# Research Papers — 2026-02 · bundle page 55 of 210 > Full-text markdown of papers #2701–2750 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/55 [← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/54.md) [Next bundle →](https://aipod.dev/papers/archive/2026-02/page/56.md) ### RACER: Risk-Aware Calibrated Efficient Routing for Large Language Models Authors: Sai Hao, Hao Zeng, Hongxin Wei, Bingyi Jing Published: 2026-02-20 Categories: cs.LG, cs.AI, math.ST arXiv: https://arxiv.org/abs/2603.06616v1 Efficiently routing queries to the optimal large language model (LLM) is crucial for optimizing the cost-performance trade-off in multi-model systems. However, most existing routers rely on single-model selection, making them susceptible to misrouting. In this work, we formulate LLM routing as the $α$-VOR problem to minimize expected set size while controlling the misrouting risk, and propose a novel method -- RACER, extending base routers to output model sets that can be subsequently aggregated for improved output. In particular, RACER constructs nested model sets via augmented scoring and utilizes finite-sample concentration bounds to calibrate a threshold that allows for both variable set sizes and abstention. We theoretically prove that RACER achieves rigorous distribution-free risk control on unseen test data in a post-hoc and model-agnostic manner. Extensive experiments verify our theoretical guarantees and demonstrate that RACER consistently enhances downstream accuracy across a wide range of benchmarks. --- ### Annealed Co-Generation: Disentangling Variables via Progressive Pairwise Modeling Authors: Hantao Zhang, Jieke Wu, Mingda Xu, Xiao Hu, Yingxuan You, Pascal Fua Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06615v1 For multivariate co-generation in scientific applications, we advocate pairwise block rather than joint modeling of all variables. This design mitigates the computational burden and data imbalance. To this end, we propose an Annealed Co-Generation (ACG) framework that replaces high-dimensional diffusion modeling with a low-dimensional diffusion model, which enables multivariate co-generation by composing pairwise variable generations. We first train an unconditional diffusion model over causal variables that are disentangled into pairs. At inference time, we recover the joint distribution by coupling these pairwise models through shared common variables, enabling coherent multivariate generation without any additional training. By employing a three-stage annealing process-Consensus, Heating, and Cooling-our method enforces consistency across shared common variables and progressively constrains each pairwise data distribution to lie on a learnable manifold, while maintaining high likelihood within each pair. We demonstrate the framework's flexibility and efficacy on two distinct scientific tasks: flow-field completion and antibody generation. All datasets and code will be made publicly available upon publication. --- ### Correlation Analysis of Generative Models Authors: Zhengguo Li, Chaobing Zheng, Wei Wang Published: 2026-02-20 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.06614v1 Based on literature review about existing diffusion models and flow matching with a neural network to predict a predefined target from noisy data, a unified representation is first proposed for these models using two simple linear equations in this paper. Theoretical analysis of the proposed model is then presented. Our theoretical analysis shows that the correlation between the noisy data and the predicted target is sometimes weak in the existing diffusion models and flow matching. This might affect the prediction (or learning) process which plays a crucial role in all models. --- ### OptiRoulette Optimizer: A New Stochastic Meta-Optimizer for up to 5.3x Faster Convergence Authors: Stamatis Mastromichalakis Published: 2026-02-20 Categories: cs.LG, cs.AI, cs.CV, cs.NE arXiv: https://arxiv.org/abs/2603.06613v2 This paper presents OptiRoulette, a stochastic meta-optimizer that selects update rules during training instead of fixing a single optimizer. The method combines warmup optimizer locking, random sampling from an active optimizer pool, compatibility-aware learning-rate scaling during optimizer transitions, and failure-aware pool replacement. OptiRoulette is implemented as a drop-in, "torch.optim.Optimizer-compatible" component and packaged for pip installation. We report completed 10-seed results on five image-classification suites: CIFAR-100, CIFAR-100-C, SVHN, Tiny ImageNet, and Caltech-256. Against a single-optimizer AdamW baseline, OptiRoulette improves mean test accuracy from 0.6734 to 0.7656 on CIFAR-100 (+9.22 percentage points), 0.2904 to 0.3355 on CIFAR-100-C (+4.52), 0.9667 to 0.9756 on SVHN (+0.89), 0.5669 to 0.6642 on Tiny ImageNet (+9.73), and 0.5946 to 0.6920 on Caltech-256 (+9.74). Its main advantage is convergence reliability at higher targets: it reaches CIFAR-100/CIFAR-100-C 0.75, SVHN 0.96, Tiny ImageNet 0.65, and Caltech-256 0.62 validation accuracy in 10/10 runs, while the AdamW baseline reaches none of these targets within budget. On shared targets, OptiRoulette also reduces time-to-target (e.g., Caltech-256 at 0.59: 25.7 vs 77.0 epochs). Paired-seed deltas are positive on all datasets; CIFAR-100-C test ROC-AUC is the only metric not statistically significant in the current 10-seed study. --- ### Consensus is Not Verification: Why Crowd Wisdom Strategies Fail for LLM Truthfulness Authors: Yegor Denisov-Blanch, Joshua Kazdan, Jessica Chudnovsky, Rylan Schaeffer, Sheng Guan, Soji Adeshina, Sanmi Koyejo Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06612v1 Pass@k and other methods of scaling inference compute can improve language model performance in domains with external verifiers, including mathematics and code, where incorrect candidates can be filtered reliably. This raises a natural question: can we similarly scale compute to elicit gains in truthfulness for domains without convenient verification? We show that across five benchmarks and models, surprisingly, it cannot. Even at 25x the inference cost of naive sampling, polling-style aggregation yields no consistent accuracy gains over single-sample baselines and often amplifies shared misconceptions. We find that under uncertainty, models are better at predicting what other models will say within model ensembles than at identifying what is true, revealing a separation between social prediction and truth verification. Across models and benchmarks, aggregation fails to provide a robust truth signal because language model errors are strongly correlated. The source of correlation goes beyond any individual benchmark: we show that even when conditioned on out of distribution random strings and asked to produce pseudo-random outputs, different models produce correlated outputs. Confidence-based weighting provides no benefit because self-reported confidence fails to reliably distinguish correct from incorrect answers. These results delineate a boundary for inference-time scaling: in verified domains, additional samples provide more candidates for a verifier to filter; in unverified domains, additional samples merely reinforce shared misconceptions. --- ### A Novel Approach for Testing Water Safety Using Deep Learning Inference of Microscopic Images of Unincubated Water Samples Authors: Sanjay Srinivasan Published: 2026-02-20 Categories: cs.OH, cs.CV, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2603.06611v1 Fecal-contaminated water causes diseases and even death. Current microbial water safety tests require pathogen incubation, taking 24-72 hours and costing \$20-\$50 per test. This paper presents a solution (DeepScope) exceeding UNICEF's ideal Target Product Profile requirements for presence/absence testing, with an estimated per-test cost of \$0.44. By eliminating the need for pathogen incubation, DeepScope reduces testing time by over 98\%. In DeepScope, a dataset of microscope images of bacteria and water samples was assembled. An innovative augmentation technique, generating up to 21 trillion images from a single microscope image, was developed. Four convolutional neural network models were developed using transfer learning and regularization techniques, then evaluated on a field-test dataset comprising 100,000 microscope images of unseen, real-world water samples collected from fourteen different water sources across Sammamish, WA. Precision-recall analysis showed the DeepScope model achieves 93\% accuracy, with precision of 90\% and recall exceeding 94\%. The DeepScope model was deployed on a web server, and mobile applications for Android and iOS were developed, enabling Internet-based or smartphone-based water safety testing, with results obtained in seconds. --- ### A systematic approach to answering the easy problems of consciousness based on an executable cognitive system Authors: Qi Zhang Published: 2026-02-20 Categories: q-bio.NC, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2603.04440v1 Consciousness is the window of the brain and reflects many fundamental cognitive properties involving both computational and cognitive mechanisms. A collection of these properties was described as the "easy problems" by Chalmers, including the ability to discriminate, categorize, and react to stimuli; information integration; reportability; information access; attention; deliberate control; and the difference between wakefulness and sleep. These "easy problems" have not been systematically addressed. This study presents a first attempt to address them systematically based on an executable cognitive system and its implemented computational mechanisms, built upon an understanding of conceptual knowledge proposed by Kant. The study suggests that the abilities to discriminate, categorize, react, report, and integrate information can all be derived from the system's learning mechanism; attention and deliberate control are goal-oriented and can be attributed to emotional states and its information-manipulation mechanism; and the difference between wakefulness and dream sleep lies mainly in the source of stimuli. The connections between the implemented mechanisms in the executive system and conclusions drawn from empirical findings are also discussed, and many of these discussions and conclusions are supported by demonstrations of the executive system. --- ### CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction Authors: Qingyong Zhu, Yumin Tan, Xiang Gu, Dong Liang Published: 2026-02-20 Categories: eess.IV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.04438v3 Fully unsupervised deep generative modeling (FU-DGM) offers significant potential for compressively sampled magnetic resonance imaging (CS-MRI) reconstruction. Representative FU-DGM formulations, such as deep image prior (DIP) and implicit neural representation (INR), employ architectural bias to induce a low-dimensional manifold in the image space that aligns with the forward observation. However, as the underlying inverse system is highly ill-posed, prolonged iterative fitting in FU-DGM typically leads to poor efficiency and noise amplification. In this paper, guided by the cognitive principle of easy-to-hard learning, we propose CogGen, an FU-DGM framework that reformulates CS-MRI reconstruction as a staged inversion problem. Specifically, CogGen implements an self-paced curriculum learning (SPCL)-driven progressive scheduling strategy through an MRI-aware dual-threshold weighting criterion, which adaptively regulates k-space measurement participation. The data-consistency residual thresholding evaluates the fitting reliability of the current generator, while the k-space radius thresholding controls stage-wise measurement exposure, thereby avoiding uniform fitting throughout optimization. Theoretically, our analysis shows that, when early stages favor easy-to-fit measurements, CogGen yields a reduced local sufficient-iteration bound and a smaller cumulative noise-amplification bound, explaining the improved convergence behavior and reconstruction fidelity of CogGen within a finite iteration budget. Numerical experiments demonstrate that both CogGen instantiations, CogGen-DIP and CogGen-INR, achieve superior performance over prevailing CS-MRI reconstruction techniques, including unsupervised and supervised pipelines. --- ### Multimodal Modular Chain of Thoughts in Energy Performance Certificate Assessment Authors: Zhen Peng, Peter J. Bentley Published: 2026-02-20 Categories: physics.soc-ph, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.00115v1 Accurate evaluation of building energy performance remains challenging in regions where scalable Energy Performance Certificate (EPC) assessments are unavailable. This paper presents a cost-efficient framework that leverages Vision-Language models for automated EPC pre-assessment from limited visual information. The proposed Multimodal Modular Chain of Thoughts (MMCoT) architecture decomposes EPC estimation into intermediate reasoning stages and explicitly propagates inferred attributes across tasks using structured prompting. Experiments on a multimodal dataset of 81 residential properties in the United Kingdom show that MMCoT achieves statistically significant improvements over instruction-only prompting for EPC estimation. Analysis based on accuracy, recall, mean absolute error, and confusion matrices indicate that the proposed approach captures the ordinal structure of EPC ratings, with most errors occurring between adjacent classes. These results suggest that modular prompt-based reasoning offers a promising direction for low-cost EPC pre-assessment in data-scarce settings. --- ### Descriptor: Parasitoid Wasps and Associated Hymenoptera Dataset (DAPWH) Authors: Joao Manoel Herrera Pinheiro, Gabriela Do Nascimento Herrera, Luciana Bueno Dos Reis Fernandes, Alvaro Doria Dos Santos, Ricardo V. Godoy, Eduardo A. B. Almeida, Helena Carolina Onody, Marcelo Andrade Da Costa Vieira, Angelica Maria Penteado-Dias, Marcelo Becker Published: 2026-02-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.20028v3 Accurate taxonomic identification is the cornerstone of biodiversity monitoring and agricultural management, particularly for the hyper-diverse superfamily Ichneumonoidea. Comprising the families Ichneumonidae and Braconidae, these parasitoid wasps are ecologically critical for regulating insect populations, yet they remain one of the most taxonomically challenging groups due to their cryptic morphology and vast number of undescribed species. To address the scarcity of robust digital resources for these key groups, we present a curated image dataset designed to advance automated identification systems. The dataset contains 3,556 high-resolution images, primarily focused on Neotropical Ichneumonidae and Braconidae, while also including supplementary families such as Andrenidae, Apidae, Bethylidae, Chrysididae, Colletidae, Halictidae, Megachilidae, Pompilidae, and Vespidae to improve model robustness. Crucially, a subset of 1,739 images is annotated in COCO format, featuring multi-class bounding boxes for the full insect body, wing venation, and scale bars. This resource provides a foundation for developing computer vision models capable of identifying these families. --- ### Toward AI Autonomous Navigation for Mechanical Thrombectomy using Hierarchical Modular Multi-agent Reinforcement Learning (HM-MARL) Authors: Harry Robertshaw, Nikola Fischer, Lennart Karstensen, Benjamin Jackson, Xingyu Chen, S. M. Hadi Sadati, Christos Bergeles, Alejandro Granados, Thomas C Booth Published: 2026-02-20 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.18663v1 Mechanical thrombectomy (MT) is typically the optimal treatment for acute ischemic stroke involving large vessel occlusions, but access is limited due to geographic and logistical barriers. Reinforcement learning (RL) shows promise in autonomous endovascular navigation, but generalization across 'long' navigation tasks remains challenging. We propose a Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL) framework for autonomous two-device navigation in vitro, enabling efficient and generalizable navigation. HM-MARL was developed to autonomously navigate a guide catheter and guidewire from the femoral artery to the internal carotid artery (ICA). A modular multi-agent approach was used to decompose the complex navigation task into specialized subtasks, each trained using Soft Actor-Critic RL. The framework was validated in both in silico and in vitro testbeds to assess generalization and real-world feasibility. In silico, a single-vasculature model achieved 92-100% success rates on individual anatomies, while a multi-vasculature model achieved 56-80% across multiple patient anatomies. In vitro, both HM-MARL models successfully navigated 100% of trials from the femoral artery to the right common carotid artery and 80% to the right ICA but failed on the left-side vessel superhuman challenge due to the anatomy and catheter type used in navigation. This study presents the first demonstration of in vitro autonomous navigation in MT vasculature. While HM-MARL enables generalization across anatomies, the simulation-to-real transition introduces challenges. Future work will refine RL strategies using world models and validate performance on unseen in vitro data, advancing autonomous MT towards clinical translation. --- ### Large Causal Models for Temporal Causal Discovery Authors: Nikolaos Kougioulis, Nikolaos Gkorgkolis, MingXue Wang, Bora Caglayan, Dario Simionato, Andrea Tonon, Ioannis Tsamardinos Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18662v3 Causal discovery for both cross-sectional and temporal data has traditionally followed a dataset-specific paradigm, where a new model is fitted for each individual dataset. Such an approach limits the potential of multi-dataset pretraining. The concept of large causal models (LCMs) envisions a class of pre-trained neural architectures specifically designed for temporal causal discovery. Prior approaches are constrained to small variable counts, degrade with larger inputs, and rely heavily on synthetic data, limiting generalization. We propose a principled framework for LCMs, combining diverse synthetic generators with realistic time-series datasets, allowing learning at scale. Extensive experiments on synthetic, semi-synthetic and realistic benchmarks show that LCMs scale effectively to higher variable counts and deeper architectures while maintaining strong performance. Trained models achieve competitive or superior accuracy compared to classical and neural baselines, particularly in out-of-distribution settings, while enabling fast, single-pass inference. Results demonstrate LCMs as a promising foundation-model paradigm for temporal causal discovery. Experiments and model weights are available at https://github.com/kougioulis/LCM/. --- ### Large Causal Models for Temporal Causal Discovery Authors: Nikolaos Kougioulis, Nikolaos Gkorgkolis, MingXue Wang, Bora Caglayan, Dario Simionato, Andrea Tonon, Ioannis Tsamardinos Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18662v2 Causal discovery for both cross-sectional and temporal data has traditionally followed a dataset-specific paradigm, where a new model is fitted for each individual dataset. Such an approach limits the potential of multi-dataset pretraining. The concept of large causal models (LCMs) envisions a class of pre-trained neural architectures specifically designed for temporal causal discovery. Prior approaches are constrained to small variable counts, degrade with larger inputs, and rely heavily on synthetic data, limiting generalization. We propose a principled framework for LCMs, combining diverse synthetic generators with realistic time-series datasets, allowing learning at scale. Extensive experiments on synthetic, semi-synthetic and realistic benchmarks show that LCMs scale effectively to higher variable counts and deeper architectures while maintaining strong performance. Trained models achieve competitive or superior accuracy compared to classical and neural baselines, particularly in out-of-distribution settings, while enabling fast, single-pass inference. Results demonstrate LCMs as a promising foundation-model paradigm for temporal causal discovery. Experiments and model weights are available at https://github.com/kougioulis/LCM/. --- ### Communication-Efficient Personalized Adaptation via Federated-Local Model Merging Authors: Yinan Zou, Md Kamran Chowdhury Shisher, Christopher G. Brinton, Vishrant Tripathi Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18658v1 Parameter-efficient fine-tuning methods, such as LoRA, offer a practical way to adapt large vision and language models to client tasks. However, this becomes particularly challenging under task-level heterogeneity in federated deployments. In this regime, personalization requires balancing general knowledge with personalized knowledge, yet existing approaches largely rely on heuristic mixing rules and lack theoretical justification. Moreover, prior model merging approaches are also computation and communication intensive, making the process inefficient in federated settings. In this work, we propose Potara, a principled framework for federated personalization that constructs a personalized model for each client by merging two complementary models: (i) a federated model capturing general knowledge, and (ii) a local model capturing personalized knowledge. Through the construct of linear mode connectivity, we show that the expected task loss admits a variance trace upper bound, whose minimization yields closed-form optimal mixing weights that guarantee a tighter bound for the merged model than for either the federated or local model alone. Experiments on vision and language benchmarks show that Potara consistently improves personalization while reducing communication, leading to a strong performance-communication trade-off. --- ### PolyFrame at MWE-2026 AdMIRe 2: When Words Are Not Enough: Multimodal Idiom Disambiguation Authors: Nina Hosseini-Kivanani Published: 2026-02-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.18652v2 Multimodal models struggle with idiomatic expressions due to their non-compositional meanings, a challenge amplified in multilingual settings. We introduced PolyFrame, our system for the MWE-2026 AdMIRe2 shared task on multimodal idiom disambiguation, featuring a unified pipeline for both image+text ranking (Subtask A) and text-only caption ranking (Subtask B). All model variants retain frozen CLIP-style vision--language encoders and the multilingual BGE M3 encoder, training only lightweight modules: a logistic regression and LLM-based sentence-type predictor, idiom synonym substitution, distractor-aware scoring, and Borda rank fusion. Starting from a CLIP baseline (26.7% Top-1 on English dev, 6.7% on English test), adding idiom-aware paraphrasing and explicit sentence-type classification increased performance to 60.0% Top-1 on English and 60.0% Top-1 (0.822 NDCG@5) in zero-shot transfer to Portuguese. On the multilingual blind test, our systems achieved average Top-1/NDCG scores of 0.35/0.73 for Subtask A and 0.32/0.71 for Subtask B across 15 languages. Ablation results highlight idiom-aware rewriting as the main contributor to performance, while sentence-type prediction and multimodal fusion enhance robustness. These findings suggest that effective idiom disambiguation is feasible without fine-tuning large multimodal encoders. --- ### NutriOrion: A Hierarchical Multi-Agent Framework for Personalized Nutrition Intervention Grounded in Clinical Guidelines Authors: Junwei Wu, Runze Yan, Hanqi Luo, Darren Liu, Minxiao Wang, Kimberly L. Townsend, Lydia S. Hartwig, Derek Milketinas, Xiao Hu, Carl Yang Published: 2026-02-20 Categories: cs.MA, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2602.18650v1 Personalized nutrition intervention for patients with multimorbidity is critical for improving health outcomes, yet remains challenging because it requires the simultaneous integration of heterogeneous clinical conditions, medications, and dietary guidelines. Single-agent large language models (LLMs) often suffer from context overload and attention dilution when processing such high-dimensional patient profiles. We introduce NutriOrion, a hierarchical multi-agent framework with a parallel-then-sequential reasoning topology. NutriOrion decomposes nutrition planning into specialized domain agents with isolated contexts to mitigate anchoring bias, followed by a conditional refinement stage. The framework includes a multi-objective prioritization algorithm to resolve conflicting dietary requirements and a safety constraint mechanism that injects pharmacological contraindications as hard negative constraints during synthesis, ensuring clinical validity by construction rather than post-hoc filtering. For clinical interoperability, NutriOrion maps synthesized insights into the ADIME standard and FHIR R4 resources. Evaluated on 330 stroke patients with multimorbidity, NutriOrion outperforms multiple baselines, including GPT-4.1 and alternative multi-agent architectures. It achieves a 12.1 percent drug-food interaction violation rate, demonstrates strong personalization with negative correlations (-0.26 to -0.35) between patient biomarkers and recommended risk nutrients, and yields clinically meaningful dietary improvements, including a 167 percent increase in fiber and a 27 percent increase in potassium, alongside reductions in sodium (9 percent) and sugars (12 percent). --- ### Global Low-Rank, Local Full-Rank: The Holographic Encoding of Learned Algorithms Authors: Yongzhong Xu Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.18649v1 Grokking -- the abrupt transition from memorization to generalization after extended training -- has been linked to the emergence of low-dimensional structure in learning dynamics. Yet neural network parameters inhabit extremely high-dimensional spaces. How can a low-dimensional learning process produce solutions that resist low-dimensional compression? We investigate this question in multi-task modular arithmetic, training shared-trunk Transformers with separate heads for addition, multiplication, and a quadratic operation modulo 97. Across three model scales (315K--2.2M parameters) and five weight decay settings, we compare three reconstruction methods: per-matrix SVD, joint cross-matrix SVD, and trajectory PCA. Across all conditions, grokking trajectories are confined to a 2--6 dimensional global subspace, while individual weight matrices remain effectively full-rank. Reconstruction from 3--5 trajectory PCs recovers over 95\% of final accuracy, whereas both per-matrix and joint SVD fail at sub-full rank. Even when static decompositions capture most spectral energy, they destroy task-relevant structure. These results show that learned algorithms are encoded through dynamically coordinated updates spanning all matrices, rather than localized low-rank components. We term this the holographic encoding principle: grokked solutions are globally low-rank in the space of learning directions but locally full-rank in parameter space, with implications for compression, interpretability, and understanding how neural networks encode computation. --- ### Noise Scheduling as Information-Guided Allocation in Diffusion Training Authors: Gabriel Raya, Bac Nguyen, Georgios Batzolis, Yuhta Takida, Dejan Stancevic, Naoki Murata, Chieh-Hsin Lai, Yuki Mitsufuji, Luca Ambrogioni Published: 2026-02-20 Categories: cs.LG, cs.AI, cs.CV, cs.IT arXiv: https://arxiv.org/abs/2602.18647v2 We introduce InfoNoise, an online adaptive noise schedule for diffusion training that reallocates optimization effort toward noise levels where denoising is most informative. Together with loss weighting, a noise schedule induces an effective allocation across denoising problems, often fixed before informative noise levels are known. InfoNoise makes this allocation data-adaptive by estimating a conditional-entropy-rate profile from denoising losses during training, without auxiliary models or offline search. Through I--MMSE, this profile identifies where noisy observations rapidly reduce uncertainty about the clean sample and guides adaptation of the training noise distribution. It changes only this distribution, keeping the objective, weighting, and parameterization fixed. On image benchmarks, where schedules have been extensively tuned, InfoNoise matches or slightly exceeds strong baselines and can reach the same quality with fewer updates. On representation, sequence, and modality shifts, including DNA and language generation, InfoNoise improves over fixed and adaptive baselines and reaches target quality with up to $3\times$ less training compute. These results establish the conditional-entropy-rate profile as the data-dependent target for noise schedule design and make online adaptation a practical alternative to manual schedule search. --- ### Adaptive Time Series Reasoning via Segment Selection Authors: Shvat Messica, Jiawen Zhang, Kevin Li, Theodoros Tsiligkaridis, Marinka Zitnik Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18645v3 Time series reasoning tasks often start with a natural language question and require targeted analysis of a time series. Evidence may span the full series or appear in a few short intervals, so the model must decide what to inspect. Most existing approaches encode the entire time series into a fixed representation before inference, regardless of whether or not the entire sequence is relevant. We introduce ARTIST, which formulates time-series reasoning as a sequential decision problem. ARTIST interleaves reasoning with adaptive temporal segment selection. It adopts a controller-reasoner architecture and uses reinforcement learning to train the controller role to select informative segments and the reasoner role to generate segment-conditioned reasoning traces and final answers. During inference, the model actively acquires task-relevant information instead of relying on a static summary of the full sequence. We use a novel hierarchical policy optimization approach for post-training that allows the model to excel in both segment selection and question-answering behavior. We evaluate ARTIST on six time-series reasoning benchmarks and compare it with large language models, vision-language models, and prior time-series reasoning systems. ARTIST improves average accuracy by 6.46 absolute percentage points over the strongest baseline. The largest gains appear on rare event localization and multi-segment reasoning tasks. Supervised fine-tuning improves performance, and reinforcement learning provides additional gains by optimizing question-adaptive segment selection. These results show that selective data use drives effective time-series reasoning. --- ### Auto Quantum Machine Learning for Multisource Classification Authors: Tomasz Rybotycki, Sebastian Dziura, Piotr Gawron Published: 2026-02-20 Categories: quant-ph, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2602.18642v1 With fault-tolerant quantum computing on the horizon, there is growing interest in applying quantum computational methods to data-intensive scientific fields like remote sensing. Quantum machine learning (QML) has already demonstrated potential for such demanding tasks. One area of particular focus is quantum data fusion -- a complex data analysis problem that has attracted significant recent attention. In this work, we introduce an automated QML (AQML) approach for addressing data fusion challenges. We evaluate how AQML-generated quantum circuits perform compared to classical multilayer perceptrons (MLPs) and manually designed QML models when processing multisource inputs. Furthermore, we apply our method to change detection using the multispectral ONERA dataset, achieving improved accuracy over previously reported QML-based change detection results. --- ### Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System Authors: Longfei Yun, Yihan Wu, Haoran Liu, Xiaoxuan Liu, Ziyun Xu, Yi Wang, Yang Xia, Pengfei Wang, Mingze Gao, Yunxiang Wang, Changfan Chen, Fei Liu et al. Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.18640v4 Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progress in this domain is increasingly bottlenecked by the engineering context constraint: the arduous process of translating ambiguous product intent into reasonable, executable, verifiable hypotheses, rather than by modeling techniques alone. We present GEARS (Generative Engine for Agentic Ranking Systems), a framework that reframes ranking optimization as an autonomous discovery process within a programmable experimentation environment. Rather than treating optimization as static model selection, GEARS leverages Specialized Agent Skills to encapsulate ranking expert knowledge into reusable reasoning capabilities, enabling operators to steer systems via high-level intent vibe personalization. Furthermore, to ensure production reliability, the framework incorporates validation hooks to enforce statistical robustness and filter out brittle policies that overfit short-term signals. Experimental validation across diverse product surfaces demonstrates that GEARS consistently identifies superior, near-Pareto-efficient policies by synergizing algorithmic signals with deep ranking context while maintaining rigorous deployment stability. --- ### Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System Authors: Longfei Yun, Yihan Wu, Haoran Liu, Xiaoxuan Liu, Ziyun Xu, Yi Wang, Yang Xia, Pengfei Wang, Mingze Gao, Yunxiang Wang, Changfan Chen, Wenjie Fu et al. Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.18640v2 Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progress in this domain is increasingly bottlenecked by the engineering context constraint: the arduous process of translating ambiguous product intent into reasonable, executable, verifiable hypotheses, rather than by modeling techniques alone. We present GEARS (Generative Engine for Agentic Ranking Systems), a framework that reframes ranking optimization as an autonomous discovery process within a programmable experimentation environment. Rather than treating optimization as static model selection, GEARS leverages Specialized Agent Skills to encapsulate ranking expert knowledge into reusable reasoning capabilities, enabling operators to steer systems via high-level intent vibe personalization. Furthermore, to ensure production reliability, the framework incorporates validation hooks to enforce statistical robustness and filter out brittle policies that overfit short-term signals. Experimental validation across diverse product surfaces demonstrates that GEARS consistently identifies superior, near-Pareto-efficient policies by synergizing algorithmic signals with deep ranking context while maintaining rigorous deployment stability. --- ### Learning Invariant Visual Representations for Planning with Joint-Embedding Predictive World Models Authors: Leonardo F. Toso, Davit Shadunts, Yunyang Lu, Nihal Sharma, Donglin Zhan, Nam H. Nguyen, James Anderson Published: 2026-02-20 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2602.18639v1 World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recent latent predictive architectures (JEPAs), including the DINO world model (DINO-WM), display a degradation in test time robustness due to their sensitivity to "slow features". These include visual variations such as background changes and distractors that are irrelevant to the task being solved. We address this limitation by augmenting the predictive objective with a bisimulation encoder that enforces control-relevant state equivalence, mapping states with similar transition dynamics to nearby latent states while limiting contributions from slow features. We evaluate our model on a simple navigation task under different test-time background changes and visual distractors. Across all benchmarks, our model consistently improves robustness to slow features while operating in a reduced latent space, up to 10x smaller than that of DINO-WM. Moreover, our model is agnostic to the choice of pretrained visual encoder and maintains robustness when paired with DINOv2, SimDINOv2, and iBOT features. --- ### Online decoding of rat self-paced locomotion speed from EEG using recurrent neural networks Authors: Alejandro de Miguel, Nelson Totah, Uri Maoz Published: 2026-02-20 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2602.18637v1 $\textit{Objective.}$ Accurate neural decoding of locomotion holds promise for advancing rehabilitation, prosthetic control, and understanding neural correlates of action. Recent studies have demonstrated decoding of locomotion kinematics across species on motorized treadmills. However, efforts to decode locomotion speed in more natural contexts$-$where pace is self-selected rather than externally imposed$-$are scarce, generally achieve only modest accuracy, and require intracranial implants. Here, we aim to decode self-paced locomotion speed non-invasively and continuously using cortex-wide EEG recordings from rats. $\textit{Approach.}$ We introduce an asynchronous brain$-$computer interface (BCI) that processes a stream of 32-electrode skull-surface EEG (0.01$-$45 Hz) to decode instantaneous speed from a non-motorized treadmill during self-paced locomotion in head-fixed rats. Using recurrent neural networks and a dataset of over 133 h of recordings, we trained decoders to map ongoing EEG activity to treadmill speed. $\textit{Main results.}$ Our decoding achieves a correlation of 0.88 ($R^2$ = 0.78) for speed, primarily driven by visual cortex electrodes and low-frequency ($< 8$ Hz) oscillations. Moreover, pre-training on a single session permitted decoding on other sessions from the same rat, suggesting uniform neural signatures that generalize across sessions but fail to transfer across animals. Finally, we found that cortical states not only carry information about current speed, but also about future and past dynamics, extending up to 1000 ms. $\textit{Significance.}$ These findings demonstrate that self-paced locomotion speed can be decoded accurately and continuously from non-invasive, cortex-wide EEG. Our approach provides a framework for developing high-performing, non-invasive BCI systems and contributes to understanding distributed neural representations of action dynamics. --- ### Musical Training, but not Mere Exposure to Music, Drives the Emergence of Chroma Equivalence in Artificial Neural Networks Authors: Lukas Grasse, Matthew S. Tata Published: 2026-02-20 Categories: cs.SD, cs.NE arXiv: https://arxiv.org/abs/2602.18635v1 Pitch is a fundamental aspect of auditory perception. Pitch perception is commonly described across two perceptual dimensions: pitch height is the sense that tones with varying frequencies seem to be higher or lower, and chroma equivalence is the cyclical similarity of notes octaves, corresponding to a doubling of fundamental frequency. Existing research is divided on whether chroma equivalence is a learned percept that varies according to musical experience and culture, or is an innate percept that develops automatically. Building on a recent framework that proposes to use ANNs to ask 'why' questions about the brain, we evaluated recent auditory ANNs using representational similarity analysis to test the emergence of pitch height and chroma equivalence in their learned representations. Additionally, we fine-tuned two models, Wav2Vec 2.0 and Data2Vec, on a self-supervised learning task using speech and music, and a supervised music transcription task. We found that all models exhibited varying degrees of pitch height representation, but that only models trained on the supervised music transcription task exhibited chroma equivalence. Mere exposure to music through self-supervised learning was not sufficient for chroma equivalence to emerge. This supports the view that chroma equivalence is a higher-order cognitive computation that emerges to support the specific task of music perception, distinct from other auditory perception such as speech listening. This work also highlights the usefulness of ANNs for probing the developmental conditions that give rise to perceptual representations in humans. --- ### DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning Authors: Fangyuan Xu, Sihao Chen, Zinan Lin, Taiwei Shi, Sydney Graham, Pei Zhou, Mengting Wan, Alex Stein, Virginia Estellers, Charles Chen, Morris Sharp, Richard Speyer et al. Published: 2026-02-20 Categories: cs.CL arXiv: https://arxiv.org/abs/2602.18633v1 Differentially private (DP) synthetic data generation plays a pivotal role in developing large language models (LLMs) on private data, where data owners cannot provide eyes-on access to individual examples. Generating DP synthetic data typically involves a difficult trade-off. On one hand, DP finetuning methods train an LLM as a synthetic data generator with formal privacy guarantees, yet it still requires the raw content of private examples for model training. However, methods that avoid direct exposure to private data are bounded by an off-the-shelf, un-finetuned model, whose outputs often lack domain fidelity. Can we train an LLM to generate high-quality synthetic text without eyes-on access to individual private examples? In this work, we introduce Differentially Private Reinforcement Fine-Tuning (DP-RFT), an online reinforcement learning algorithm for synthetic data generation with LLMs. DP-RFT leverages DP-protected nearest-neighbor votes from an eyes-off private corpus as a reward signal for on-policy synthetic samples generated by an LLM. The LLM iteratively learns to generate synthetic data to maximize the expected DP votes through Proximal Policy Optimization (PPO). We evaluate DP-RFT for long-form and domain-specific synthetic data generation, such as news articles, meeting transcripts, and medical article abstracts. Our experiments show that DP-RFT closes the gap between private evolution and DP finetuning methods in terms of the fidelity and downstream utility of the generated synthetic data, while respecting the private data boundary. --- ### Lost in Instructions: Study of Blind Users' Experiences with DIY Manuals and AI-Rewritten Instructions for Assembly, Operation, and Troubleshooting of Tangible Products Authors: Monalika Padma Reddy, Aruna Balasubramanian, Jiawei Zhou, Xiaojun Bi, IV Ramakrishnan, Vikas Ashok Published: 2026-02-20 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.18630v1 AI tools like ChatGPT and Be-My-AI are increasingly being used by blind individuals. Although prior work has explored their use in some Do-It-Yourself (DIY) tasks by blind individuals, little is known about how they use these tools and the available product-manual resources to assemble, operate, and troubleshoot physical or tangible products - tasks requiring spatial reasoning, structural understanding, and precise execution. We address this knowledge gap via an interview study and a usability study with blind participants, investigating how they leverage AI tools and product manuals for DIY tasks with physical products. Findings show that manuals are essential resources, but product-manual instructions are often inadequate for blind users. AI tools presently do not adequately address this insufficiency; in fact, we observed that they often exacerbate this issue with incomplete, incoherent, or misleading guidance. Lastly, we suggest improvements to AI tools for generating tailored instructions for blind users' DIY tasks involving tangible products. --- ### Non-Interfering Weight Fields: Treating Model Parameters as a Continuously Extensible Function Authors: Sarim Chaudhry Published: 2026-02-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.18628v1 Large language models store all learned knowledge in a single, fixed weight vector. Teaching a model new capabilities requires modifying those same weights, inevitably degrading previously acquired knowledge. This fundamental limitation, known as catastrophic forgetting, has resisted principled solutions for decades. Existing approaches treat weights as immutable artifacts that must be protected through techniques like regularization heuristics, replay buffers, or isolated adapter modules. The problem is none of these provide a structural guarantee against forgetting. In this work, we propose Non-Interfering Weight Fields (NIWF), a framework that replaces the fixed weight paradigm with a learned function that generates weight configurations on demand from a continuous capability coordinate space. After training on a task, we commit the occupied coordinate region by snapshotting the fields outputs on anchor points to enforce a functional lock during all future training. We validate NIWF on sequential instructionfollowing and code generation tasks using Mistral-7B, demonstrating zero forgetting on committed tasks with competitive perplexity on new tasks. The framework introduces the notion of software-like versioning for neural network intelligence, where capabilities can be committed, extended, composed, and rolled back without retraining. --- ### Federated Learning-Assisted Optimization of Mobile Transmission with Digital Twins Authors: Mohammad Heydari, Terence D. Todd, Dongmei Zhao, George Karakostas Published: 2026-02-20 Categories: cs.NI, cs.LG arXiv: https://arxiv.org/abs/2602.18627v1 A Digital Twin (DT) may protect information that is considered private to its associated physical system. For a mobile device, this may include its mobility profile, recent location(s), and experienced channel conditions. Online schedulers, however, typically use this type of information to perform tasks such as shared bandwidth and channel time slot assignments. In this paper, we consider three transmission scheduling problems with energy constraints, where such information is needed, and yet must remain private: minimizing total transmission time when (i) fixed-power or (ii) fixed-rate time slotting with power control is used, and (iii) maximizing the amount of data uploaded in a fixed time period. Using a real-time federated optimization framework, we show how the scheduler can iteratively interact only with the DTs to produce global fractional solutions to these problems, without the latter revealing their private information. Then dependent rounding is used to round the fractional solution into a channel transmission schedule for the physical systems. Experiments show consistent makespan reductions with near-zero bandwidth/energy violations and millisecond-order end-to-end runtime for typical edge server hardware. To the best of our knowledge, this is the first framework that enables channel sharing across DTs using operations that do not expose private data. --- ### Finding the Signal in the Noise: An Exploratory Study on Assessing the Effectiveness of AI and Accessibility Forums for Blind Users' Support Needs Authors: Satwik Ram Kodandaram, Jiawei Zhou, Xiaojun Bi, IV Ramakrishnan, Vikas Ashok Published: 2026-02-20 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2602.18623v1 Accessibility forums and, more recently, generative AI tools have become vital resources for blind users seeking solutions to computer-interaction issues and learning about new assistive technologies, screen reader features, tutorials, and software updates. Understanding user experiences with these resources is essential for identifying and addressing persistent support gaps. Towards this, we interviewed 14 blind users who regularly engage with forums and GenAI tools. Findings revealed that forums often overwhelm users with multiple overlapping topics, redundant or irrelevant content, and fragmented responses that must be mentally pieced together, increasing cognitive load. GenAI tools, while offering more direct assistance, introduce new barriers by producing unreliable answers, including overly verbose or fragmented guidance, fabricated information, and contradictory suggestions that fail to follow prompts, thereby heightening verification demands. Based on these insights, we outlined design opportunities to improve the reliability of assistive resources, aiming to provide blind users with more trustworthy and cognitively-manageable support. --- ### Narrating For You: Prompt-guided Audio-visual Narrating Face Generation Employing Multi-entangled Latent Space Authors: Aashish Chandra, Aashutosh A, Abhijit Das Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18618v1 We present a novel approach for generating realistic speaking and talking faces by synthesizing a person's voice and facial movements from a static image, a voice profile, and a target text. The model encodes the prompt/driving text, the driving image, and the voice profile of an individual and then combines them to pass them to the multi-entangled latent space to foster key-value pairs and queries for the audio and video modality generation pipeline. The multi-entangled latent space is responsible for establishing the spatiotemporal person-specific features between the modalities. Further, entangled features are passed to the respective decoder of each modality for output audio and video generation. --- ### Effect of Patch Size on Fine-Tuning Vision Transformers in Two-Dimensional and Three-Dimensional Medical Image Classification Authors: Massoud Dehghan, Ramona Woitek, Amirreza Mahbod Published: 2026-02-20 Categories: cs.CV arXiv: https://arxiv.org/abs/2602.18614v1 Vision Transformers (ViTs) and their variants have become state-of-the-art in many computer vision tasks and are widely used as backbones in large-scale vision and vision-language foundation models. While substantial research has focused on architectural improvements, the impact of patch size, a crucial initial design choice in ViTs, remains underexplored, particularly in medical domains where both two-dimensional (2D) and three-dimensional (3D) imaging modalities exist. In this study, using 12 medical imaging datasets from various imaging modalities (including seven 2D and five 3D datasets), we conduct a thorough evaluation of how different patch sizes affect ViT classification performance. Using a single graphical processing unit (GPU) and a range of patch sizes (1, 2, 4, 7, 14, 28), we fine-tune ViT models and observe consistent improvements in classification performance with smaller patch sizes (1, 2, and 4), which achieve the best results across nearly all datasets. More specifically, our results indicate improvements in balanced accuracy of up to 12.78% for 2D datasets (patch size 2 vs. 28) and up to 23.78% for 3D datasets (patch size 1 vs. 14), at the cost of increased computational expense. Moreover, by applying a straightforward ensemble strategy that fuses the predictions of the models trained with patch sizes 1, 2, and 4, we demonstrate a further boost in performance in most cases, especially for the 2D datasets. Our implementation is publicly available on GitHub: https://github.com/HealMaDe/MedViT --- ### Diagnosing LLM Reranker Behavior Under Fixed Evidence Pools Authors: Baris Arat, Emre Sefer Published: 2026-02-20 Categories: cs.LG, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.18613v2 Standard reranking evaluations study how a reranker orders candidates returned by an upstream retriever. This setup couples ranking behavior with retrieval quality, so differences in output cannot be attributed to the ranking policy alone. We introduce a controlled diagnostic for reranking that uses Multi-News clusters as fixed evidence pools. We limit each pool to eight documents and pass identical inputs to all rankers. Within this setup, BM25 and MMR serve as interpretable reference points for lexical matching and diversity optimization. Across 345 clusters, we find that redundancy patterns vary by model: one LLM implicitly diversifies at larger selection budgets, while another increases redundancy. In contrast, LLMs underperform on lexical coverage at small selection budgets. As a result, LLM rankings diverge substantially from both baselines rather than consistently approximating either strategy. By reducing retrieval variance through fixed pools, we interpret these differences more directly as differences in ranking policy. This diagnostic is model agnostic and can be applied to any ranker, including open source systems and proprietary APIs. Our code and processed data for both the Multi-News diagnostic and the complementary TREC-DL evaluation are publicly available at https://github.com/barisarat/llm_reranker_multinews.git. --- ### Diagnosing LLM Reranker Behavior Under Fixed Evidence Pools Authors: Baris Arat, Emre Sefer Published: 2026-02-20 Categories: cs.LG, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2602.18613v1 Standard reranking evaluations study how a reranker orders candidates returned by an upstream retriever. This setup couples ranking behavior with retrieval quality, so differences in output cannot be attributed to the ranking policy alone. We introduce a controlled diagnostic that isolates reranking by using Multi-News clusters as fixed evidence pools. We limit each pool to exactly eight documents and pass identical inputs to all rankers. Within this setup, BM25 and MMR serve as interpretable reference points for lexical matching and diversity optimization. Across 345 clusters, we find that redundancy patterns vary by model: one LLM implicitly diversifies at larger selection budgets, while another increases redundancy. In contrast, LLMs underperform on lexical coverage at small selection budgets. As a result, LLM rankings diverge substantially from both baselines rather than consistently approximating either strategy. By eliminating retrieval variance, we can attribute these differences directly to the ranking policy. This diagnostic is model-agnostic and applicable to any ranker, including open source systems and proprietary APIs. --- ### Feedback-based Automated Verification in Vibe Coding of CAS Adaptation Built on Constraint Logic Authors: Michal Töpfer, František Plášil, Tomáš Bureš, Petr Hnětynka Published: 2026-02-20 Categories: cs.AI arXiv: https://arxiv.org/abs/2602.18607v1 In CAS adaptation, a challenge is to define the dynamic architecture of the system and changes in its behavior. Implementation-wise, this is projected into an adaptation mechanism, typically realized as an Adaptation Manager (AM). With the advances of generative LLMs, generating AM code based on system specification and desired AM behavior (partially in natural language) is a tempting opportunity. The recent introduction of vibe coding suggests a way to target the problem of the correctness of generated code by iterative testing and vibe coding feedback loops instead of direct code inspection. In this paper, we show that generating an AM via vibe coding feedback loops is a viable option when the verification of the generated AM is based on a very precise formulation of the functional requirements. We specify these as constraints in a novel temporal logic FCL that allows us to express the behavior of traces with much finer granularity than classical LTL enables. Furthermore, we show that by combining the adaptation and vibe coding feedback loops where the FCL constraints are evaluated for the current system state, we achieved good results in the experiments with generating AMs for two example systems from the CAS domain. Typically, just a few feedback loop iterations were necessary, each feeding the LLM with reports describing detailed violations of the constraints. This AM testing was combined with high run path coverage achieved by different initial settings. --- ### OVerSeeC: Open-Vocabulary Costmap Generation from Satellite Images and Natural Language Authors: Rwik Rana, Jesse Quattrociocchi, Dongmyeong Lee, Christian Ellis, Amanda Adkins, Adam Uccello, Garrett Warnell, Joydeep Biswas Published: 2026-02-20 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2602.18606v2 Aerial imagery provides essential global context for autonomous navigation, enabling route planning at scales inaccessible to onboard sensing. We address the problem of generating global costmaps for long-range planning directly from satellite imagery when entities and mission-specific traversal rules are expressed in natural language at test time. This setting is challenging since mission requirements vary, terrain entities may be unknown at deployment, and user prompts often encode compositional traversal logic. Existing approaches relying on fixed ontologies and static cost mappings cannot accommodate such flexibility. While foundation models excel at language interpretation and open-vocabulary perception, no single model can simultaneously parse nuanced mission directives, locate arbitrary entities in large-scale imagery, and synthesize them into an executable cost function for planners. We therefore propose OVerSeeC, a zero-shot modular framework that decomposes the problem into Interpret-Locate-Synthesize: (i) an LLM extracts entities and ranked preferences, (ii) an open-vocabulary segmentation pipeline identifies these entities from high-resolution imagery, and (iii) the LLM uses the user's natural language preferences and masks to synthesize executable costmap code. Empirically, OVerSeeC handles novel entities, respects ranked and compositional preferences, and produces routes consistent with human-drawn trajectories across diverse regions, demonstrating robustness to distribution shifts. This shows that modular composition of foundation models enables open-vocabulary, preference-aligned costmap generation for scalable, mission-adaptive global planning. --- ### Enhancing Goal Inference via Correction Timing Authors: Anjiabei Wang, Shuangge Wang, Tesca Fitzgerald Published: 2026-02-20 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2602.18603v1 Corrections offer a natural modality for people to provide feedback to a robot, by (i) intervening in the robot's behavior when they believe the robot is failing (or will fail) the task objectives and (ii) modifying the robot's behavior to successfully fulfill the task. Each correction offers information on what the robot should and should not do, where the corrected behavior is more aligned with task objectives than the original behavior. Most prior work on learning from corrections involves interpreting a correction as a new demonstration (consisting of the modified robot behavior), or a preference (for the modified trajectory compared to the robot's original behavior). However, this overlooks one essential element of the correction feedback, which is the human's decision to intervene in the robot's behavior in the first place. This decision can be influenced by multiple factors including the robot's task progress, alignment with human expectations, dynamics, motion legibility, and optimality. In this work, we investigate whether the timing of this decision can offer a useful signal for inferring these task-relevant influences. In particular, we investigate three potential applications for this learning signal: (1) identifying features of a robot's motion that may prompt people to correct it, (2) quickly inferring the final goal of a human's correction based on the timing and initial direction of their correction motion, and (3) learning more precise constraints for task objectives. Our results indicate that correction timing results in improved learning for the first two of these applications. Overall, our work provides new insights on the value of correction timing as a signal for robot learning. --- ### MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs Authors: Ziqiao Shang, Ling-Yue Ge, Zian Xu, Zi-Jian Cheng, Shi-Yu Tian, Zhenyu Huang, Wenbo Fu, Weiming Wu, Yang Chen, Xiangwen Zhang, Yulan Hu, Bin Liu et al. Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18600v5 Systematically evaluating Multimodal Large Language Models (MLLMs) is essential for advancing Artificial General Intelligence (AGI). Yet existing benchmarks remain inadequate for rigorously measuring their reasoning capabilities under multi-criteria constraints. To address this gap, we introduce MapTab, a multimodal benchmark designed to assess holistic multi-criteria reasoning in MLLMs through route-planning tasks. MapTab requires models to perceive and ground visual information from map images while integrating route attributes, such as Time and Price, from structured tables. It covers two scenarios: Metromap, spanning metro networks in 160 cities across 52 countries, and Travelmap, featuring 168 representative tourist attractions from 19 countries. Overall, MapTab includes 328 images, 196,800 route-planning queries, and 3,936 QA queries, incorporating four key criteria: Time, Price, Comfort, and Reliability. Extensive evaluations of 21 representative MLLMs show that current models still struggle with multicriteria multimodal reasoning. Notably, when visual perception is unreliable, multimodal reasoning can even underperform unimodal approaches. MapTab therefore offers a challenging and realistic testbed for systematically evaluating and advancing MLLMs across core perception, integration, numerical comparison, and route planning capabilities. --- ### Ensemble Prediction of Task Affinity for Efficient Multi-Task Learning Authors: Afiya Ayman, Ayan Mukhopadhyay, Aron Laszka Published: 2026-02-20 Categories: cs.LG arXiv: https://arxiv.org/abs/2602.18591v1 A fundamental problem in multi-task learning (MTL) is identifying groups of tasks that should be learned together. Since training MTL models for all possible combinations of tasks is prohibitively expensive for large task sets, a crucial component of efficient and effective task grouping is predicting whether a group of tasks would benefit from learning together, measured as per-task performance gain over single-task learning. In this paper, we propose ETAP (Ensemble Task Affinity Predictor), a scalable framework that integrates principled and data-driven estimators to predict MTL performance gains. First, we consider the gradient-based updates of shared parameters in an MTL model to measure the affinity between a pair of tasks as the similarity between the parameter updates based on these tasks. This linear estimator, which we call affinity score, naturally extends to estimating affinity within a group of tasks. Second, to refine these estimates, we train predictors that apply non-linear transformations and correct residual errors, capturing complex and non-linear task relationships. We train these predictors on a limited number of task groups for which we obtain ground-truth gain values via multi-task learning for each group. We demonstrate on benchmark datasets that ETAP improves MTL gain prediction and enables more effective task grouping, outperforming state-of-the-art baselines across diverse application domains. --- ### DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction Authors: Jiayang Shi, Daniel M. Pelt, K. Joost Batenburg Published: 2026-02-20 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.18589v1 Diffusion models have recently emerged as powerful priors for solving inverse problems. While computed tomography (CT) is theoretically a linear inverse problem, it poses many practical challenges. These include correlated noise, artifact structures, reliance on system geometry, and misaligned value ranges, which make the direct application of diffusion models more difficult than in domains like natural image generation. To systematically evaluate how diffusion models perform in this context and compare them with established reconstruction methods, we introduce DM4CT, a comprehensive benchmark for CT reconstruction. DM4CT includes datasets from both medical and industrial domains with sparse-view and noisy configurations. To explore the challenges of deploying diffusion models in practice, we additionally acquire a high-resolution CT dataset at a high-energy synchrotron facility and evaluate all methods under real experimental conditions. We benchmark ten recent diffusion-based methods alongside seven strong baselines, including model-based, unsupervised, and supervised approaches. Our analysis provides detailed insights into the behavior, strengths, and limitations of diffusion models for CT reconstruction. The real-world dataset is publicly available at zenodo.org/records/15420527, and the codebase is open-sourced at github.com/DM4CT/DM4CT. --- ### BloomNet: Exploring Single vs. Multiple Object Annotation for Flower Recognition Using YOLO Variants Authors: Safwat Nusrat, Prithwiraj Bhattacharjee Published: 2026-02-20 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2602.18585v1 Precise localization and recognition of flowers are crucial for advancing automated agriculture, particularly in plant phenotyping, crop estimation, and yield monitoring. This paper benchmarks several YOLO architectures such as YOLOv5s, YOLOv8n/s/m, and YOLOv12n for flower object detection under two annotation regimes: single-image single-bounding box (SISBB) and single-image multiple-bounding box (SIMBB). The FloralSix dataset, comprising 2,816 high-resolution photos of six different flower species, is also introduced. It is annotated for both dense (clustered) and sparse (isolated) scenarios. The models were evaluated using Precision, Recall, and Mean Average Precision (mAP) at IoU thresholds of 0.5 (mAP@0.5) and 0.5-0.95 (mAP@0.5:0.95). In SISBB, YOLOv8m (SGD) achieved the best results with Precision 0.956, Recall 0.951, mAP@0.5 0.978, and mAP@0.5:0.95 0.865, illustrating strong accuracy in detecting isolated flowers. With mAP@0.5 0.934 and mAP@0.5:0.95 0.752, YOLOv12n (SGD) outperformed the more complicated SIMBB scenario, proving robustness in dense, multi-object detection. Results show how annotation density, IoU thresholds, and model size interact: recall-optimized models perform better in crowded environments, whereas precision-oriented models perform best in sparse scenarios. In both cases, the Stochastic Gradient Descent (SGD) optimizer consistently performed better than alternatives. These density-sensitive sensors are helpful for non-destructive crop analysis, growth tracking, robotic pollination, and stress evaluation. --- ### GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry Authors: Guanghui Min, Tianhao Huang, Ke Wan, Chen Chen Published: 2026-02-20 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2602.18584v2 Targeted data selection has emerged as a crucial paradigm for efficient instruction tuning, aiming to identify a small yet influential subset of training examples for a specific target task. In practice, influence is often measured through the effect of an example on parameter updates. To make selection scalable, many approaches leverage optimizer statistics (e.g., Adam states) as an axis-aligned surrogate for update geometry (i.e., diagonal precondition), implicitly treating parameters as coordinate-wise independent. We show that this assumption breaks down in parameter-efficient fine-tuning (PEFT) methods such as LoRA. In this setting, the induced optimization geometry exhibits strong cross-parameter coupling with non-trivial off-diagonal interactions, while the task-relevant update directions are confined to a low-dimensional subspace. Motivated by this mismatch, we propose GIST (Gradient Isometric Subspace Transformation), a simple yet principled alternative that replaces axis-aligned scaling with robust subspace alignment. GIST recovers a task-specific subspace from validation gradients via singular value decomposition (SVD), projects training gradients into this coupled subspace, and scores examples by their alignment with target directions. Extensive experiments have demonstrated that GIST matches or outperforms the state-of-the-art baseline with only 0.29% of the storage and 25% of the computational time under the same selection budget. --- ### Luna-2: Scalable Single-Token Evaluation with Small Language Models Authors: Vatsal Goel, Rishon Dsouza, Nikhil Ega, Amey Ramesh Rambatla, Rob Friel, Shuai Shao, Yash Sheth Published: 2026-02-20 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2602.18583v1 Real-time guardrails require evaluation that is accurate, cheap, and fast - yet today's default, LLM-as-a-judge (LLMAJ), is slow, expensive, and operationally non-deterministic due to multi-token generation. We present Luna-2, a novel architecture that leverages decoder-only small language models (SLMs) into a deterministic evaluation model to reliably compute complex task-specific LLMAJ metrics (e.g. toxicity, hallucination, tool selection quality, etc.) at an accuracy at par or higher than LLMAJ using frontier LLMs while drastically reducing the cost and latency of computation. Each metric is implemented as a lightweight LoRA/PEFT head on top of a shared SLM backbone, enabling hundreds of specialized metrics to run concurrently on a single GPU, deployable locally next to AI systems in a privacy-preserving and latency optimizing manner. Across content safety and hallucination benchmarks, Luna-2 matches the accuracy of state-of-the-art LLM-based evaluators while reducing inference cost by over 80x and latency by over 20x. In this paper, we outline the model architecture, training methodology and report real-world empirical results on accuracy, latency, and throughput results. In production, Luna-2 is protecting 100M+ AI sessions and processing over 100B tokens per month for our customers with eval cost savings of over $30M annually. --- ### Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications Authors: Zhiqin Qian, Ryan Diaz, Sangwon Seo, Vaibhav Unhelkar Published: 2026-02-20 Categories: cs.AI, cs.CL, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2602.18582v1 When training artificial intelligence (AI) to perform tasks, humans often care not only about whether a task is completed but also how it is performed. As AI agents tackle increasingly complex tasks, aligning their behavior with human-provided specifications becomes critical for responsible AI deployment. Reward design provides a direct channel for such alignment by translating human expectations into reward functions that guide reinforcement learning (RL). However, existing methods are often too limited to capture nuanced human preferences that arise in long-horizon tasks. Hence, we introduce Hierarchical Reward Design from Language (HRDL): a problem formulation that extends classical reward design to encode richer behavioral specifications for hierarchical RL agents. We further propose Language to Hierarchical Rewards (L2HR) as a solution to HRDL. Experiments show that AI agents trained with rewards designed via L2HR not only complete tasks effectively but also better adhere to human specifications. Together, HRDL and L2HR advance the research on human-aligned AI agents. --- ### Learning Beyond Optimization: Stress-Gated Dynamical Regime Regulation in Autonomous Systems Authors: Sheng Ran Published: 2026-02-20 Categories: cs.LG, cond-mat.stat-mech, physics.soc-ph arXiv: https://arxiv.org/abs/2602.18581v1 Despite their apparent diversity, modern machine learning methods can be reduced to a remarkably simple core principle: learning is achieved by continuously optimizing parameters to minimize or maximize a scalar objective function. This paradigm has been extraordinarily successful for well-defined tasks where goals are fixed and evaluation criteria are explicit. However, if artificial systems are to move toward true autonomy-operating over long horizons and across evolving contexts-objectives may become ill-defined, shifting, or entirely absent. In such settings, a fundamental question emerges: in the absence of an explicit objective function, how can a system determine whether its ongoing internal dynamics are productive or pathological? And how should it regulate structural change without external supervision? In this work, we propose a dynamical framework for learning without an explicit objective. Instead of minimizing external error signals, the system evaluates the intrinsic health of its own internal dynamics and regulates structural plasticity accordingly. We introduce a two-timescale architecture that separates fast state evolution from slow structural adaptation, coupled through an internally generated stress variable that accumulates evidence of persistent dynamical dysfunction. Structural modification is then triggered not continuously, but as a state-dependent event. Through a minimal toy model, we demonstrate that this stress-regulated mechanism produces temporally segmented, self-organized learning episodes without reliance on externally defined goals. Our results suggest a possible route toward autonomous learning systems capable of self-assessment and internally regulated structural reorganization. --- ### Multiclass Calibration Assessment and Recalibration of Probability Predictions via the Linear Log Odds Calibration Function Authors: Amy Vennos, Xin Xing, Christopher T. Franck Published: 2026-02-20 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2602.18573v1 Machine-generated probability predictions are essential in modern classification tasks such as image classification. A model is well calibrated when its predicted probabilities correspond to observed event frequencies. Despite the need for multicategory recalibration methods, existing methods are limited to (i) comparing calibration between two or more models rather than directly assessing the calibration of a single model, (ii) requiring under-the-hood model access, e.g., accessing logit-scale predictions within the layers of a neural network, and (iii) providing output which is difficult for human analysts to understand. To overcome (i)-(iii), we propose Multicategory Linear Log Odds (MCLLO) recalibration, which (i) includes a likelihood ratio hypothesis test to assess calibration, (ii) does not require under-the-hood access to models and is thus applicable on a wide range of classification problems, and (iii) can be easily interpreted. We demonstrate the effectiveness of the MCLLO method through simulations and three real-world case studies involving image classification via convolutional neural network, obesity analysis via random forest, and ecology via regression modeling. We compare MCLLO to four comparator recalibration techniques utilizing both our hypothesis test and the existing calibration metric Expected Calibration Error to show that our method works well alone and in concert with other methods. --- ### Sub-City Real Estate Price Index Forecasting at Weekly Horizons Using Satellite Radar and News Sentiment Authors: Baris Arat, Hasan Fehmi Ates, Emre Sefer Published: 2026-02-20 Categories: cs.LG, q-fin.ST arXiv: https://arxiv.org/abs/2602.18572v1 Reliable real estate price indicators are typically published at city level and low frequency, limiting their use for neighborhood-scale monitoring and long-horizon planning. We study whether sub-city price indices can be forecasted at weekly frequency by combining physical development signals from satellite radar with market narratives from news text. Using over 350,000 transactions from Dubai Land Department (2015-2025), we construct weekly price indices for 19 sub-city regions and evaluate forecasts from 2 to 34 weeks ahead. Our framework fuses regional transaction history with Sentinel-1 SAR backscatter, news sentiment combining lexical tone and semantic embeddings, and macroeconomic context. Results are strongly horizon dependent: at horizons up to 10 weeks, price history alone matches multimodal configurations, but beyond 14 weeks sentiment and SAR become critical. At long horizons (26-34 weeks), the full multimodal model reduces mean absolute error from 4.48 to 2.93 (35% reduction), with gains statistically significant across regions. Nonparametric learners consistently outperform deep architectures in this data regime. These findings establish benchmarks for weekly sub-city index forecasting and demonstrate that remote sensing and news sentiment materially improve predictability at strategically relevant horizons. --- ### Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs? Authors: Spandan Garg, Yufan Huang Published: 2026-02-20 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2602.18571v2 While significant progress has been made in automating various aspects of software development through coding agents, there is still significant room for improvement in their bug fixing capabilities. Debugging and investigation of runtime behavior remains largely a manual, developer-driven process. Popular coding agents typically rely on either static analysis of the code or iterative test-fix cycles, which is akin to trial and error debugging. We posit that there is a wealth of rich runtime information that developers routinely access while debugging code, which agents are currently deprived of due to design limitations. Despite how prevalent debuggers are in modern IDEs and command-line tools, they have surprisingly not made their way into coding agents. In this work, we introduce Debug2Fix, a novel framework that incorporates interactive debugging as a core component of a software engineering agent via a subagent architecture. We incorporate debuggers for Java and Python into our agent framework and evaluate against GitBug-Java and SWE-Bench-Live and achieve >20% improvement in performance compared to the baseline for certain models. Furthermore, using our framework, we're able to make weaker models like GPT-5 and Claude Haiku 4.5 match or exceed the performances of stronger models like Claude Sonnet 4.5, showing that better tool design is often just as important as switching to a more expensive model. Finally, we conduct systematic ablations demonstrating the importance of both the subagent architecture and debugger integration. --- ### RPU -- A Reasoning Processing Unit Authors: Matthew Adiletta, Gu-Yeon Wei, David Brooks Published: 2026-02-20 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2602.18568v2 Large language model (LLM) inference performance is increasingly bottlenecked by the memory wall. While GPUs continue to scale raw compute throughput, they struggle to deliver scalable performance for memory bandwidth bound workloads. This challenge is amplified by emerging reasoning LLM applications, where long output sequences, low arithmetic intensity, and tight latency constraints demand significantly higher memory bandwidth. As a result, system utilization drops and energy per inference rises, highlighting the need for an optimized system architecture for scalable memory bandwidth. To address these challenges we present the Reasoning Processing Unit (RPU), a chiplet-based architecture designed to address the challenges of the modern memory wall. RPU introduces: (1) A Capacity-Optimized High-Bandwidth Memory (HBM-CO) that trades capacity for lower energy and cost; (2) a scalable chiplet architecture featuring a bandwidth-first power and area provisioning design; and (3) a decoupled microarchitecture that separates memory, compute, and communication pipelines to sustain high bandwidth utilization. Simulation results show that RPU performs up to 45.3x lower latency and 18.6x higher throughput over an H100 system at ISO-TDP on Llama3-405B. --- ### From Static Spectra to Operando Infrared Dynamics: Physics Informed Flow Modeling and a Benchmark Authors: Shuquan Ye, Ben Fei, Hongbin Xu, Jiaying Lin, Wanli Ouyang Published: 2026-02-20 Categories: physics.chem-ph, cs.AI arXiv: https://arxiv.org/abs/2602.18551v1 The Solid Electrolyte Interphase (SEI) is critical to the performance of lithium-ion batteries, yet its analysis via Operando Infrared (IR) spectroscopy remains experimentally complex and expensive, which limits its accessibility for standard research facilities. To overcome this bottleneck, we formulate a novel task, Operando IR Prediction, which aims to forecast the time-resolved evolution of spectral ``fingerprints'' from a single static spectrum. To facilitate this, we introduce OpIRSpec-7K, the first large-scale operando dataset comprising 7,118 high-quality samples across 10 distinct battery systems, alongside OpIRBench, a comprehensive evaluation benchmark with carefully designed protocols. Addressing the limitations of standard spectrum, video, and sequence models in capturing voltage-driven chemical dynamics and complex composition, we propose Aligned Bi-stream Chemical Constraint (ABCC), an end-to-end physics-aware framework. It reformulates MeanFlow and introduces a novel Chemical Flow to explicitly model reaction trajectories, employs a two-stream disentanglement mechanism for solvent-SEI separation, and enforces physics and spectrum constraints such as mass conservation and peak shifts. ABCC significantly outperforms state-of-the-art static, sequential, and generative baselines. ABCC even generalizes to unseen systems and enables interpretable downstream recovery of SEI formation pathways, supporting AI-driven electrochemical discovery. ---