature injection that produces the final high-fidelity output. We evaluate on the FIRE-Reg-256 retinal fundus benchmark, demonstrating improvements over both traditional and deep learning baselines. Additional experiments on two microscopy benchmarks further confirm cross-domain applicability. With only 2.56M parameters, PCReg-Net achieves real-time inference at 141 FPS. Code is available at https://github.com/JiahaoQin/PCReg-Net. --- ### Spectral Collapse in Diffusion Inversion Authors: Nicolas Bourriez, Alexandre Verine, Auguste Genovesio Published: 2026-02-09 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2602.13303v1 Conditional diffusion inversion provides a powerful framework for unpaired image-to-image translation. However, we demonstrate through an extensive analysis that standard deterministic inversion (e.g. DDIM) fails when the source domain is spectrally sparse compared to the target domain (e.g., super-resolution, sketch-to-image). In these contexts, the recovered latent from the input does not follow the expected isotropic Gaussian distribution. Instead it exhibits a signal with lower frequencies, locking target sampling to oversmoothed and texture-poor generations. We term this phenomenon spectral collapse. We observe that stochastic alternatives attempting to restore the noise variance tend to break the semantic link to the input, leading to structural drift. To resolve this structure-texture trade-off, we propose Orthogonal Variance Guidance (OVG), an inference-time method that corrects the ODE dynamics to enforce the theoretical Gaussian noise magnitude within the null-space of the structural gradient. Extensive experiments on microscopy super-resolution (BBBC021) and sketch-to-image (Edges2Shoes) demonstrate that OVG effectively restores photorealistic textures while preserving structural fidelity. --- ### DriveMamba: Task-Centric Scalable State Space Model for Efficient End-to-End Autonomous Driving Authors: Haisheng Su, Wei Wu, Feixiang Song, Junjie Zhang, Zhenjie Yang, Junchi Yan Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.13301v2 Recent advances towards End-to-End Autonomous Driving (E2E-AD) have been often devoted on integrating modular designs into a unified framework for joint optimization e.g. UniAD, which follow a sequential paradigm (i.e., perception-prediction-planning) based on separable Transformer decoders and rely on dense BEV features to encode scene representations. However, such manual ordering design can inevitably cause information loss and cumulative errors, lacking flexible and diverse relation modeling among different modules and sensors. Meanwhile, insufficient training of image backbone and quadratic-complexity of attention mechanism also hinder the scalability and efficiency of E2E-AD system to handle spatiotemporal input. To this end, we propose DriveMamba, a Task-Centric Scalable paradigm for efficient E2E-AD, which integrates dynamic task relation modeling, implicit view correspondence learning and long-term temporal fusion into a single-stage Unified Mamba decoder. Specifically, both extracted image features and expected task outputs are converted into token-level sparse representations in advance, which are then sorted by their instantiated positions in 3D space. The linear-complexity operator enables efficient long-context sequential token modeling to capture task-related inter-dependencies simultaneously. Additionally, a bidirectional trajectory-guided "local-to-global" scan method is designed to preserve spatial locality from ego-perspective, thus facilitating the ego-planning. Extensive experiments conducted on nuScenes and Bench2Drive datasets demonstrate the superiority, generalizability and great efficiency of DriveMamba. --- ### KidMesh: Computational Mesh Reconstruction for Pediatric Congenital Hydronephrosis Using Deep Neural Networks Authors: Haoran Sun, Zhanpeng Zhu, Anguo Zhang, Bo Liu, Zhaohua Lin, Liqin Huang, Mingjing Yang, Lei Liu, Shan Lin, Wangbin Ding Published: 2026-02-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.13299v1 Pediatric congenital hydronephrosis (CH) is a common urinary tract disorder, primarily caused by obstruction at the renal pelvis-ureter junction. Magnetic resonance urography (MRU) can visualize hydronephrosis, including renal pelvis and calyces, by utilizing the natural contrast provided by water. Existing voxel-based segmentation approaches can extract CH regions from MRU, facilitating disease diagnosis and prognosis. However, these segmentation methods predominantly focus on morphological features, such as size, shape, and structure. To enable functional assessments, such as urodynamic simulations, external complex post-processing steps are required to convert these results into mesh-level representations. To address this limitation, we propose an end-to-end method based on deep neural networks, namely KidMesh, which could automatically reconstruct CH meshes directly from MRU. Generally, KidMesh extracts feature maps from MRU images and converts them into feature vertices through grid sampling. It then deforms a template mesh according to these feature vertices to generate the specific CH meshes of MRU images. Meanwhile, we develop a novel schema to train KidMesh without relying on accurate mesh-level annotations, which are difficult to obtain due to the sparsely sampled MRU slices. Experimental results show that KidMesh could reconstruct CH meshes in an average of 0.4 seconds, and achieve comparable performance to conventional methods without requiring post-processing. The reconstructed meshes exhibited no self-intersections, with only 3.7% and 0.2% of the vertices having error distances exceeding 3.2mm and 6.4mm, respectively. After rasterization, these meshes achieved a Dice score of 0.86 against manually delineated CH masks. Furthermore, these meshes could be used in renal urine flow simulations, providing valuable urodynamic information for clinical practice. --- ### The Effective Depth Paradox: Evaluating the Relationship between Architectural Topology and Trainability in Deep CNNs Authors: Manfred M. Fischer, Joshua Pitts Published: 2026-02-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.13298v3 This paper investigates the relationship between convolutional neural network (CNN) topology and image recognition performance through a comparative study of the VGG, ResNet, and GoogLeNet architectural families. Utilizing a unified experimental framework, the study isolates the impact of depth from confounding implementation variables. A formal distinction is introduced between nominal depth ($D_{\mathrm{nom}}$), representing the physical layer count, and effective depth ($D_{\mathrm{eff}}$), an operational metric quantifying the expected number of sequential transformations. Empirical results demonstrate that architectures utilizing identity shortcuts or branching modules maintain optimization stability by decoupling $D_{\mathrm{eff}}$ from $D_{\mathrm{nom}}$. These findings suggest that effective depth serves as a superior framework for predicting scaling potential and practical trainability, ultimately indicating that architectural topology - rather than sheer layer volume - is the primary determinant of gradient health in deep learning models. --- ### Conditional Generative Models for High-Resolution Range Profiles: Capturing Geometry-Driven Trends in a Large-Scale Maritime Dataset Authors: Edwyn Brient, Santiago Velasco-Forero, Rami Kassab Published: 2026-02-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.13297v1 High-resolution range profiles (HRRPs) enable fast onboard processing for radar automatic target recognition, but their strong sensitivity to acquisition conditions limits robustness across operational scenarios. Conditional HRRP generation can mitigate this issue, yet prior studies are constrained by small, highly specific datasets. We study HRRP synthesis on a largescale maritime database representative of coastal surveillance variability. Our analysis indicates that the fundamental scenario drivers are geometric: ship dimensions and the desired aspect angle. Conditioning on these variables, we train generative models and show that the synthesized signatures reproduce the expected line-of-sight geometric trend observed in real data. These results highlight the central role of acquisition geometry for robust HRRP generation. --- ### MFN Decomposition and Related Metrics for High-Resolution Range Profiles Generative Models Authors: Edwyn Brient, Santiago Velasco-Forero, Rami Kassab Published: 2026-02-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.13296v1 High-resolution range profile (HRRP ) data are in vogue in radar automatic target recognition (RATR). With the interest in classifying models using HRRP, filling gaps in datasets using generative models has recently received promising contributions. Evaluating generated data is a challenging topic, even for explicit data like face images. However, the evaluation methods used in the state-ofthe-art of HRRP generation rely on classification models. Such models, called ''black-box'', do not allow either explainability on generated data or multi-level evaluation. This work focuses on decomposing HRRP data into three components: the mask, the features, and the noise. Using this decomposition, we propose two metrics based on the physical interpretation of those data. We take profit from an expensive dataset to evaluate our metrics on a challenging task and demonstrate the discriminative ability of those. --- ### VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstruction Authors: Jiarong Liang, Max Ku, Ka-Hei Hui, Ping Nie, Wenhu Chen Published: 2026-02-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.13294v3 Evaluating whether Multimodal Large Language Models (MLLMs) genuinely reason about physical dynamics remains challenging. Most existing benchmarks rely on recognition-style protocols such as Visual Question Answering (VQA) and Violation of Expectation (VoE), which can often be answered without committing to an explicit, testable physical hypothesis. We propose VisPhyWorld, an execution-based framework that evaluates physical reasoning by requiring models to generate executable simulator code from visual observations. By producing runnable code, the inferred world representation is directly inspectable, editable, and falsifiable. This separates physical reasoning from rendering. Building on this framework, we introduce VisPhyBench, comprising 209 evaluation scenes derived from 108 physical templates and a systematic protocol that evaluates how well models reconstruct appearance and reproduce physically plausible motion. Our pipeline produces valid reconstructed videos in 97.7% of benchmark runs before fallback. Experiments show that while state-of-the-art MLLMs achieve strong semantic scene understanding, they struggle to accurately infer physical parameters and to simulate consistent physical dynamics. Our code is available https://github.com/TIGER-AI-Lab/VisPhyWorld --- ### NutVLM: A Self-Adaptive Defense Framework against Full-Dimension Attacks for Vision Language Models in Autonomous Driving Authors: Xiaoxu Peng, Dong Zhou, Jianwen Zhang, Guanghui Sun, Anh Tu Ngo, Anupam Chattopadhyay Published: 2026-02-09 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2602.13293v2 Vision Language Models (VLMs) have advanced perception in autonomous driving (AD), but they remain vulnerable to adversarial threats. These risks range from localized physical patches to imperceptible global perturbations. Existing defense methods for VLMs remain limited and often fail to reconcile robustness with clean-sample performance. To bridge these gaps, we propose NutVLM, a comprehensive self-adaptive defense framework designed to secure the entire perception-decision lifecycle. Specifically, we first employ NutNet++ as a sentinel, which is a unified detection-purification mechanism. It identifies benign samples, local patches, and global perturbations through three-way classification. Subsequently, localized threats are purified via efficient grayscale masking, while global perturbations trigger Expert-guided Adversarial Prompt Tuning (EAPT). Instead of the costly parameter updates of full-model fine-tuning, EAPT generates "corrective driving prompts" via gradient-based latent optimization and discrete projection. These prompts refocus the VLM's attention without requiring exhaustive full-model retraining. Evaluated on the Dolphins benchmark, our NutVLM yields a 4.89% improvement in overall metrics (e.g., Accuracy, Language Score, and GPT Score). These results validate NutVLM as a scalable security solution for intelligent transportation. Our code is available at https://github.com/PXX/NutVLM. --- ### Mirror: A Multi-Agent System for AI-Assisted Ethics Review Authors: Yifan Ding, Yuhui Shi, Zhiyan Li, Zilong Wang, Yifeng Gao, Yajun Yang, Mengjie Yang, Yixiu Liang, Xipeng Qiu, Xuanjing Huang, Xingjun Ma, Yu-Gang Jiang et al. Published: 2026-02-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.13292v1 Ethics review is a foundational mechanism of modern research governance, yet contemporary systems face increasing strain as ethical risks arise as structural consequences of large-scale, interdisciplinary scientific practice. The demand for consistent and defensible decisions under heterogeneous risk profiles exposes limitations in institutional review capacity rather than in the legitimacy of ethics oversight. Recent advances in large language models (LLMs) offer new opportunities to support ethics review, but their direct application remains limited by insufficient ethical reasoning capability, weak integration with regulatory structures, and strict privacy constraints on authentic review materials. In this work, we introduce Mirror, an agentic framework for AI-assisted ethical review that integrates ethical reasoning, structured rule interpretation, and multi-agent deliberation within a unified architecture. At its core is EthicsLLM, a foundational model fine-tuned on EthicsQA, a specialized dataset of 41K question-chain-of-thought-answer triples distilled from authoritative ethics and regulatory corpora. EthicsLLM provides detailed normative and regulatory understanding, enabling Mirror to operate in two complementary modes. Mirror-ER (expedited Review) automates expedited review through an executable rule base that supports efficient and transparent compliance checks for minimal-risk studies. Mirror-CR (Committee Review) simulates full-board deliberation through coordinated interactions among expert agents, an ethics secretary agent, and a principal investigator agent, producing structured, committee-level assessments across ten ethical dimensions. Empirical evaluations demonstrate that Mirror significantly improves the quality, consistency, and professionalism of ethics assessments compared with strong generalist LLMs. --- ### Agent Mars: Multi-Agent Simulation for Multi-Planetary Life Exploration and Settlement Authors: Ziyang Wang Published: 2026-02-09 Categories: cs.MA, astro-ph.IM, cs.AI arXiv: https://arxiv.org/abs/2602.13291v1 Artificial Intelligence (AI) has transformed robotics, healthcare, industry, and scientific discovery, yet a major frontier may lie beyond Earth. Space exploration and settlement offer vast environments and resources, but impose constraints unmatched on Earth: delayed/intermittent communications, extreme resource scarcity, heterogeneous expertise, and strict safety, accountability, and command authority. The key challenge is auditable coordination among specialised humans, robots, and digital services in a safety-critical system-of-systems. We introduce Agent Mars, an open, end-to-end multi-agent simulation framework for Mars base operations. Agent Mars formalises a realistic organisation with a 93-agent roster across seven layers of command and execution (human roles and physical assets), enabling base-scale studies beyond toy settings. It implements hierarchical and cross-layer coordination that preserves chain-of-command while allowing vetted cross-layer exchanges with audit trails; supports dynamic role handover with automatic failover under outages; and enables phase-dependent leadership for routine operations, emergencies, and science campaigns. Agent Mars further models mission-critical mechanisms-scenario-aware short/long-horizon memory, configurable propose-vote consensus, and translator-mediated heterogeneous protocols-to capture how teams align under stress. To quantify behaviour, we propose the Agent Mars Performance Index (AMPI), an interpretable composite score with diagnostic sub-metrics. Across 13 reproducible Mars-relevant operational scripts, Agent Mars reveals coordination trade-offs and identifies regimes where curated cross-layer collaboration and functional leadership reduce overhead without sacrificing reliability. Agent Mars provides a benchmarkable, auditable foundation for Space AI. --- ### Data-driven registration and modeling of brain deformation for image-guided neurosurgery Authors: Tiago Assis, Colin P. Galvin, Joshua P. Castillo, Nazim Haouchine, Marta Kersten-Oertel, Zeyu Gao, Mireia Crispin-Ortuzar, Stephen J. Price, Thomas Santarius, Yangming Ou, Sarah Frisken, Nuno C. Garcia et al. Published: 2026-02-09 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.10155v4 Accurate compensation of brain deformation is critical for reliable image-guided neurosurgery. Surgical manipulation and tumor resection induce tissue motion, causing preoperative planning images to become misaligned with the intraoperative anatomy. In this review, we examine data-driven methods developed between 2020 and 2025 for brain deformation registration and modeling, with a particular focus on learning-based approaches. A comprehensive literature search was conducted in PubMed, IEEE Xplore, Scopus, and Web of Science using predefined inclusion and exclusion criteria for computational methods addressing brain deformation in neurosurgical imaging, resulting in 46 eligible studies. We provide a unified analysis of methodological strategies, including deep learning-based image registration, direct deformation field regression, synthesis-driven multimodal alignment, resection-aware architectures for handling missing correspondences, and hybrid models integrating biomechanical priors. We also examine dataset utilization, evaluation metrics, validation protocols, and the assessment of uncertainty and generalization across studies. While learning-based methods demonstrate promising accuracy and computational efficiency, current approaches remain limited by out-of-distribution robustness, standardized benchmarking, interpretability, and readiness for clinical deployment. Our review highlights these gaps and outlines future directions toward more robust, generalizable, and clinically translatable solutions for neurosurgical guidance. By organizing recent advances and critically assessing evaluation practices, this work provides a comprehensive reference for researchers and clinicians working on data-driven registration and modeling of brain deformation. --- ### Data-Driven Registration and Modeling of Brain Deformation for Image-Guided Neurosurgery: A Systematic Review Authors: Tiago Assis, Colin P. Galvin, Joshua P. Castillo, Nazim Haouchine, Marta Kersten-Oertel, Zeyu Gao, Mireia Crispin-Ortuzar, Stephen J. Price, Thomas Santarius, Yangming Ou, Sarah Frisken, Nuno C. Garcia et al. Published: 2026-02-09 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2602.10155v3 Accurate compensation of brain deformation is critical for reliable image-guided neurosurgery. Surgical manipulation and tumor resection induce tissue motion, causing preoperative planning images to become misaligned with the intraoperative anatomy. In this systematic review, we examine data-driven methods developed between 2020 and 2025 for brain deformation registration and modeling, with a particular focus on learning-based approaches. A comprehensive literature search was conducted in PubMed, IEEE Xplore, Scopus, and Web of Science using predefined inclusion and exclusion criteria for computational methods addressing brain deformation in neurosurgical imaging, resulting in 46 eligible studies. We provide a unified analysis of methodological strategies, including deep learning-based image registration, direct deformation field regression, synthesis-driven multimodal alignment, resection-aware architectures for handling missing correspondences, and hybrid models integrating biomechanical priors. We also examine dataset utilization, evaluation metrics, validation protocols, and the assessment of uncertainty and generalization across studies. While learning-based methods demonstrate promising accuracy and computational efficiency, current approaches remain limited by out-of-distribution robustness, standardized benchmarking, interpretability, and readiness for clinical deployment. Our review highlights these gaps and outlines future directions toward more robust, generalizable, and clinically translatable solutions for neurosurgical guidance. By organizing recent advances and critically assessing evaluation practices, this work provides a comprehensive reference for researchers and clinicians working on data-driven registration and modeling of brain deformation. --- ### PRISM-XR: Empowering Privacy-Aware XR Collaboration with Multimodal Large Language Models Authors: Jiangong Chen, Mingyu Zhu, Bin Li Published: 2026-02-09 Categories: cs.CR, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2602.10154v1 Multimodal Large Language Models (MLLMs) enhance collaboration in Extended Reality (XR) environments by enabling flexible object and animation creation through the combination of natural language and visual inputs. However, visual data captured by XR headsets includes real-world backgrounds that may contain irrelevant or sensitive user information, such as credit cards left on the table or facial identities of other users. Uploading those frames to cloud-based MLLMs poses serious privacy risks, particularly when such data is processed without explicit user consent. Additionally, existing colocation and synchronization mechanisms in commercial XR APIs rely on time-consuming, privacy-invasive environment scanning and struggle to adapt to the highly dynamic nature of MLLM-integrated XR environments. In this paper, we propose PRISM-XR, a novel framework that facilitates multi-user collaboration in XR by providing privacy-aware MLLM integration. PRISM-XR employs intelligent frame preprocessing on the edge server to filter sensitive data and remove irrelevant context before communicating with cloud generative AI models. Additionally, we introduce a lightweight registration process and a fully customizable content-sharing mechanism to enable efficient, accurate, and privacy-preserving content synchronization among users. Our numerical evaluation results indicate that the proposed platform achieves nearly 90% accuracy in fulfilling user requests and less than 0.27 seconds registration time while maintaining spatial inconsistencies of less than 3.5 cm. Furthermore, we conducted an IRB-approved user study with 28 participants, demonstrating that our system could automatically filter highly sensitive objects in over 90% of scenarios while maintaining strong overall usability. --- ### Basic Legibility Protocols Improve Trusted Monitoring Authors: Ashwin Sreevatsa, Sebastian Prasanna, Cody Rushing Published: 2026-02-09 Categories: cs.CR, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2602.10153v1 The AI Control research agenda aims to develop control protocols: safety techniques that prevent untrusted AI systems from taking harmful actions during deployment. Because human oversight is expensive, one approach is trusted monitoring, where weaker, trusted models oversee stronger, untrusted models$\unicode{x2013}$but this often fails when the untrusted model's actions exceed the monitor's comprehension. We introduce legibility protocols, which encourage the untrusted model to take actions that are easier for a monitor to evaluate. We perform control evaluations in the APPS coding setting, where an adversarial agent attempts to write backdoored code without detection. We study legibility protocols that allow the untrusted model to thoroughly document its code with comments$\unicode{x2013}$in contrast to prior work, which removed comments to prevent deceptive ones. We find that: (i) commenting protocols improve safety without sacrificing task performance relative to comment-removal baselines; (ii) commenting disproportionately benefits honest code, which typically has a natural explanation that resolves monitor suspicion, whereas backdoored code frequently lacks an easy justification; (iii) gains from commenting increase with monitor strength, as stronger monitors better distinguish genuine justifications from only superficially plausible ones. --- ### Validating Interpretability in siRNA Efficacy Prediction: A Perturbation-Based, Dataset-Aware Protocol Authors: Zahra Khodagholi, Niloofar Yousefi Published: 2026-02-09 Categories: q-bio.GN, cs.LG arXiv: https://arxiv.org/abs/2602.10152v2 Saliency maps are increasingly used as design guidance in siRNA efficacy prediction, yet attribution methods are rarely validated before motivating sequence edits. We introduce a pre-synthesis gate: a protocol for counterfactual sensitivity faithfulness that tests whether mutating high-saliency positions changes model output more than composition-matched controls. Cross-dataset transfer reveals two failure modes that would otherwise go undetected: faithful-but-wrong (saliency valid, predictions fail) and inverted saliency (top-saliency edits less impactful than random). Strikingly, models trained on mRNA-level assays collapse on a luciferase reporter dataset, demonstrating that protocol shifts can silently invalidate deployment. Across four benchmarks, 19/20 fold instances pass; the single failure shows inverted saliency. A biology-informed regularizer (BioPrior) strengthens saliency faithfulness with modest, dataset-dependent predictive trade-offs. Our results establish saliency validation as essential pre-deployment practice for explanation-guided therapeutic design. Code is available at https://github.com/shadi97kh/BioPrior. --- ### PEST: Physics-Enhanced Swin Transformer for 3D Turbulence Simulation Authors: Yilong Dai, Shengyu Chen, Xiaowei Jia, Peyman Givi, Runlong Yu Published: 2026-02-09 Categories: physics.flu-dyn, cs.AI, math.AP arXiv: https://arxiv.org/abs/2602.10150v1 Accurate simulation of turbulent flows is fundamental to scientific and engineering applications. Direct numerical simulation (DNS) offers the highest fidelity but is computationally prohibitive, while existing data-driven alternatives struggle with stable long-horizon rollouts, physical consistency, and faithful simulation of small-scale structures. These challenges are particularly acute in three-dimensional (3D) settings, where the cubic growth of spatial degrees of freedom dramatically amplifies computational cost, memory demand, and the difficulty of capturing multi-scale interactions. To address these challenges, we propose a Physics-Enhanced Swin Transformer (PEST) for 3D turbulence simulation. PEST leverages a window-based self-attention mechanism to effectively model localized PDE interactions while maintaining computational efficiency. We introduce a frequency-domain adaptive loss that explicitly emphasizes small-scale structures, enabling more faithful simulation of high-frequency dynamics. To improve physical consistency, we incorporate Navier--Stokes residual constraints and divergence-free regularization directly into the learning objective. Extensive experiments on two representative turbulent flow configurations demonstrate that PEST achieves accurate, physically consistent, and stable autoregressive long-term simulations, outperforming existing data-driven baselines. --- ### Semantic Labeling for Third-Party Cybersecurity Risk Assessment: A Semi-Supervised Approach to Intent-Aware Question Retrieval Authors: Ali Nour Eldin, Mohamed Sellami, Mehdi Acheli, Walid Gaaloul, Julien Steunou Published: 2026-02-09 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.10149v3 Third-Party Risk Assessment (TPRA) relies on large repositories of cybersecurity compliance questions used to assess external suppliers against standards such as ISO/IEC 27001 and NIST. In practice, not all questions are relevant for a specific supplier and selecting questions for a given assessment context remains a manual and time-consuming task. Existing question retrieval approaches based on lexical or semantic similarity can identify topically related questions, but they often fail to capture the underlying assessment intent, including control domain and evaluation scope. To address this limitation, we investigate whether an explicit semantic label space can improve intent-aware TPRA question selection. In particular, we separate label space discovery from large-scale label assignment. We start by discovering overlapping clusters of semantically similar questions and then exploit LLMs to assign unique labels for each cluster. Second, we propagate labels through k-nearest neighbors (kNN) for a larger-scale question annotation. Question retrieval is finally achieved by similarity measure of the query with respect to the extracted labels instead of the questions themselves. This reduces repeated LLM calls while preserving label consistency. Experimental results show that the proposed semi-supervised framework reduces labeling cost and runtime compared with per-question LLM annotation while maintaining label quality and improving efficiency. Furthermore, label-based retrieval achieves better alignment with cybersecurity control domains and assessment scope than similarity-based retrieval, highlighting the value of semantic labels as an intermediate representation. --- ### Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks Authors: Yu Yan, Sheng Sun, Shengjia Cheng, Teli Liu, Mingfeng Li, Min Liu Published: 2026-02-09 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2602.10148v1 Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work by distributing malicious clues across modalities to disperse model attention and bypass safety alignment mechanisms. However, these adversarial attacks rely on simple and fixed image-text combinations that lack attack complexity scalability, limiting their effectiveness for red-teaming VLMs' continuously evolving reasoning capabilities. We propose \textbf{CrossTALK} (\textbf{\underline{Cross}}-modal en\textbf{\underline{TA}}ng\textbf{\underline{L}}ement attac\textbf{\underline{K}}), which is a scalable approach that extends and entangles information clues across modalities to exceed VLMs' trained and generalized safety alignment patterns for jailbreak. Specifically, {knowledge-scalable reframing} extends harmful tasks into multi-hop chain instructions, {cross-modal clue entangling} migrates visualizable entities into images to build multimodal reasoning links, and {cross-modal scenario nesting} uses multimodal contextual instructions to steer VLMs toward detailed harmful outputs. Experiments show our COMET achieves state-of-the-art attack success rate. --- ### On the Use of a Large Language Model to Support the Conduction of a Systematic Mapping Study: A Brief Report from a Practitioner's View Authors: Cauã Ferreira Barros, Marcos Kalinowski, Mohamad Kassab, Valdemar Vicente Graciano Neto Published: 2026-02-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.10147v1 The use of Large Language Models (LLMs) has drawn growing interest within the scientific community. LLMs can handle large volumes of textual data and support methods for evidence synthesis. Although recent studies highlight the potential of LLMs to accelerate screening and data extraction steps in systematic reviews, detailed reports of their practical application throughout the entire process remain scarce. This paper presents an experience report on the conduction of a systematic mapping study with the support of LLMs, describing the steps followed, the necessary adjustments, and the main challenges faced. Positive aspects are discussed, such as (i) the significant reduction of time in repetitive tasks and (ii) greater standardization in data extraction, as well as negative aspects, including (i) considerable effort to build reliable well-structured prompts, especially for less experienced users, since achieving effective prompts may require several iterations and testing, which can partially offset the expected time savings, (ii) the occurrence of hallucinations, and (iii) the need for constant manual verification. As a contribution, this work offers lessons learned and practical recommendations for researchers interested in adopting LLMs in systematic mappings and reviews, highlighting both efficiency gains and methodological risks and limitations to be considered. --- ### VERA: Identifying and Leveraging Visual Evidence Retrieval Heads in Long-Context Understanding Authors: Rongcan Pei, Huan Li, Fang Guo, Qi Zhu Published: 2026-02-09 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2602.10146v1 While Vision-Language Models (VLMs) have shown promise in textual understanding, they face significant challenges when handling long context and complex reasoning tasks. In this paper, we dissect the internal mechanisms governing long-context processing in VLMs to understand their performance bottlenecks. Through the lens of attention analysis, we identify specific Visual Evidence Retrieval (VER) Heads - a sparse, dynamic set of attention heads critical for locating visual cues during reasoning, distinct from static OCR heads. We demonstrate that these heads are causal to model performance; masking them leads to significant degradation. Leveraging this discovery, we propose VERA (Visual Evidence Retrieval Augmentation), a training-free framework that detects model uncertainty (i.e., entropy) to trigger the explicit verbalization of visual evidence attended by VER heads. Comprehensive experiments demonstrate that VERA significantly improves long-context understanding of open-source VLMs: it yields an average relative improvement of 21.3% on Qwen3-VL-8B-Instruct and 20.1% on GLM-4.1V-Thinking across five benchmarks. --- ### Silence Routing: When Not Speaking Improves Collective Judgment Authors: Itsuki Fujisaki, Kunhao Yang Published: 2026-02-09 Categories: physics.soc-ph, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2602.10145v1 The wisdom of crowds has been shown to operate not only for factual judgments but also in matters of taste, where accuracy is defined relative to an individual's preferences. However, it remains unclear how different types of social signals should be selectively used in such domains. Focusing on a music preference dataset in which contributors provide both personal evaluations (Own) and estimates of population-level preferences (Estimated), we propose a routing framework for collective intelligence in taste. The framework specifies when contributors should speak, what they should report, and when silence is preferable. Using simulation-based aggregation, we show that prediction accuracy improves over an all-own baseline across a broad region of the parameter space, conditional on items where routing applies. Importantly, these gains arise only when silence is allowed, enabling second-order signals to function effectively. The results demonstrate that collective intelligence in matters of taste depends on principled signal routing rather than simple averaging. --- ### When LLMs get significantly worse: A statistical approach to detect model degradations Authors: Jonas Kübler, Kailash Budhathoki, Matthäus Kleindessner, Xiong Zhou, Junming Yin, Ashish Khetan, George Karypis Published: 2026-02-09 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.10144v2 Minimizing the inference cost and latency of foundation models has become a crucial area of research. Optimization approaches include theoretically lossless methods and others without accuracy guarantees like quantization. In all of these cases it is crucial to ensure that the model quality has not degraded. However, even at temperature zero, model generations are not necessarily robust even to theoretically lossless model optimizations due to numerical errors. We thus require statistical tools to decide whether a finite-sample accuracy deviation is an evidence of a model's degradation or whether it can be attributed to (harmless) noise in the evaluation. We propose a statistically sound hypothesis testing framework based on McNemar's test allowing to efficiently detect model degradations, while guaranteeing a controlled rate of false positives. The crucial insight is that we have to confront the model scores on each sample, rather than aggregated on the task level. Furthermore, we propose three approaches to aggregate accuracy estimates across multiple benchmarks into a single decision. We provide an implementation on top of the largely adopted open source LM Evaluation Harness and provide a case study illustrating that the method correctly flags degraded models, while not flagging model optimizations that are provably lossless. We find that with our tests even empirical accuracy degradations of 0.3% can be confidently attributed to actual degradations rather than noise. --- ### MPA: Multimodal Prototype Augmentation for Few-Shot Learning Authors: Liwen Wu, Wei Wang, Lei Zhao, Zhan Gao, Qika Lin, Shaowen Yao, Zuozhu Liu, Bin Pu Published: 2026-02-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.10143v1 Recently, few-shot learning (FSL) has become a popular task that aims to recognize new classes from only a few labeled examples and has been widely applied in fields such as natural science, remote sensing, and medical images. However, most existing methods focus only on the visual modality and compute prototypes directly from raw support images, which lack comprehensive and rich multimodal information. To address these limitations, we propose a novel Multimodal Prototype Augmentation FSL framework called MPA, including LLM-based Multi-Variant Semantic Enhancement (LMSE), Hierarchical Multi-View Augmentation (HMA), and an Adaptive Uncertain Class Absorber (AUCA). LMSE leverages large language models to generate diverse paraphrased category descriptions, enriching the support set with additional semantic cues. HMA exploits both natural and multi-view augmentations to enhance feature diversity (e.g., changes in viewing distance, camera angles, and lighting conditions). AUCA models uncertainty by introducing uncertain classes via interpolation and Gaussian sampling, effectively absorbing uncertain samples. Extensive experiments on four single-domain and six cross-domain FSL benchmarks demonstrate that MPA achieves superior performance compared to existing state-of-the-art methods across most settings. Notably, MPA surpasses the second-best method by 12.29% and 24.56% in the single-domain and cross-domain setting, respectively, in the 5-way 1-shot setting. --- ### SinFoS: A Parallel Dataset for Translating Sinhala Figures of Speech Authors: Johan Sofalas, Dilushri Pavithra, Nevidu Jayatilleke, Ruvan Weerasinghe Published: 2026-02-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.09866v1 Figures of Speech (FoS) consist of multi-word phrases that are deeply intertwined with culture. While Neural Machine Translation (NMT) performs relatively well with the figurative expressions of high-resource languages, it often faces challenges when dealing with low-resource languages like Sinhala due to limited available data. To address this limitation, we introduce a corpus of 2,344 Sinhala figures of speech with cultural and cross-lingual annotations. We examine this dataset to classify the cultural origins of the figures of speech and to identify their cross-lingual equivalents. Additionally, we have developed a binary classifier to differentiate between two types of FOS in the dataset, achieving an accuracy rate of approximately 92%. We also evaluate the performance of existing LLMs on this dataset. Our findings reveal significant shortcomings in the current capabilities of LLMs, as these models often struggle to accurately convey idiomatic meanings. By making this dataset publicly available, we offer a crucial benchmark for future research in low-resource NLP and culturally aware machine translation. --- ### The effect of whitening on explanation performance Authors: Benedict Clark, Stoyan Karastoyanov, Rick Wilming, Stefan Haufe Published: 2026-02-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.09278v1 Explainable Artificial Intelligence (XAI) aims to provide transparent insights into machine learning models, yet the reliability of many feature attribution methods remains a critical challenge. Prior research (Haufe et al., 2014; Wilming et al., 2022, 2023) has demonstrated that these methods often erroneously assign significant importance to non-informative variables, such as suppressor variables, leading to fundamental misinterpretations. Since statistical suppression is induced by feature dependencies, this study investigates whether data whitening, a common preprocessing technique for decorrelation, can mitigate such errors. Using the established XAI-TRIS benchmark (Clark et al., 2024b), which offers synthetic ground-truth data and quantitative measures of explanation correctness, we empirically evaluate 16 popular feature attribution methods applied in combination with 5 distinct whitening transforms. Additionally, we analyze a minimal linear two-dimensional classification problem (Wilming et al., 2023) to theoretically assess whether whitening can remove the impact of suppressor features from Bayes-optimal models. Our results indicate that, while specific whitening techniques can improve explanation performance, the degree of improvement varies substantially across XAI methods and model architectures. These findings highlight the complex relationship between data non-linearities, preprocessing quality, and attribution fidelity, underscoring the vital role of pre-processing techniques in enhancing model interpretability. --- ### Mutual Information Collapse Explains Disentanglement Failure in $β$-VAEs Authors: Minh Vu, Xiaoliang Wan, Shuangqing Wei Published: 2026-02-09 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2602.09277v1 The $β$-VAE is a foundational framework for unsupervised disentanglement, using $β$ to regulate the trade-off between latent factorization and reconstruction fidelity. Empirically, however, disentanglement performance exhibits a pervasive non-monotonic trend: benchmarks such as MIG and SAP typically peak at intermediate $β$ and collapse as regularization increases. We demonstrate that this collapse is a fundamental information-theoretic failure, where strong Kullback-Leibler pressure promotes marginal independence at the expense of the latent channel's semantic informativeness. By formalizing this mechanism in a linear-Gaussian setting, we prove that for $β> 1$, stationarity-induced dynamics trigger a spectral contraction of the encoder gain, driving latent-factor mutual information to zero. To resolve this, we introduce the $λβ$-VAE, which decouples regularization pressure from informational collapse via an auxiliary $L_2$ reconstruction penalty $λ$. Extensive experiments on dSprites, Shapes3D, and MPI3D-real confirm that $λ> 0$ stabilizes disentanglement and restores latent informativeness over a significantly broader range of $β$, providing a principled theoretical justification for dual-parameter regularization in variational inference backbones. --- ### Effective Reasoning Chains Reduce Intrinsic Dimensionality Authors: Archiki Prasad, Mandar Joshi, Kenton Lee, Mohit Bansal, Peter Shaw Published: 2026-02-09 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.09276v2 Chain-of-thought (CoT) reasoning and its variants have substantially improved the performance of language models on complex reasoning tasks, yet the precise mechanisms by which different strategies facilitate generalization remain poorly understood. While current explanations often point to increased test-time computation or structural guidance, establishing a consistent, quantifiable link between these factors and generalization remains challenging. In this work, we identify intrinsic dimensionality as a quantitative measure for characterizing the effectiveness of reasoning chains. Intrinsic dimensionality quantifies the minimum number of model dimensions needed to reach a given accuracy threshold on a given task. By keeping the model architecture fixed and varying the task formulation through different reasoning strategies, we demonstrate that effective reasoning strategies consistently reduce the intrinsic dimensionality of the task. Validating this on GSM8K with Gemma-3 1B and 4B, we observe a strong inverse correlation between the intrinsic dimensionality of a reasoning strategy and its generalization performance on both in-distribution and out-of-distribution data. Our findings suggest that effective reasoning chains facilitate learning by better compressing the task using fewer parameters, offering a new quantitative metric for analyzing reasoning processes. ---