# Research Papers — 2026-03 · bundle page 204 of 243 > Full-text markdown of papers #10151–10200 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/204 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/203.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/205.md) ### Thinking with Spatial Code for Physical-World Video Reasoning Authors: Jieneng Chen, Wenxin Ma, Ruisheng Yuan, Yunzhi Zhang, Jiajun Wu, Alan Yuille Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.05591v1 We introduce Thinking with Spatial Code, a framework that transforms RGB video into explicit, temporally coherent 3D representations for physical-world visual question answering. We highlight the empirical finding that our proposed spatial encoder can parse videos into structured spatial code with explicit 3D oriented bounding boxes and semantic labels, enabling large language models (LLMs) to reason directly over explicit spatial variables. Specifically, we propose the spatial encoder that encodes image and geometric features by unifying 6D object parsing and tracking backbones with geometric prediction, and we further finetuning LLMs with reinforcement learning using a spatial rubric reward that encourages perspective-aware, geometrically grounded inference. As a result, our model outperforms proprietary vision-language models on VSI-Bench, setting a new state-of-the-art. Code is available at https://github.com/Beckschen/spatialcode. --- ### Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models Authors: Ivan Luiz De Moura Matos, Abdel Djalil Sad Saoud, Ekaterina Iakovleva, Vito Paolo Pastore, Enzo Tartaglione Published: 2026-03-05 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2603.05582v2 The issue of algorithmic biases in deep learning has led to the development of various debiasing techniques, many of which perform complex training procedures or dataset manipulation. However, an intriguing question arises: is it possible to extract fair and bias-agnostic subnetworks from standard vanilla-trained models without relying on additional data, such as unbiased training set? In this work, we introduce Bias-Invariant Subnetwork Extraction (BISE), a learning strategy that identifies and isolates "bias-free" subnetworks that already exist within conventionally trained models, without retraining or finetuning the original parameters. Our approach demonstrates that such subnetworks can be extracted via pruning and can operate without modification, effectively relying less on biased features and maintaining robust performance. Our findings contribute towards efficient bias mitigation through structural adaptation of pre-trained neural networks via parameter removal, as opposed to costly strategies that are either data-centric or involve (re)training all model parameters. Extensive experiments on common benchmarks show the advantages of our approach in terms of the performance and computational efficiency of the resulting debiased model. --- ### Spatiotemporal Heterogeneity of AI-Driven Traffic Flow Patterns and Land Use Interaction: A GeoAI-Based Analysis of Multimodal Urban Mobility Authors: Olaf Yunus Laitinen Imanov Published: 2026-03-05 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2603.05581v2 Urban traffic flow is governed by the complex, nonlinear interaction between land use configuration and spatiotemporally heterogeneous mobility demand. Conventional global regression and time-series models cannot simultaneously capture these multi-scale dynamics across multiple travel modes. This study proposes a GeoAI Hybrid analytical framework that sequentially integrates Multiscale Geographically Weighted Regression (MGWR), Random Forest (RF), and Spatio-Temporal Graph Convolutional Networks (ST-GCN) to model the spatiotemporal heterogeneity of traffic flow patterns and their interaction with land use across three mobility modes: motor vehicle, public transit, and active transport. Applying the framework to an empirically calibrated dataset of 350 traffic analysis zones across six cities spanning two contrasting urban morphologies, four key findings emerge: (i) the GeoAI Hybrid achieves a root mean squared error (RMSE) of 0.119 and an R^2 of 0.891, outperforming all benchmarks by 23-62%; (ii) SHAP analysis identifies land use mix as the strongest predictor for motor vehicle flows and transit stop density as the strongest predictor for public transit; (iii) DBSCAN clustering identifies five functionally distinct urban traffic typologies with a silhouette score of 0.71, and GeoAI Hybrid residuals exhibit Moran's I=0.218 (p<0.001), a 72% reduction relative to OLS baselines; and (iv) cross-city transfer experiments reveal moderate within-cluster transferability (R^2>=0.78) and limited cross-cluster generalisability, underscoring the primacy of urban morphological context. The framework offers planners and transportation engineers an interpretable, scalable toolkit for evidence-based multimodal mobility management and land use policy design. --- ### Spatiotemporal Heterogeneity of AI-Driven Traffic Flow Patterns and Land Use Interaction: A GeoAI-Based Analysis of Multimodal Urban Mobility Authors: Olaf Yunus Laitinen Imanov Published: 2026-03-05 Categories: cs.LG, cs.AI, eess.SP arXiv: https://arxiv.org/abs/2603.05581v1 Urban traffic flow is governed by the complex, nonlinear interaction between land use configuration and spatiotemporally heterogeneous mobility demand. Conventional global regression and time-series models cannot simultaneously capture these multi-scale dynamics across multiple travel modes. This study proposes a GeoAI Hybrid analytical framework that sequentially integrates Multiscale Geographically Weighted Regression (MGWR), Random Forest (RF), and Spatio-Temporal Graph Convolutional Networks (ST-GCN) to model the spatiotemporal heterogeneity of traffic flow patterns and their interaction with land use across three mobility modes: motor vehicle, public transit, and active transport. Applying the framework to an empirically calibrated dataset of 350 traffic analysis zones across six cities spanning two contrasting urban morphologies, four key findings emerge: (i) the GeoAI Hybrid achieves a root mean squared error (RMSE) of 0.119 and an R^2 of 0.891, outperforming all benchmarks by 23-62%; (ii) SHAP analysis identifies land use mix as the strongest predictor for motor vehicle flows and transit stop density as the strongest predictor for public transit; (iii) DBSCAN clustering identifies five functionally distinct urban traffic typologies with a silhouette score of 0.71, and GeoAI Hybrid residuals exhibit Moran's I=0.218 (p<0.001), a 72% reduction relative to OLS baselines; and (iv) cross-city transfer experiments reveal moderate within-cluster transferability (R^2>=0.78) and limited cross-cluster generalisability, underscoring the primacy of urban morphological context. The framework offers planners and transportation engineers an interpretable, scalable toolkit for evidence-based multimodal mobility management and land use policy design. --- ### A Novel Hybrid Heuristic-Reinforcement Learning Optimization Approach for a Class of Railcar Shunting Problems Authors: Ruonan Zhao, Joseph Geunes Published: 2026-03-05 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2603.05579v1 Railcar shunting is a core planning task in freight railyards, where yard planners need to disassemble and reassemble groups of railcars to form outbound trains. Classification tracks with access from one side only can be considered as stack structures, where railcars are added and removed from only one end, leading to a last-in-first-out (LIFO) retrieval order. In contrast, two-sided tracks function like queue structures, allowing railcars to be added from one end and removed from the opposite end, following a first-in-first-out (FIFO) order. We consider a problem requiring assembly of multiple outbound trains using two locomotives in a railyard with two-sided classification track access. To address this combinatorially challenging problem class, we decompose the problem into two subproblems, each with one-sided classification track access and a locomotive on each side. We present a novel Hybrid Heuristic-Reinforcement Learning (HHRL) framework that integrates railway-specific heuristic solution approaches with a reinforcement learning method, specifically Q-learning. The proposed framework leverages methods to decrease the state-action space and guide exploration during reinforcement learning. The results of a series of numerical experiments demonstrate the efficiency and quality of the HHRL algorithm in both one-sided access, single-locomotive problems and two-sided access, two-locomotive problems. --- ### Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent Authors: Bowei Xia, Mengkang Hu, Shijian Wang, Jiarui Jin, Wenxiang Jiao, Yuan Lu, Kexin Li, Ping Luo Published: 2026-03-05 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.05578v1 Research on self-evolving language agents has accelerated, drawing increasing attention to their ability to create, adapt, and maintain tools from task requirements. However, existing benchmarks predominantly rely on predefined specifications, which limits scalability and hinders truly autonomous evolution. While recent studies attempt to dynamically generate tools, they primarily emphasize downstream performance, resulting in a "black-box" evaluation that makes it difficult to attribute failures to specific causes. To address this, we propose Tool-Genesis, a diagnostic benchmark designed to quantify agent capabilities across multiple dimensions, including interface compliance, functional correctness, and downstream utility. Tool-Genesis evaluates whether agents can construct task-relevant tools solely from abstract requirements (without preset specifications) and use them to solve realistic problems. Crucially, we find that even state-of-the-art models struggle to produce precise tool interfaces or executable logic in a one-shot setting. These minor initial flaws are amplified through the pipeline, leading to a sharp degradation in downstream metrics. We hope Tool-Genesis will guide future research toward training and steering models to synthesize persistent, general-purpose tools that better address real-world challenges. --- ### Koopman Regularized Deep Speech Disentanglement for Speaker Verification Authors: Nikos Chazaridis, Mohammad Belal, Rafael Mestre, Timothy J. Norman, Christine Evers Published: 2026-03-05 Categories: cs.SD, cs.LG arXiv: https://arxiv.org/abs/2603.05577v1 Human speech contains both linguistic content and speaker dependent characteristics making speaker verification a key technology in identity critical applications. Modern deep learning speaker verification systems aim to learn speaker representations that are invariant to semantic content and nuisance factors such as ambient noise. However, many existing approaches depend on labelled data, textual supervision or large pretrained models as feature extractors, limiting scalability and practical deployment, raising sustainability concerns. We propose Deep Koopman Speech Disentanglement Autoencoder (DKSD-AE), a structured autoencoder that combines a novel multi-step Koopman operator learning module with instance normalization to disentangle speaker and content dynamics. Quantitative experiments across multiple datasets demonstrate that DKSD-AE achieves improved or competitive speaker verification performance compared to state-of-the-art baselines while maintaining high content EER, confirming effective disentanglement. These results are obtained with substantially fewer parameters and without textual supervision. Moreover, performance remains stable under increased evaluation scale, highlighting representation robustness and generalization. Our findings suggest that Koopman-based temporal modelling, when combined with instance normalization, provides an efficient and principled solution for speaker-focused representation learning. --- ### Prediction-Powered Conditional Inference Authors: Yang Sui, Jin Zhou, Hua Zhou, Xiaowu Dai Published: 2026-03-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.05575v2 We study prediction-powered conditional inference in the setting where labeled data are scarce, unlabeled covariates are abundant, and a black-box machine-learning predictor is available. The goal is to perform statistical inference on conditional functionals evaluated at a fixed target point, such as conditional means, without imposing a parametric model for the conditional relationship. Our approach combines localization with prediction-based variance reduction. First, we introduce an RKHS localization method that learns a data-adaptive weight from covariates and reformulates the target conditional moment at the target point as a weighted unconditional moment. Second, we incorporate machine-learning predictions through a correction-based decomposition of this localized moment, yielding a prediction-powered estimator and confidence interval that reduce variance when the predictor is informative while preserving validity regardless of predictor accuracy. We establish nonasymptotic error bounds and, in the abundant-unlabeled regime, minimax-optimal convergence rates for the resulting estimator, prove pointwise asymptotic normality with consistent variance estimation, and provide an explicit variance decomposition that characterizes how machine-learning predictions and unlabeled covariates improve statistical efficiency. Numerical experiments on simulated and real datasets demonstrate valid conditional coverage and substantially sharper confidence intervals than alternative methods. --- ### Prediction-Powered Conditional Inference Authors: Yang Sui, Jin Zhou, Hua Zhou, Xiaowu Dai Published: 2026-03-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.05575v1 We study prediction-powered conditional inference in the setting where labeled data are scarce, unlabeled covariates are abundant, and a black-box machine-learning predictor is available. The goal is to perform statistical inference on conditional functionals evaluated at a fixed test point, such as conditional means, without imposing a parametric model for the conditional relationship. Our approach combines localization with prediction-based variance reduction. First, we introduce a reproducing kernel-based localization method that learns a data-adaptive weight function from covariates and reformulates the target conditional moment at the test point as a weighted unconditional moment. Second, we incorporate machine-learning predictions through a correction-based decomposition of this localized moment, yielding a prediction-powered estimator and confidence interval that reduce variance when the predictor is informative while preserving validity regardless of predictor accuracy. We establish nonasymptotic error bounds and minimax-optimal convergence rates for the resulting estimator, prove pointwise asymptotic normality with consistent variance estimation, and provide an explicit variance decomposition that characterizes how machine-learning predictions and unlabeled covariates improve statistical efficiency. Numerical experiments on simulated and real datasets demonstrate valid conditional coverage and substantially sharper confidence intervals than alternative methods. --- ### PRISM: Personalized Refinement of Imitation Skills for Manipulation via Human Instructions Authors: Arnau Boix-Granell, Alberto San-Miguel-Tello, Magí Dalmau-Moreno, Néstor García Published: 2026-03-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.05574v1 This paper presents PRISM: an instruction-conditioned refinement method for imitation policies in robotic manipulation. This approach bridges Imitation Learning (IL) and Reinforcement Learning (RL) frameworks into a seamless pipeline, such that an imitation policy on a broad generic task, generated from a set of user-guided demonstrations, can be refined through reinforcement to generate new unseen fine-grain behaviours. The refinement process follows the Eureka paradigm, where reward functions for RL are iteratively generated from an initial natural-language task description. Presented approach, builds on top of this mechanism to adapt a refined IL policy of a generic task to new goal configurations and the introduction of constraints by adding also human feedback correction on intermediate rollouts, enabling policy reusability and therefore data efficiency. Results for a pick-and-place task in a simulated scenario show that proposed method outperforms policies without human feedback, improving robustness on deployment and reducing computational burden. --- ### Why Depth Matters in Parallelizable Sequence Models: A Lie Algebraic View Authors: Gyuryang Heo, Timothy Ngotiaoco, Kazuki Irie, Samuel J. Gershman, Bernardo L. Sabatini Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.05573v2 Scalable sequence models, such as Transformer variants and structured state-space models, often trade expressivity power for sequence-level parallelism, which enables efficient training. Here we examine the bounds on error and how error scales when models operate outside of their expressivity regimes using a Lie-algebraic control perspective. Our theory formulates a correspondence between the depth of a sequence model and the tower of Lie algebra extensions. Echoing recent theoretical studies, we characterize the Lie-algebraic class of constant-depth sequence models and their corresponding expressivity bounds. Furthermore, we analytically derive an approximation error bound and show that error diminishes exponentially as the depth increases, consistent with the strong empirical performance of these models. We validate our theoretical predictions using experiments on symbolic word and continuous-valued state-tracking problems. --- ### Machine Learning for analysis of Multiple Sclerosis cross-tissue bulk and single-cell transcriptomics data Authors: Francesco Massafra, Samuele Punzo, Silvia Giulia Galfré, Alessandro Maglione, Simone Pernice, Stefano Forti, Simona Rolla, Marco Beccuti, Marinella Clerico, Corrado Priami, Alina Sîrbu Published: 2026-03-05 Categories: q-bio.GN, cs.LG arXiv: https://arxiv.org/abs/2603.05572v1 Multiple Sclerosis (MS) is a chronic autoimmune disease of the central nervous system whose molecular mechanisms remain incompletely understood. In this study, we developed an end-to-end machine learning pipeline to analyze transcriptomic data from peripheral blood mononuclear cells and cerebrospinal fluid, integrating both bulk microarray and single-cell RNA sequencing datasets (concentrating on CD4+ and B-cells). After rigorous preprocessing, batch correction, and gene declustering, XGBoost classifiers were trained to distinguish MS patients from healthy controls. Explainable AI tools, namely SHapley Additive exPlanations (SHAP), were employed to identify key genes driving classification, and results were compared with Differential Expression Analysis (DEA). SHAP-prioritized genes were further investigated through interaction networks and pathway enrichment analyses. The models achieved strong performance, particularly in CSF B-cells (AUC=0.94) and microarray (AUC=0.86). SHAP gene selection proved to be complementary to classical DEA. Gene clusters identified across multiple datasets highlighted immune activation, non-canonical immune checkpoints (ITK, CLEC2D, KLRG1, CEACAM1), ribosomal and translational programs, ubiquitin-proteasome regulation, lipid trafficking, and Epstein-Barr virus-related pathways. Our integrative and explainable framework reveals complementary insights beyond conventional analysis and provides novel mechanistic hypotheses and potential biomarkers for MS pathogenesis. --- ### CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain Authors: Hung Nguyen, Hans Moen, Pekka Marttinen Published: 2026-03-05 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.05569v2 Extracting insights from Electronic Health Record (EHR) databases often requires SQL expertise, creating a barrier for clinical decision-making and research. A promising approach is to use Large Language Models (LLMs) to translate natural language questions into SQL through Retrieval-Augmented Generation (RAG), where relevant question-SQL examples are retrieved to generate new queries via few-shot learning. However, adapting this method to the medical domain is non-trivial, as effective retrieval requires examples that align with both the logical structure of the question and its referenced entities (e.g., drug names, procedure titles). Standard single-step RAG struggles to optimize both aspects simultaneously and often relies on near-exact matches to generalize effectively. This issue is especially severe in healthcare, as questions often contain noisy and inconsistent medical jargon. To address this, we present CBR-to-SQL, a framework inspired by Case-based Reasoning theory that decomposes RAG's single-step retrieval into two explicit stages: one that focuses on retrieving structurally relevant examples, and one that aligns entities with the target database schema. Evaluated on two clinical benchmarks, CBR-to-SQL achieves competitive accuracies compared to fine-tuned methods. More importantly, it demonstrates considerably higher sample efficiency and robustness than the standard RAG approach, particularly under data scarcity and retrieval perturbations. --- ### Learning Optimal Distributionally Robust Individualized Treatment Rules Integrating Multi-Source Data Authors: Wenhai Cui, Wen Su, Xingqiu Zhao Published: 2026-03-05 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.05568v1 Integrative analysis of multiple datasets for estimating optimal individualized treatment rules (ITRs) can enhance decision efficiency. A central challenge is posterior shift, wherein the conditional distribution of potential outcomes given covariates differs between source and target populations. We propose a prior information-based distributionally robust ITR (PDRO-ITR) that maximizes the worst-case policy value over a covariate-dependent distributional uncertainty set, ensuring robust performance under posterior shift. The uncertainty set is constructed as an individualized combination of source distributions, with weights combining prior source-membership probabilities and deviation terms constrained to the probability simplex to accommodate posterior shift. We derive a closed-form solution for the PDRO-ITR and develop an adaptive procedure to tune the uncertainty level. We establish risk bounds for the PDRO-ITR estimator, which guarantees robust performance under the worst case. Extensive simulations and two real-data applications demonstrate that the proposed method achieves superior performance compared to existing approaches. --- ### FuseDiff: Symmetry-Preserving Joint Diffusion for Dual-Target Structure-Based Drug Design Authors: Jianliang Wu, Anjie Qiao, Zhen Wang, Zhewei Wei, Sheng Chen Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.05567v2 Dual-target structure-based drug design aims to generate a single ligand together with two pocket-specific binding poses, each compatible with a corresponding target pocket, enabling polypharmacological therapies with improved efficacy and reduced resistance. Existing approaches typically rely on staged pipelines, which either decouple the two poses via conditional-independence assumptions or enforce overly rigid correlations, and therefore fail to jointly generate two target-specific binding modes. To address this, we propose FuseDiff, an end-to-end diffusion model that jointly generates a ligand molecular graph and two pocket-specific binding poses conditioned on both pockets. FuseDiff features a message-passing backbone with Dual-target Local Context Fusion (DLCF), which fuses each ligand atom's local context from both pockets to enable expressive joint modeling while preserving the desired symmetries. Together with explicit bond generation, FuseDiff enforces topological consistency across the two poses under a shared graph while allowing target-specific geometric adaptation in each pocket. To support principled training and evaluation, we derive a dual-target training set and use an independent held-out test set for evaluation. Experiments on the benchmark and a real-world dual-target system show that FuseDiff achieves state-of-the-art docking performance and enables the first systematic assessment of dual-target pose quality prior to docking-based pose search. --- ### FuseDiff: Symmetry-Preserving Joint Diffusion for Dual-Target Structure-Based Drug Design Authors: Jianliang Wu, Anjie Qiao, Zhen Wang, Zhewei Wei, Sheng Chen Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.05567v1 Dual-target structure-based drug design aims to generate a single ligand together with two pocket-specific binding poses, each compatible with a corresponding target pocket, enabling polypharmacological therapies with improved efficacy and reduced resistance. Existing approaches typically rely on staged pipelines, which either decouple the two poses via conditional-independence assumptions or enforce overly rigid correlations, and therefore fail to jointly generate two target-specific binding modes. To address this, we propose FuseDiff, an end-to-end diffusion model that jointly generates a ligand molecular graph and two pocket-specific binding poses conditioned on both pockets. FuseDiff features a message-passing backbone with Dual-target Local Context Fusion (DLCF), which fuses each ligand atom's local context from both pockets to enable expressive joint modeling while preserving the desired symmetries. Together with explicit bond generation, FuseDiff enforces topological consistency across the two poses under a shared graph while allowing target-specific geometric adaptation in each pocket. To support principled training and evaluation, we derive a dual-target training set and use an independent held-out test set for evaluation. Experiments on the benchmark and a real-world dual-target system show that FuseDiff achieves state-of-the-art docking performance and enables the first systematic assessment of dual-target pose quality prior to docking-based pose search. --- ### Aligning the True Semantics: Constrained Decoupling and Distribution Sampling for Cross-Modal Alignment Authors: Xiang Ma, Lexin Fang, Litian Xu, Caiming Zhang Published: 2026-03-05 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2603.05566v1 Cross-modal alignment is a crucial task in multimodal learning aimed at achieving semantic consistency between vision and language. This requires that image-text pairs exhibit similar semantics. Traditional algorithms pursue embedding consistency to achieve semantic consistency, ignoring the non-semantic information present in the embedding. An intuitive approach is to decouple the embeddings into semantic and modality components, aligning only the semantic component. However, this introduces two main challenges: (1) There is no established standard for distinguishing semantic and modal information. (2) The modality gap can cause semantic alignment deviation or information loss. To align the true semantics, we propose a novel cross-modal alignment algorithm via \textbf{C}onstrained \textbf{D}ecoupling and \textbf{D}istribution \textbf{S}ampling (CDDS). Specifically, (1) A dual-path UNet is introduced to adaptively decouple the embeddings, applying multiple constraints to ensure effective separation. (2) A distribution sampling method is proposed to bridge the modality gap, ensuring the rationality of the alignment process. Extensive experiments on various benchmarks and model backbones demonstrate the superiority of CDDS, outperforming state-of-the-art methods by 6.6\% to 14.2\%. --- ### When AI Levels the Playing Field: Skill Homogenization, Asset Concentration, and Two Regimes of Inequality Authors: Xupeng Chen, Shuchen Meng Published: 2026-03-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.05565v2 Generative AI compresses within-task skill differences while shifting economic value toward concentrated complementary assets, creating an apparent paradox: the technology that equalizes individual performance may widen aggregate inequality. We formalize this tension in a task-based model with endogenous education, employer screening, and heterogeneous firms. The model yields two regimes whose boundary depends on AI's technology structure (proprietary vs. commodity) and labor market institutions (rent-sharing elasticity, asset concentration). A scenario analysis via Method of Simulated Moments, matching six empirical targets, disciplines the model's quantitative magnitudes; a sensitivity decomposition reveals that the five non-$Δ$Gini moments identify mechanism rates but not the aggregate sign, which at the calibrated parameters is pinned by $m_6$ and $ξ$, while AI's technology structure ($η_1$ vs. $η_0$) independently crosses the boundary. The contribution is the mechanism -- not a verdict on the sign. Occupation-level regressions using BLS OEWS data (2019--2023) illustrate why such data cannot test the model's task-level predictions. The predictions are testable with within-occupation, within-task panel data that do not yet exist at scale. --- ### Model Change for Description Logic Concepts Authors: Ana Ozaki, Jandson S. Ribeiro Published: 2026-03-05 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2603.05562v1 We consider the problem of modifying a description logic concept in light of models represented as pointed interpretations. We call this setting model change, and distinguish three main kinds of changes: eviction, which consists of only removing models; reception, which incorporates models; and revision, which combines removal with incorporation of models in a single operation. We introduce a formal notion of revision and argue that it does not reduce to a simple combination of eviction and reception, contrary to intuition. We provide positive and negative results on the compatibility of eviction and reception for EL and ALC description logic concepts and on the compatibility of revision for ALC concepts. --- ### Towards Efficient and Stable Ocean State Forecasting: A Continuous-Time Koopman Approach Authors: Rares Grozavescu, Pengyu Zhang, Mark Girolami, Etienne Meunier Published: 2026-03-05 Categories: cs.LG, cs.AI, physics.app-ph, physics.comp-ph, physics.geo-ph arXiv: https://arxiv.org/abs/2603.05560v2 We investigate the Continuous-Time Koopman Autoencoder (CT-KAE) as a lightweight surrogate model for long-horizon ocean state forecasting in a two-layer quasi-geostrophic (QG) system. By projecting nonlinear dynamics into a latent space governed by a linear ordinary differential equation, the model enforces structured and interpretable temporal evolution while enabling temporally resolution-invariant forecasting via a matrix exponential formulation. Across 2083-day rollouts, CT-KAE exhibits bounded error growth and stable large-scale statistics, in contrast to autoregressive Transformer baselines which exhibit gradual error amplification and energy drift over long rollouts. While fine-scale turbulent structures are partially dissipated, bulk energy spectra, enstrophy evolution, and autocorrelation structure remain consistent over long horizons. The model achieves orders-of-magnitude faster inference compared to the numerical solver, suggesting that continuous-time Koopman surrogates offer a promising backbone for efficient and stable physical-machine learning climate models. --- ### Autocorrelation effects in a stochastic-process model for solving two-armed bandit problems Authors: Tomoki Yamagami, Mikio Hasegawa, Takatomo Mihana, Ryoichi Horisaki, Atsushi Uchida Published: 2026-03-05 Categories: cs.LG, cs.ET, math.PR, physics.optics arXiv: https://arxiv.org/abs/2603.05559v2 Decision makers exploiting photonic chaotic dynamics obtained by semiconductor lasers provide an ultrafast approach to solving multi-armed bandit problems by using a temporal optical signal as the driving source for sequential decisions. In such systems, the sampling interval of the chaotic waveform shapes the temporal correlation of the resulting time series, and experiments have reported that decision accuracy depends strongly on this autocorrelation property. However, it remains unclear whether the benefit of autocorrelation can be explained by a minimal mathematical model. Here, we analyze a stochastic-process model for solving the two-armed bandit problem based on time series, where the threshold and a two-valued Markov signal evolve jointly. Numerical results reveal an environment-dependent structure: negative (positive) autocorrelation is optimal in reward-rich (reward-poor) environments. These findings show that negative autocorrelation of the time series is advantageous when the sum of the winning probabilities is more than one, whereas positive autocorrelation is useful when the sum of the winning probabilities is less than one. Moreover, the performance is independent of autocorrelation if the sum of the winning probabilities equals one, which is mathematically clarified. This study paves the way for solving the two-armed bandit problems for reinforcement learning applications in wireless communications and robotics. --- ### IntSeqBERT: Learning Arithmetic Structure in OEIS via Modulo-Spectrum Embeddings Authors: Kazuhisa Nakasho Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.05556v2 Integer sequences in the OEIS span values from single-digit constants to astronomical factorials and exponentials, making prediction challenging for standard tokenised models that cannot handle out-of-vocabulary values or exploit periodic arithmetic structure. We present IntSeqBERT, a dual-stream Transformer encoder for masked integer-sequence modelling on OEIS. Each sequence element is encoded along two complementary axes: a continuous log-scale magnitude embedding and sin/cos modulo embeddings for 100 residues (moduli $2$--$101$), fused via FiLM. Three prediction heads (magnitude regression, sign classification, and modulo prediction for 100 moduli) are trained jointly on 274,705 OEIS sequences. At the Large scale (91.5M parameters), IntSeqBERT achieves 95.85% magnitude accuracy and 50.38% Mean Modulo Accuracy (MMA) on the test set, outperforming a standard tokenised Transformer baseline by $+8.9$ pt and $+4.5$ pt, respectively. An ablation removing the modulo stream confirms it accounts for $+15.2$ pt of the MMA gain and contributes an additional $+6.2$ pt to magnitude accuracy. A probabilistic Chinese Remainder Theorem (CRT)-based Solver converts the model's predictions into concrete integers, yielding a 7.4-fold improvement in next-term prediction over the tokenised-Transformer baseline (Top-1: 19.09% vs. 2.59%). Modulo spectrum analysis reveals a strong negative correlation between Normalised Information Gain (NIG) and Euler's totient ratio $\varphi(m)/m$ ($r = -0.851$, $p < 10^{-28}$), providing empirical evidence that composite moduli capture OEIS arithmetic structure more efficiently via CRT aggregation. --- ### EigenData: A Self-Evolving Multi-Agent Platform for Function-Calling Data Synthesis, Auditing, and Repair Authors: Jiaao Chen, Jingyuan Qi, Mingye Gao, Wei-Chen Wang, Hanrui Wang, Di Jin Published: 2026-03-05 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.05553v1 Function-calling agents -- large language models that invoke tools and APIs -- require high-quality, domain-specific training data spanning executable environments, backing databases, and diverse multi-turn trajectories. We introduce EigenData, an integrated, self-evolving platform that automates the full data lifecycle through a multi-agent architecture. A top-level orchestrator, EigenCore, coordinates three specialized sub-systems: DatabaseAgent for realistic domain database construction, CodingAgent for verified executable environment generation with iterative test-debug loops, and DataAgent for multi-turn trajectory synthesis with self-evolving prompt optimization. Cross-component feedback ensures consistency across all artifacts. We apply EigenData to audit and repair the Berkeley Function-Calling Leaderboard (BFCL-V3), identifying systematic errors in function schemas, implementations, and reference trajectories, automatically correcting them through coordinated schema refinement, code-level bug fixes, and trajectory modification, and introducing an outcome-aware evaluation protocol that assesses task success via database-state correctness rather than turn-level trajectory matching. We demonstrate that the repaired benchmark, coupled with outcome-aware metrics, produces model rankings substantially better correlated with human judgments of functional correctness. --- ### AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction Authors: Jiashu Yang, Chi Zhang, Abudukelimu Wuerkaixi, Xuxin Cheng, Cao Liu, Ke Zeng, Xu Jia, Xunliang Cai Published: 2026-03-05 Categories: cs.IR, cs.CV arXiv: https://arxiv.org/abs/2603.05551v2 Multimodal document question answering requires retrieving dispersed evidence from visually rich long documents and performing reliable reasoning over heterogeneous information. Existing multimodal RAG systems remain limited by two bottlenecks: static retrieval that ignores query complexity, and end-to-end Vision-Language Models (VLMs) that couple visual perception with logical reasoning, leading to inefficient computation and unstable answer generation. We propose AutoThinkRAG, a complexity-aware inference architecture for multimodal document QA. It has two components: (1) a Query Complexity Router that analyzes query difficulty and structure to adaptively select retrieval and reasoning paths; and (2) a Perception--Reasoning Decoupling architecture that uses a lightweight VLM as a high-fidelity visual interpreter to convert query-relevant visual cues into textual representations, which are then passed to an LLM for logical reasoning and answer synthesis. This design improves both efficiency and robustness, especially on long-document and unanswerable queries. Experiments on DocBench and MMLongBench show that AutoThinkRAG achieves 82.13\% and 51.29\% overall accuracy, respectively, while reducing per-query token consumption by 18.9\% and monetary cost by 18.2\%. Further analyses show that the gains are most pronounced on complex queries requiring adaptive retrieval and multi-step reasoning. --- ### Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera Setups Authors: Leif Van Holland, Domenic Zingsheim, Mana Takhsha, Hannah Dröge, Patrick Stotko, Markus Plack, Reinhard Klein Published: 2026-03-05 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2603.05507v1 High-quality 3D streaming from multiple cameras is crucial for immersive experiences in many AR/VR applications. The limited number of views - often due to real-time constraints - leads to missing information and incomplete surfaces in the rendered images. Existing approaches typically rely on simple heuristics for the hole filling, which can result in inconsistencies or visual artifacts. We propose to complete the missing textures using a novel, application-targeted inpainting method independent of the underlying representation as an image-based post-processing step after the novel view rendering. The method is designed as a standalone module compatible with any calibrated multi-camera system. For this we introduce a multi-view aware, transformer-based network architecture using spatio-temporal embeddings to ensure consistency across frames while preserving fine details. Additionally, our resolution-independent design allows adaptation to different camera setups, while an adaptive patch selection strategy balances inference speed and quality, allowing real-time performance. We evaluate our approach against state-of-the-art inpainting techniques under the same real-time constraints and demonstrate that our model achieves the best trade-off between quality and speed, outperforming competitors in both image and video-based metrics. --- ### FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning Authors: Weijie Lyu, Ming-Hsuan Yang, Zhixin Shu Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.05506v1 We introduce FaceCam, a system that generates video under customizable camera trajectories for monocular human portrait video input. Recent camera control approaches based on large video-generation models have shown promising progress but often exhibit geometric distortions and visual artifacts on portrait videos due to scale-ambiguous camera representations or 3D reconstruction errors. To overcome these limitations, we propose a face-tailored scale-aware representation for camera transformations that provides deterministic conditioning without relying on 3D priors. We train a video generation model on both multi-view studio captures and in-the-wild monocular videos, and introduce two camera-control data generation strategies: synthetic camera motion and multi-shot stitching, to exploit stationary training cameras while generalizing to dynamic, continuous camera trajectories at inference time. Experiments on Ava-256 dataset and diverse in-the-wild videos demonstrate that FaceCam achieves superior performance in camera controllability, visual quality, identity and motion preservation. --- ### RoboPocket: Improve Robot Policies Instantly with Your Phone Authors: Junjie Fang, Wendi Chen, Han Xue, Fangyuan Zhou, Tian Le, Yi Wang, Yuting Zhang, Jun Lv, Chuan Wen, Cewu Lu Published: 2026-03-05 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.05504v2 Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces have emerged as a scalable solution for in-the-wild data acquisition, they predominantly operate in an open-loop manner: operators blindly collect demonstrations without knowing the underlying policy's weaknesses, leading to inefficient coverage of critical state distributions. Conversely, interactive methods like DAgger effectively address covariate shift but rely on physical robot execution, which is costly and difficult to scale. To reconcile this trade-off, we introduce RoboPocket, a portable system that enables Robot-Free Instant Policy Iteration using single consumer smartphones. Its core innovation is a Remote Inference framework that visualizes the policy's predicted trajectory via Augmented Reality (AR) Visual Foresight. This immersive feedback allows collectors to proactively identify potential failures and focus data collection on the policy's weak regions without requiring a physical robot. Furthermore, we implement an asynchronous Online Finetuning pipeline that continuously updates the policy with incoming data, effectively closing the learning loop in minutes. Extensive experiments demonstrate that RoboPocket adheres to data scaling laws and doubles the data efficiency compared to offline scaling strategies, overcoming their long-standing efficiency bottleneck. Moreover, our instant iteration loop also boosts sample efficiency by up to 2$\times$ in distributed environments a small number of interactive corrections per person. Project page and videos: https://robo-pocket.github.io. --- ### Accelerating Text-to-Video Generation with Calibrated Sparse Attention Authors: Shai Yehezkel, Shahar Yadin, Noam Elata, Yaron Ostrovsky-Berman, Bahjat Kawar Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.05503v1 Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. The large transformer-based backbones used in these models are bottlenecked by spatiotemporal attention. In this paper, we identify that a significant fraction of token-to-token connections consistently yield negligible scores across various inputs, and their patterns often repeat across queries. Thus, the attention computation in these cases can be skipped with little to no effect on the result. This observation continues to hold for connections among local token blocks. Motivated by this, we introduce CalibAtt, a training-free method that accelerates video generation via calibrated sparse attention. CalibAtt performs an offline calibration pass that identifies block-level sparsity and repetition patterns that are stable across inputs, and compiles these patterns into optimized attention operations for each layer, head, and diffusion timestep. At inference time, we compute the selected input-dependent connections densely, and skip the unselected ones in a hardware-efficient manner. Extensive experiments on Wan 2.1 14B, Mochi 1, and few-step distilled models at various resolutions show that CalibAtt achieves up to 1.58x end-to-end speedup, outperforming existing training-free methods while maintaining video generation quality and text-video alignment. --- ### POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation Authors: Zeju Qiu, Lixin Liu, Adrian Weller, Han Shi, Weiyang Liu Published: 2026-03-05 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.05500v2 Efficient and stable training of large language models (LLMs) remains a core challenge in modern machine learning systems. To address this challenge, Reparameterized Orthogonal Equivalence Training (POET), a spectrum-preserving framework that optimizes each weight matrix through orthogonal equivalence transformation, has been proposed. Although POET provides strong training stability, its original implementation incurs high memory consumption and computational overhead due to intensive matrix multiplications. To overcome these limitations, we introduce POET-X, a scalable and memory-efficient variant that performs orthogonal equivalence transformations with significantly reduced computational cost. POET-X maintains the generalization and stability benefits of POET while achieving substantial improvements in throughput and memory efficiency. In our experiments, POET-X enables the pretraining of billion-parameter LLMs on a single Nvidia H100 GPU, and in contrast, standard optimizers such as AdamW run out of memory under the same settings. --- ### The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks Authors: Shangwen Sun, Alfredo Canziani, Yann LeCun, Jiachen Zhu Published: 2026-03-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.05498v1 We study two recurring phenomena in Transformer language models: massive activations, in which a small number of tokens exhibit extreme outliers in a few channels, and attention sinks, in which certain tokens attract disproportionate attention mass regardless of semantic relevance. Prior work observes that these phenomena frequently co-occur and often involve the same tokens, but their functional roles and causal relationship remain unclear. Through systematic experiments, we show that the co-occurrence is largely an architectural artifact of modern Transformer design, and that the two phenomena serve related but distinct functions. Massive activations operate globally: they induce near-constant hidden representations that persist across layers, effectively functioning as implicit parameters of the model. Attention sinks operate locally: they modulate attention outputs across heads and bias individual heads toward short-range dependencies. We identify the pre-norm configuration as the key choice that enables the co-occurrence, and show that ablating it causes the two phenomena to decouple. --- ### Cheap Thrills: Effective Amortized Optimization Using Inexpensive Labels Authors: Khai Nguyen, Petros Ellinas, Anvita Bhagavathula, Priya L. Donti Published: 2026-03-05 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2603.05495v2 To scale optimization and simulation, prior work has explored training machine-learning surrogates that map problem parameters to solutions inexpensively at inference time. Unfortunately, commonly used approaches, including supervised and self-supervised learning with either soft or hard feasibility enforcement, face inherent challenges such as reliance on expensive high-quality labels or difficult optimization landscapes. To address their trade-offs, we propose a novel framework that collects "cheap" imperfect labels, performs supervised model pretraining with a merit loss-based termination scheme, and finally refines the model through self-supervised learning to improve final performance. Empirical validation across challenging domains -- including nonconvex constrained optimization, power-grid operation, and stiff dynamical systems -- shows that this three-stage strategy yields faster convergence; improved accuracy, feasibility, and optimality; and up to 59x reductions in total offline computational cost. We further analyze why and when our framework improves surrogate model training, finding that (i) merit loss is an informative signal and (ii) only small numbers of cheap, inexact labels are needed to place the model in a favorable regime for self-supervised learning. --- ### Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation Authors: Helena Casademunt, Bartosz Cywiński, Khoi Tran, Arya Jakkli, Samuel Marks, Neel Nanda Published: 2026-03-05 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.05494v2 Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation -- modifying prompts or weights so that the model answers truthfully -- and lie detection -- classifying whether a given response is false. Prior work evaluates such methods on models specifically trained to lie or conceal information, but these artificial constructions may not resemble naturally-occurring dishonesty. We instead study open-weights LLMs from Chinese developers, which are trained to censor politically sensitive topics: Qwen3 models frequently produce falsehoods about subjects like Falun Gong or the Tiananmen protests while occasionally answering correctly, indicating they possess knowledge they are trained to suppress. Using this as a testbed, we evaluate a suite of elicitation and lie detection techniques. For honesty elicitation, sampling without a chat template, few-shot prompting, and fine-tuning on generic honesty data most reliably increase truthful responses. For lie detection, prompting the censored model to classify its own responses performs near an uncensored-model upper bound, and linear probes trained on unrelated data offer a cheaper alternative. The strongest honesty elicitation techniques also transfer to frontier open-weights models including DeepSeek R1. Notably, no technique fully eliminates false responses. We release all prompts, code, and transcripts. --- ### Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought Authors: Siddharth Boppana, Annabel Ma, Max Loeffler, Raphael Sarfati, Eric Bigelow, Atticus Geiger, Owen Lewis, Jack Merullo Published: 2026-03-05 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.05488v4 We provide evidence of performative chain-of-thought (CoT) in reasoning models, where a model becomes strongly confident in its final answer, but continues generating tokens without revealing its internal belief. Our analysis compares activation probing, early forced answering, and a CoT monitor across two large models (DeepSeek-R1 671B & GPT-OSS 120B) and find task difficulty-specific differences: The model's final answer is decodable from activations far earlier in CoT than a monitor is able to say, especially for easy recall-based MMLU questions. We contrast this with genuine reasoning in difficult multihop GPQA-Diamond questions. Despite this, inflection points (e.g., backtracking, 'aha' moments) occur almost exclusively in responses where probes show large belief shifts, suggesting these behaviors track genuine uncertainty rather than learned "reasoning theater." Finally, probe-guided early exit reduces tokens by up to 80% on MMLU and 30% on GPQA-Diamond with similar accuracy, positioning attention probing as an efficient tool for detecting performative reasoning and enabling adaptive computation. --- ### Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation Authors: Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar Published: 2026-03-05 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.05485v1 As AI models progress beyond simple chatbots into more complex workflows, we draw ever closer to the event horizon beyond which AI systems will be utilized in autonomous, self-maintaining feedback loops. Any autonomous AI system will depend on automated, verifiable rewards and feedback; in settings where ground truth is sparse or non-deterministic, one practical source of such rewards is an LLM-as-a-Judge. Although LLM judges continue to improve, the literature has yet to introduce systems capable of enforcing standards with strong guarantees, particularly when bias vectors are unknown or adversarially discovered. To remedy this issue, we propose average bias-boundedness (A-BB), an algorithmic framework which formally guarantees reductions of harm/impact as a result of any measurable bias in an LLM judge. Evaluating on Arena-Hard-Auto with four LLM judges, we achieve (tau=0.5, delta=0.01) bias-bounded guarantees while retaining 61-99% correlation with original rankings across formatting and schematic bias settings, with most judge-bias combinations exceeding 80%. The code to reproduce our findings is available at https://github.com/penfever/bias-bounded-evaluation. --- ### Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline Authors: Guo Chen, Lidong Lu, Yicheng Liu, Liangrui Dong, Lidong Zou, Jixin Lv, Zhenquan Li, Xinyi Mao, Baoqi Pei, Shihao Wang, Zhiqi Li, Karan Sapra et al. Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.05484v1 While datasets for video understanding have scaled to hour-long durations, they typically consist of densely concatenated clips that differ from natural, unscripted daily life. To bridge this gap, we introduce MM-Lifelong, a dataset designed for Multimodal Lifelong Understanding. Comprising 181.1 hours of footage, it is structured across Day, Week, and Month scales to capture varying temporal densities. Extensive evaluations reveal two critical failure modes in current paradigms: end-to-end MLLMs suffer from a Working Memory Bottleneck due to context saturation, while representative agentic baselines experience Global Localization Collapse when navigating sparse, month-long timelines. To address this, we propose the Recursive Multimodal Agent (ReMA), which employs dynamic memory management to iteratively update a recursive belief state, significantly outperforming existing methods. Finally, we establish dataset splits designed to isolate temporal and domain biases, providing a rigorous foundation for future research in supervised learning and out-of-distribution generalization. --- ### SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis Authors: Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss, George H. Chen Published: 2026-03-05 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.05483v1 Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applications such as precision medicine and individualized policy-making. Yet, the survival analysis setting poses unique challenges for HTE estimation due to censoring, unobserved counterfactuals, and complex identification assumptions. Despite recent advances, from Causal Survival Forests to survival meta-learners and outcome imputation approaches, evaluation practices remain fragmented and inconsistent. We introduce SurvHTE-Bench, the first comprehensive benchmark for HTE estimation with censored outcomes. The benchmark spans (i) a modular suite of synthetic datasets with known ground truth, systematically varying causal assumptions and survival dynamics, (ii) semi-synthetic datasets that pair real-world covariates with simulated treatments and outcomes, and (iii) real-world datasets from a twin study (with known ground truth) and from an HIV clinical trial. Across synthetic, semi-synthetic, and real-world settings, we provide the first rigorous comparison of survival HTE methods under diverse conditions and realistic assumption violations. SurvHTE-Bench establishes a foundation for fair, reproducible, and extensible evaluation of causal survival methods. The data and code of our benchmark are available at: https://github.com/Shahriarnz14/SurvHTE-Bench . --- ### Thermodynamic Response Functions in Singular Bayesian Models Authors: Sean Plummer Published: 2026-03-05 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2603.05480v1 Singular statistical models-including mixtures, matrix factorization, and neural networks-violate regular asymptotics due to parameter non-identifiability and degenerate Fisher geometry. Although singular learning theory characterizes marginal likelihood behavior through invariants such as the real log canonical threshold and singular fluctuation, these quantities remain difficult to interpret operationally. At the same time, widely used criteria such as WAIC and WBIC appear disconnected from underlying singular geometry. We show that posterior tempering induces a one-parameter deformation of the posterior distribution whose associated observables generate a hierarchy of thermodynamic response functions. A universal covariance identity links derivatives of tempered expectations to posterior fluctuations, placing WAIC, WBIC, and singular fluctuation within a unified response framework. Within this framework, classical quantities from singular learning theory acquire natural thermodynamic interpretations: RLCT governs the leading free-energy slope, singular fluctuation corresponds to curvature of the tempered free energy, and WAIC measures predictive fluctuation. We formalize an observable algebra that quotients out non-identifiable directions, allowing structurally meaningful order parameters to be constructed in singular models. Across canonical singular examples-including symmetric Gaussian mixtures, reduced-rank regression, and overparameterized neural networks-we empirically demonstrate phase-transition-like behavior under tempering. Order parameters collapse, susceptibilities peak, and complexity measures align with structural reorganization in posterior geometry. Our results suggest that thermodynamic response theory provides a natural organizing framework for interpreting complexity, predictive variability, and structural reorganization in singular Bayesian learning. --- ### Towards 3D Scene Understanding of Gas Plumes in LWIR Hyperspectral Images Using Neural Radiance Fields Authors: Scout Jarman, Zigfried Hampel-Arias, Adra Carr, Kevin R. Moon Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.05473v1 Hyperspectral images (HSI) have many applications, ranging from environmental monitoring to national security, and can be used for material detection and identification. Longwave infrared (LWIR) HSI can be used for gas plume detection and analysis. Oftentimes, only a few images of a scene of interest are available and are analyzed individually. The ability to combine information from multiple images into a single, cohesive representation could enhance analysis by providing more context on the scene's geometry and spectral properties. Neural radiance fields (NeRFs) create a latent neural representation of volumetric scene properties that enable novel-view rendering and geometry reconstruction, offering a promising avenue for hyperspectral 3D scene reconstruction. We explore the possibility of using NeRFs to create 3D scene reconstructions from LWIR HSI and demonstrate that the model can be used for the basic downstream analysis task of gas plume detection. The physics-based DIRSIG software suite was used to generate a synthetic multi-view LWIR HSI dataset of a simple facility with a strong sulfur hexafluoride gas plume. Our method, built on the standard Mip-NeRF architecture, combines state-of-the-art methods for hyperspectral NeRFs and sparse-view NeRFs, along with a novel adaptive weighted MSE loss. Our final NeRF method requires around 50% fewer training images than the standard Mip-NeRF and achieves an average PSNR of 39.8 dB with as few as 30 training images. Gas plume detection applied to NeRF-rendered test images using the adaptive coherence estimator achieves an average AUC of 0.821 when compared with detection masks generated from ground-truth test images. --- ### Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval Authors: Artem Vazhentsev, Maria Marina, Daniil Moskovskiy, Sergey Pletenev, Mikhail Seleznyov, Mikhail Salnikov, Elena Tutubalina, Vasily Konovalov, Irina Nikishina, Alexander Panchenko, Viktor Moskvoretskii Published: 2026-03-05 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.05471v1 Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs). To enhance trust, natural language claims from diverse sources, including human-written text, web content, and model outputs, are commonly checked for factuality by retrieving external knowledge and using an LLM to verify the faithfulness of claims to the retrieved evidence. As a result, such methods are constrained by retrieval errors and external data availability, while leaving the models intrinsic fact-verification capabilities largely unused. We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source. To study this setting, we introduce a comprehensive evaluation framework focused on generalization, testing robustness to (i) long-tail knowledge, (ii) variation in claim sources, (iii) multilinguality, and (iv) long-form generation. Across 9 datasets, 18 methods and 3 models, our experiments indicate that logit-based approaches often underperform compared to those that leverage internal model representations. Building on this finding, we introduce INTRA, a method that exploits interactions between internal representations and achieves state-of-the-art performance with strong generalization. More broadly, our work establishes fact-checking without retrieval as a promising research direction that can complement retrieval-based frameworks, improve scalability, and enable the use of such systems as reward signals during training or as components integrated into the generation process. --- ### Kraus Constrained Sequence Learning For Quantum Trajectories from Continuous Measurement Authors: Priyanshi Singh, Krishna Bhatia Published: 2026-03-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.05468v1 Real-time reconstruction of conditional quantum states from continuous measurement records is a fundamental requirement for quantum feedback control, yet standard stochastic master equation (SME) solvers require exact model specification, known system parameters, and are sensitive to parameter mismatch. While neural sequence models can fit these stochastic dynamics, the unconstrained predictors can violate physicality such as positivity or trace constraints, leading to unstable rollouts and unphysical estimates. We propose a Kraus-structured output layer that converts the hidden representation of a generic sequence backbone into a completely positive trace preserving (CPTP) quantum operation, yielding physically valid state updates by construction. We instantiate this layer across diverse backbones, RNN, GRU, LSTM, TCN, ESN and Mamba; including Neural ODE as a comparative baseline, on stochastic trajectories characterized by parameter drift. Our evaluation reveals distinct trade-offs between gating mechanisms, linear recurrence, and global attention. Across all models, Kraus-LSTM achieves the strongest results, improving state estimation quality by 7% over its unconstrained counterpart while guaranteeing physically valid predictions in non-stationary regimes. --- ### HALP: Detecting Hallucinations in Vision-Language Models without Generating a Single Token Authors: Sai Akhil Kogilathota, Sripadha Vallabha E G, Luzhe Sun, Jiawei Zhou Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.05465v1 Hallucinations remain a persistent challenge for vision-language models (VLMs), which often describe nonexistent objects or fabricate facts. Existing detection methods typically operate after text generation, making intervention both costly and untimely. We investigate whether hallucination risk can instead be predicted before any token is generated by probing a model's internal representations in a single forward pass. Across a diverse set of vision-language tasks and eight modern VLMs, including Llama-3.2-Vision, Gemma-3, Phi-4-VL, and Qwen2.5-VL, we examine three families of internal representations: (i) visual-only features without multimodal fusion, (ii) vision-token representations within the text decoder, and (iii) query-token representations that integrate visual and textual information before generation. Probes trained on these representations achieve strong hallucination-detection performance without decoding, reaching up to 0.93 AUROC on Gemma-3-12B, Phi-4-VL 5.6B, and Molmo 7B. Late query-token states are the most predictive for most models, while visual or mid-layer features dominate in a few architectures (e.g., ~0.79 AUROC for Qwen2.5-VL-7B using visual-only features). These results demonstrate that (1) hallucination risk is detectable pre-generation, (2) the most informative layer and modality vary across architectures, and (3) lightweight probes have the potential to enable early abstention, selective routing, and adaptive decoding to improve both safety and efficiency. --- ### EdgeDAM: Real-time Object Tracking for Mobile Devices Authors: Syed Muhammad Raza, Syed Murtaza Hussain Abidi, Khawar Islam, Muhammad Ibrahim, Ajmal Saeed Mian Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.05463v2 Single-object tracking (SOT) on edge devices is a critical computer vision task, requiring accurate and continuous target localization across video frames under occlusion, distractor interference, and fast motion. However, recent state-of-the-art distractor-aware memory mechanisms are largely built on segmentation-based trackers and rely on mask prediction and attention-driven memory updates, which introduce substantial computational overhead and limit real-time deployment on resource-constrained hardware; meanwhile, lightweight trackers sustain high throughput but are prone to drift when visually similar distractors appear. To address these challenges, we propose EdgeDAM, a lightweight detection-guided tracking framework that reformulates distractor-aware memory for bounding-box tracking under strict edge constraints. EdgeDAM introduces two key strategies: (1) Dual-Buffer Distractor-Aware Memory (DAM), which integrates a Recent-Aware Memory to preserve temporally consistent target hypotheses and a Distractor-Resolving Memory to explicitly store hard negative candidates and penalize their re-selection during recovery; and (2) Confidence-Driven Switching with Held-Box Stabilization, where tracker reliability and temporal consistency criteria adaptively activate detection and memory-guided re-identification during occlusion, while a held-box mechanism temporarily freezes and expands the estimate to suppress distractor contamination. Extensive experiments on five benchmarks, including the distractor-focused DiDi dataset, demonstrate improved robustness under occlusion and fast motion while maintaining real-time performance on mobile devices, achieving 88.2% accuracy on DiDi and 25 FPS on an iPhone 15. Code will be released. --- ### NCTB-QA: A Large-Scale Bangla Educational Question Answering Dataset and Benchmarking Performance Authors: Abrar Eyasir, Tahsin Ahmed, Muhammad Ibrahim Published: 2026-03-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.05462v1 Reading comprehension systems for low-resource languages face significant challenges in handling unanswerable questions. These systems tend to produce unreliable responses when correct answers are absent from context. To solve this problem, we introduce NCTB-QA, a large-scale Bangla question answering dataset comprising 87,805 question-answer pairs extracted from 50 textbooks published by Bangladesh's National Curriculum and Textbook Board. Unlike existing Bangla datasets, NCTB-QA maintains a balanced distribution of answerable (57.25%) and unanswerable (42.75%) questions. NCTB-QA also includes adversarially designed instances containing plausible distractors. We benchmark three transformer-based models (BERT, RoBERTa, ELECTRA) and demonstrate substantial improvements through fine-tuning. BERT achieves 313% relative improvement in F1 score (0.150 to 0.620). Semantic answer quality measured by BERTScore also increases significantly across all models. Our results establish NCTB-QA as a challenging benchmark for Bangla educational question answering. This study demonstrates that domain-specific fine-tuning is critical for robust performance in low-resource settings. --- ### DEBISS: a Corpus of Individual, Semi-structured and Spoken Debates Authors: Klaywert Danillo Ferreira de Souza, David Eduardo Pereira, Cláudio E. C. Campelo, Larissa Lucena Vasconcelos Published: 2026-03-05 Categories: cs.CL, cs.DB arXiv: https://arxiv.org/abs/2603.05459v1 The process of debating is essential in our daily lives, whether in studying, work activities, simple everyday discussions, political debates on TV, or online discussions on social networks. The range of uses for debates is broad. Due to the diverse applications, structures, and formats of debates, developing corpora that account for these variations can be challenging, and the scarcity of debate corpora in the state of the art is notable. For this reason, the current research proposes the DEBISS corpus: a collection of spoken and individual debates with semi-structured features. With a broad range of NLP task annotations, such as speech-to-text, speaker diarization, argument mining, and debater quality assessment. --- ### Beyond Scattered Acceptance: Fast and Coherent Inference for DLMs via Longest Stable Prefixes Authors: Pengxiang Li, Joey Tsai, Hongwei Xue, Kunyu Shi, Shilin Yan Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.05454v1 Diffusion Language Models (DLMs) promise highly parallel text generation, yet their practical inference speed is often bottlenecked by suboptimal decoding schedulers. Standard approaches rely on 'scattered acceptance'-committing high confidence tokens at disjoint positions throughout the sequence. This approach inadvertently fractures the Key-Value (KV) cache, destroys memory locality, and forces the model into costly, repeated repairs across unstable token boundaries. To resolve this, we present the Longest Stable Prefix (LSP) scheduler, a training-free and model-agnostic inference paradigm based on monolithic prefix absorption. In each denoising step, LSP evaluates token stability via a single forward pass, dynamically identifies a contiguous left-aligned block of stable predictions, and snaps its boundary to natural linguistic or structural delimiters before an atomic commitment. This prefix-first topology yields dual benefits: systemically, it converts fragmented KV cache updates into efficient, contiguous appends; algorithmically, it preserves bidirectional lookahead over a geometrically shrinking active suffix, drastically reducing token flip rates and denoiser calls. Extensive evaluations on LLaDA-8B and Dream-7B demonstrate that LSP accelerates inference by up to 3.4x across rigorous benchmarks including mathematical reasoning, code generation, multilingual (CJK) tasks, and creative writing while matching or slightly improving output quality. By fundamentally restructuring the commitment topology, LSP bridges the gap between the theoretical parallelism of DLMs and practical hardware efficiency. --- ### FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling Authors: Ted Zadouri, Markus Hoehnerbach, Jay Shah, Timmy Liu, Vijay Thakkar, Tri Dao Published: 2026-03-05 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.05451v1 Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. While FlashAttention-3 optimized attention for Hopper GPUs through asynchronous execution and warp specialization, it primarily targets the H100 architecture. The AI industry has rapidly transitioned to deploying Blackwell-based systems such as the B200 and GB200, which exhibit fundamentally different performance characteristics due to asymmetric hardware scaling: tensor core throughput doubles while other functional units (shared memory bandwidth, exponential units) scale more slowly or remain unchanged. We develop several techniques to address these shifting bottlenecks on Blackwell GPUs: (1) redesigned pipelines that exploit fully asynchronous MMA operations and larger tile sizes, (2) software-emulated exponential and conditional softmax rescaling that reduces non-matmul operations, and (3) leveraging tensor memory and the 2-CTA MMA mode to reduce shared memory traffic and atomic adds in the backward pass. We demonstrate that our method, FlashAttention-4, achieves up to 1.3$\times$ speedup over cuDNN 9.13 and 2.7$\times$ over Triton on B200 GPUs with BF16, reaching up to 1613 TFLOPs/s (71% utilization). Beyond algorithmic innovations, we implement FlashAttention-4 entirely in CuTe-DSL embedded in Python, achieving 20-30$\times$ faster compile times compared to traditional C++ template-based approaches while maintaining full expressivity. --- ### Distributed Partial Information Puzzles: Examining Common Ground Construction Under Epistemic Asymmetry Authors: Yifan Zhu, Mariah Bradford, Kenneth Lai, Timothy Obiso, Videep Venkatesha, James Pustejovsky, Nikhil Krishnaswamy Published: 2026-03-05 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.05450v1 Establishing common ground, a shared set of beliefs and mutually recognized facts, is fundamental to collaboration, yet remains a challenge for current AI systems, especially in multimodal, multiparty settings, where the collaborators bring different information to the table. We introduce the Distributed Partial Information Puzzle (DPIP), a collaborative construction task that elicits rich multimodal communication under epistemic asymmetry. We present a multimodal dataset of these interactions, annotated and temporally aligned across speech, gesture, and action modalities to support reasoning over propositional content and belief dynamics. We then evaluate two paradigms for modeling common ground (CG): (1) state-of-the-art large language models (LLMs), prompted to infer shared beliefs from multimodal updates, and (2) an axiomatic pipeline grounded in Dynamic Epistemic Logic (DEL) that incrementally performs the same task. Results on the annotated DPIP data indicate that it poses a challenge to modern LLMs' abilities to track both task progression and belief state. --- ### RealWonder: Real-Time Physical Action-Conditioned Video Generation Authors: Wei Liu, Ziyu Chen, Zizhang Li, Yue Wang, Hong-Xing Yu, Jiajun Wu Published: 2026-03-05 Categories: cs.CV, cs.AI, cs.GR arXiv: https://arxiv.org/abs/2603.05449v1 Current video generation models cannot simulate physical consequences of 3D actions like forces and robotic manipulations, as they lack structural understanding of how actions affect 3D scenes. We present RealWonder, the first real-time system for action-conditioned video generation from a single image. Our key insight is using physics simulation as an intermediate bridge: instead of directly encoding continuous actions, we translate them through physics simulation into visual representations (optical flow and RGB) that video models can process. RealWonder integrates three components: 3D reconstruction from single images, physics simulation, and a distilled video generator requiring only 4 diffusion steps. Our system achieves 13.2 FPS at 480x832 resolution, enabling interactive exploration of forces, robot actions, and camera controls on rigid objects, deformable bodies, fluids, and granular materials. We envision RealWonder opens new opportunities to apply video models in immersive experiences, AR/VR, and robot learning. Our code and model weights are publicly available in our project website: https://liuwei283.github.io/RealWonder/ --- ### Residual RL-MPC for Robust Microrobotic Cell Pushing Under Time-Varying Flow Authors: Yanda Yang, Sambeeta Das Published: 2026-03-05 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.05448v2 Contact-rich micromanipulation in microfluidic flow is challenging because small disturbances can break pushing contact and induce large lateral drift. We study planar cell pushing with a magnetic rolling microrobot that tracks a waypoint-sampled reference curve under time-varying Poiseuille flow in simulation. We propose a hybrid controller that augments a nominal MPC with a learned residual policy trained by SAC. The policy outputs a bounded 2D velocity correction that is contact-gated, so residual actions are applied only during robot-cell contact, preserving reliable approach behavior and stabilizing learning. All methods share the same actuation interface and speed envelope for fair comparisons. Simulation results show improved robustness and tracking accuracy over pure MPC and PID under nonstationary flow, with generalization from a clover training curve to unseen circle and square trajectories. A residual-bound sweep identifies an intermediate correction limit as the best trade-off, which we use in all benchmarks. --- ### NaiLIA: Multimodal Nail Design Retrieval Based on Dense Intent Descriptions and Palette Queries Authors: Kanon Amemiya, Daichi Yashima, Kei Katsumata, Takumi Komatsu, Ryosuke Korekata, Seitaro Otsuki, Komei Sugiura Published: 2026-03-05 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.05446v1 We focus on the task of retrieving nail design images based on dense intent descriptions, which represent multi-layered user intent for nail designs. This is challenging because such descriptions specify unconstrained painted elements and pre-manufactured embellishments as well as visual characteristics, themes, and overall impressions. In addition to these descriptions, we assume that users provide palette queries by specifying zero or more colors via a color picker, enabling the expression of subtle and continuous color nuances. Existing vision-language foundation models often struggle to incorporate such descriptions and palettes. To address this, we propose NaiLIA, a multimodal retrieval method for nail design images, which comprehensively aligns with dense intent descriptions and palette queries during retrieval. Our approach introduces a relaxed loss based on confidence scores for unlabeled images that can align with the descriptions. To evaluate NaiLIA, we constructed a benchmark consisting of 10,625 images collected from people with diverse cultural backgrounds. The images were annotated with long and dense intent descriptions given by over 200 annotators. Experimental results demonstrate that NaiLIA outperforms standard methods. ---