# Research Papers — 2026-03 · bundle page 26 of 243 > Full-text markdown of papers #1251–1300 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/26 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/25.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/27.md) ### Learning to Predict Future-Aligned Research Proposals with Language Models Authors: Heng Wang, Pengcheng Jiang, Jiashuo Sun, Zhiyi Shi, Haofei Yu, Jiawei Han, Heng Ji Published: 2026-03-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.27146v4 Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and soundness are hard to measure automatically, and large-scale human evaluation is costly. We propose a verifiable alternative by reframing proposal generation as a time-sliced scientific forecasting problem. Given a research question and inspiring papers available before a cutoff time, the model generates a structured proposal and is evaluated by whether it anticipates research directions that appear in papers published after the time. We operationalize this objective with the Future Alignment Score (FAS), computed via retrieval and LLM-based semantic scoring against a held-out future corpus. To train models, we build a time-consistent dataset of 21,835 paper occurrences across 3,642 instances from targets and their pre-cutoff citations, and synthesize reasoning traces that teach gap identification and inspiration borrowing. Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality. Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method. Our code and data are publicly available at https://github.com/Arthur-Heng/future-aligned-proposals. --- ### Learning to Predict Future-Aligned Research Proposals with Language Models Authors: Heng Wang, Pengcheng Jiang, Jiashuo Sun, Zhiyi Shi, Haofei Yu, Jiawei Han, Heng Ji Published: 2026-03-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.27146v3 Large language models (LLMs) are increasingly used to assist ideation in research, but evaluating the quality of LLM-generated research proposals remains difficult: novelty and soundness are hard to measure automatically, and large-scale human evaluation is costly. We propose a verifiable alternative by reframing proposal generation as a time-sliced scientific forecasting problem. Given a research question and inspiring papers available before a cutoff time, the model generates a structured proposal and is evaluated by whether it anticipates research directions that appear in papers published after the time. We operationalize this objective with the Future Alignment Score (FAS), computed via retrieval and LLM-based semantic scoring against a held-out future corpus. To train models, we build a time-consistent dataset of 21,835 paper occurrences across 3,642 instances from targets and their pre-cutoff citations, and synthesize reasoning traces that teach gap identification and inspiration borrowing. Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality. Finally, we demonstrate practical impact by implementing two model-generated proposals with a code agent, obtaining 4.17% accuracy gain on MATH from a new prompting strategy and consistent improvements for a novel model-merging method. Our code and data are publicly available at https://github.com/Arthur-Heng/future-aligned-proposals. --- ### Pan-Cancer Mapping of the Tumor Immune Landscape through Metagene Clustering and Predictive Modeling Authors: Soham Chatterjee Published: 2026-03-28 Categories: q-bio.GN, cs.LG arXiv: https://arxiv.org/abs/2603.27145v1 As immunotherapies become standard cancer treatments, it is increasingly important to identify a patient's immune profile, which encompasses the activity of immune cells within the tumor microenvironment and the presence of specific biomarkers. However, we lack mechanistic explanations drivers of immune phenotypes. Despite advances in immune profiling with high-throughput sequencing, the mechanisms driving them remain unclear. This study aimed to identify novel, robust immune-related gene clusters (metagenes) and evaluate their prognostic significance and functional relevance across various pan-cancer types using a comprehensive computational pipeline. We acquired pan-cancer bulk RNA-seq and established immune subtypes from The Cancer Genome Atlas (TCGA). Using expression-based filtering and clustering of genes with ANOVA and Gaussian Mixture Model (GMM), we identified 48 unique metagenes. These metagenes achieved 87% accuracy in predicting the established subtypes. SHAP analysis revealed the most predictive metagenes per subtype, while functional enrichment analysis identified their associated pathways. Genes were ranked by differential expression between high- and low-expression groups. The metagenes revealed insights, including co-expression of immune activation and regulatory factors, links between cell cycle regulation and immune evasion, and dynamic microenvironment remodeling signatures. Kaplan-Meier survival analysis and multivariate Cox Regression revealed that many metagenes had prognostic value for overall survival. Overall, the metagenes represent coordinated biological programs across diverse cancer types, providing a foundation for developing robust, broadly applicable immuno-oncology biomarkers that extend beyond single-gene markers. They demonstrate prognostic value across cancer types and hold potential to guide immunotherapy treatment decisions. --- ### Follow Your Heart: Landmark-Guided Transducer Pose Scoring for Point-of-Care Echocardiography Authors: Zaiyang Guo, Jessie N. Dong, Filippos Bellos, Jilei Hao, Emily J. MacKay, Trevor Chan, Shir Goldfinger, Sethu Reddy, Steven Vance, Jason J. Corso, Alison M. Pouch Published: 2026-03-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.27143v1 Point-of-care transthoracic echocardiography (TTE) makes it possible to assess a patient's cardiac function in almost any setting. A critical step in the TTE exam is acquisition of the apical 4-chamber (A4CH) view, which is used to evaluate clinically impactful measurements such as left ventricular ejection fraction (LVEF). However, optimizing transducer pose for high-quality image acquisition and subsequent measurement is a challenging task, particularly for novice users. In this work, we present a multi-task network that provides feedback cues for A4CH view acquisition and automatically estimates LVEF in high-quality A4CH images. The network cascades a transducer pose scoring module and an uncertainty-aware LV landmark detector with automated LVEF estimation. A strength is that network training and inference do not require cumbersome or costly setups for transducer position tracking. We evaluate performance on point-of-care TTE data acquired with a spatially dense "sweep" protocol around the optimal A4CH view. The results demonstrate the network's ability to determine when the transducer pose is on target, close to target, or far from target based on the images alone, while generating visual landmark cues that guide anatomical interpretation and orientation. In conclusion, we demonstrate a promising strategy to provide guidance for A4CH view acquisition, which may be useful when deploying point-of-care TTE in limited resource settings. --- ### tBayes-MICE: A Bayesian Approach to Multiple Imputation for Time Series Data Authors: Amuche Ibenegbu, Pierre Lafaye de Micheaux, Rohitash Chandra Published: 2026-03-28 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.27142v2 Time-series analysis is often affected by missing data, a common problem across several fields, including healthcare and environmental monitoring. Multiple Imputation by Chained Equations (MICE) has been prominent for imputing missing values through "fully conditional specification". We extend MICE using the Bayesian framework (tBayes-MICE), utilising Bayesian inference to impute missing values via Markov Chain Monte Carlo (MCMC) sampling to account for uncertainty in MICE model parameters and imputed values. We also include temporally informed initialisation and time-lagged features in the model to respect the sequential nature of time-series data. We evaluate the tBayes-MICE method using two real-world datasets (AirQuality and PhysioNet), and using both the Random Walk Metropolis (RWM) and the Metropolis-Adjusted Langevin Algorithm (MALA) samplers. Our results demonstrate that tBayes-MICE reduces imputation errors relative to the baseline methods over all variables and accounts for uncertainty in the imputation process, thereby providing a more accurate measure of imputation error. We also found that MALA mixed better than RWM across most variables, achieving comparable accuracy while providing more consistent posterior exploration. Overall, these findings suggest that the tBayes-MICE framework represents a practical and efficient approach to time-series imputation, balancing increased accuracy with meaningful quantification of uncertainty in various environmental and clinical settings. --- ### Routing Sensitivity Without Controllability: A Diagnostic Study of Fairness in MoE Language Models Authors: Junhyeok Lee, Kyu Sung Choi Published: 2026-03-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.27141v1 Mixture-of-Experts (MoE) language models are universally sensitive to demographic content at the routing level, yet exploiting this sensitivity for fairness control is structurally limited. We introduce Fairness-Aware Routing Equilibrium (FARE), a diagnostic framework designed to probe the limits of routing-level stereotype intervention across diverse MoE architectures. FARE reveals that routing-level preference shifts are either unachievable (Mixtral, Qwen1.5, Qwen3), statistically non-robust (DeepSeekMoE), or accompanied by substantial utility cost (OLMoE, -4.4%p CrowS-Pairs at -6.3%p TQA). Critically, even where log-likelihood preference shifts are robust, they do not transfer to decoded generation: expanded evaluations on both non-null models yield null results across all generation metrics. Group-level expert masking reveals why: bias and core knowledge are deeply entangled within expert groups. These findings indicate that routing sensitivity is necessary but insufficient for stereotype control, and identify specific architectural conditions that can inform the design of more controllable future MoE systems. --- ### The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models Authors: Shivang Chopra, Shaunak Halbe, Chengyue Huang, Brisa Maneechotesuwan, Zsolt Kira Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27139v2 Fine-tuning approaches for Vision-Language Models (VLMs) face a critical three-way trade-off between In-Distribution (ID) accuracy, Out-of-Distribution (OOD) generalization, and adversarial robustness. Existing robust fine-tuning strategies resolve at most two axes of this trade-off. Generalization-preserving methods retain ID/OOD performance but leave models vulnerable to adversarial attacks, while adversarial training improves robustness to targeted attacks but degrades ID/OOD accuracy. Our key insight is that the robustness trade-off stems from two geometric failures: sharp, anisotropic minima in parameter space and unstable feature representations that deform under perturbation. To address this, we propose GRACE (Gram-aligned Robustness via Adaptive Curvature Estimation), a unified fine-tuning framework that jointly regularizes the parameter-space curvature and feature-space invariance for VLMs. Grounded in Robust PAC-Bayes theory, GRACE employs adaptive weight perturbations scaled by local curvature to promote flatter minima, combined with a feature alignment loss that maintains representation consistency across clean, adversarial, and OOD inputs. On ImageNet fine-tuning of CLIP models, GRACE simultaneously improves ID accuracy by 10.8%, and adversarial accuracy by 13.5% while maintaining 57.0% OOD accuracy (vs. 57.4% zero-shot baseline). Geometric analysis confirms that GRACE converges to flatter minima without feature distortion across distribution shifts, providing a principled step toward generalized robustness in foundation VLMs. --- ### ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM Inference Authors: Qiuyang Zhang, Kai Zhou, Ding Tang, Kai Lu, Cheng Li, Zhenyu Yang, Peng Xu, Jiguang Wan Published: 2026-03-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27138v1 Large language models encounter critical GPU memory capacity constraints during long-context inference, where KV cache memory consumption severely limits decode batch sizes. While existing research has explored offloading KV cache to DRAM, these approaches either demand frequent GPU-CPU data transfers or impose extensive CPU computation requirements, resulting in poor GPU utilization as the system waits for I/O operations or CPU processing to complete. We propose ScoutAttention, a novel KV cache offloading framework that accelerates LLM inference through collaborative GPU-CPU attention computation. To prevent CPU computation from bottlenecking the system, ScoutAttention introduces GPU-CPU collaborative block-wise sparse attention that significantly reduces CPU load. Unlike conventional parallel computing approaches, our framework features a novel layer-ahead CPU pre-computation algorithm, enabling the CPU to initiate attention computation one layer in advance, complemented by asynchronous periodic recall mechanisms to maintain minimal CPU compute load. Experimental results demonstrate that ScoutAttention maintains accuracy within 2.4% of baseline while achieving 2.1x speedup compared to existing offloading methods. --- ### A Mean Field Games Perspective on Evolutionary Clustering Authors: Alessio Basti, Fabio Camilli, Adriano Festa Published: 2026-03-28 Categories: math.NA, stat.ML arXiv: https://arxiv.org/abs/2603.27137v2 We propose a control-theoretic framework for evolutionary clustering based on quasi-stationary Mean Field Games. Each cluster is represented by a probability density whose evolution is governed by a Fokker--Planck equation, while the associated velocity field is determined through a stationary Hamilton--Jacobi equation. The general formulation does not prescribe a finite-dimensional statistical shape for the component densities, although the number of components is fixed. In the Gaussian specialization, we show that suitable affine dynamics reproduce the mean and covariance trajectories generated by the classical Expectation--Maximization procedure. To improve temporal coherence in the presence of noise and temporary cluster overlaps, we introduce causal and non-causal time-averaged log-likelihood objectives. We also develop a fully density-based numerical implementation for non-Gaussian components. The proposed formulations are assessed on synthetic and real time-dependent datasets and compared with independent snapshot Expectation--Maximization and with the same method applied to temporally smoothed observations. In the two-dimensional benchmark, an established evolutionary \(k\)-means method is also included as an external dynamic-clustering baseline. --- ### A Mean Field Games Perspective on Evolutionary Clustering Authors: Alessio Basti, Fabio Camilli, Adriano Festa Published: 2026-03-28 Categories: math.NA, stat.ML arXiv: https://arxiv.org/abs/2603.27137v1 We propose a control-theoretic framework for evolutionary clustering based on Mean Field Games (MFG). Moving beyond static or heuristic approaches, we formulate the problem as a population dynamics game governed by a coupled Hamilton-Jacobi-Bellman and Fokker-Planck system. Driven by a variational cost functional rather than predefined statistical shapes, this continuous-time formulation provides a flexible basis for non-parametric cluster evolution. To validate the framework, we analyze the setting of time-dependent Gaussian mixtures, showing that the MFG dynamics recover the trajectories of the classical Expectation-Maximization (EM) algorithm while ensuring mass conservation. Furthermore, we introduce time-averaged log-likelihood functionals to regularize temporal fluctuations. Numerical experiments illustrate the stability of our approach and suggest a path toward more general non-parametric clustering applications where traditional EM methods may face limitations. --- ### Spectral-Aware Text-to-Time Series Generation with Billion-Scale Multimodal Meteorological Data Authors: Shijie Zhang Published: 2026-03-28 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.27135v1 Text-to-time-series generation is particularly important in meteorology, where natural language offers intuitive control over complex, multi-scale atmospheric dynamics. Existing approaches are constrained by the lack of large-scale, physically grounded multimodal datasets and by architectures that overlook the spectral-temporal structure of weather signals. We address these challenges with a unified framework for text-guided meteorological time-series generation. First, we introduce MeteoCap-3B, a billion-scale weather dataset paired with expert-level captions constructed via a Multi-agent Collaborative Captioning (MACC) pipeline, yielding information-dense and physically consistent annotations. Building on this dataset, we propose MTransformer, a diffusion-based model that enables precise semantic control by mapping textual descriptions into multi-band spectral priors through a Spectral Prompt Generator, which guides generation via frequency-aware attention. Extensive experiments on real-world benchmarks demonstrate state-of-the-art generation quality, accurate cross-modal alignment, strong semantic controllability, and substantial gains in downstream forecasting under data-sparse and zero-shot settings. Additional results on general time-series benchmarks indicate that the proposed framework generalizes beyond meteorology. --- ### Factorization Regret mediates compositional generalization in latent space Authors: John Schwarcz Published: 2026-03-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27134v8 Are there still barriers to generalization once all relevant variables are known? We consider the challenge of generalizing to a novel combination of task-relevant latent variables in the Cognitive Gridworld, a stationary Partially Observable Markov Decision Process where observations are generated by latent variables with parametric interactions. We establish Factorization Regret as an information-theoretic quantity measuring the contribution of latent variable interactions to task performance. Using this metric, we explain the sub-optimality of Echo State Networks and uncover a failure mode whereby confidence becomes decoupled from accuracy. This suggests that utilizing interactions between relevant variables is a non-trivial capability. We next introduce Representation Classification Chains to show that latent variable interactions and how to infer the variables' values can be learned together through Reinforcement Learning. Solving this variational inference problem enables generalization to novel combinations of relevant variables. Lastly, we demonstrate that once interactions are learned, imagined experience is sufficient for zero-shot control. In summary, we develop and motivate a minimal, theoretically grounded setting for research into generalization from experience. --- ### Factorization Regret mediates compositional generalization in latent space Authors: John Schwarcz Published: 2026-03-28 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.27134v6 Are there still barriers to generalization once all of the relevant variables are known? We consider the challenge of generalizing to novel combinations of task-relevant latent variables. To explore this framework, we develop the Cognitive Gridworld, a stationary Partially Observable Markov Decision Process (POMDP) in which observations are generated jointly by multiple latent variables with parametric interactions. This setting allows us to describe Factorization Regret: an information-theoretic quantity that measures the contribution of latent variable interactions to task performance. Using this metric, we first analyze Recurrent Neural Networks (RNNs) that are explicitly provided with the interactions and find that Factorization Regret explains the accuracy gap between Echo State and Fully Trained networks. Additionally, our analysis uncovers a theoretically predicted failure mode, where confidence becomes decoupled from accuracy. These results suggest that utilizing the interactions between relevant variables is a non-trivial capability. We then address a harder regime where the interactions themselves must be learned by an embedding model. Learning how variables interact while simultaneously learning how to infer their values is a variational inference problem, often described as meta-learning. To explicitly disentangle variable inference and parameter estimation, we develop Representation Classification Chains (RCCs), a novel architecture which learns how latent variables interact through Reinforcement Learning (RL), from teaching signals provided only for a subset of training goal variables. Finally, we demonstrate the usefulness of RCCs in enabling generalization to novel combinations of latent variables through offline learning. In summary, we present a theoretically grounded setting for research, development and evaluation of goal-directed general intelligence. --- ### Bayesian-Symbolic Integration for Uncertainty-Aware Parking Prediction Authors: Alireza Nezhadettehad, Arkady Zaslavsky, Abdur Rakib, Seng W. Loke Published: 2026-03-28 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.27119v1 Accurate parking availability prediction is critical for intelligent transportation systems, but real-world deployments often face data sparsity, noise, and unpredictable changes. Addressing these challenges requires models that are not only accurate but also uncertainty-aware. In this work, we propose a loosely coupled neuro-symbolic framework that integrates Bayesian Neural Networks (BNNs) with symbolic reasoning to enhance robustness in uncertain environments. BNNs quantify predictive uncertainty, while symbolic knowledge extracted via decision trees and encoded using probabilistic logic programming is leveraged in two hybrid strategies: (1) using symbolic reasoning as a fallback when BNN confidence is low, and (2) refining output classes based on symbolic constraints before reapplying the BNN. We evaluate both strategies on real-world parking data under full, sparse, and noisy conditions. Results demonstrate that both hybrid methods outperform symbolic reasoning alone, and the context-refinement strategy consistently exceeds the performance of Long Short-Term Memory (LSTM) networks and BNN baselines across all prediction windows. Our findings highlight the potential of modular neuro-symbolic integration in real-world, uncertainty-prone prediction tasks. --- ### Quantitative measurements of biological/chemical concentrations using smartphone cameras Authors: Zhendong Cao, Hongji Dai, Zhida Li, Ash Parameswaran Published: 2026-03-28 Categories: eess.IV, cs.CV, eess.SP, eess.SY arXiv: https://arxiv.org/abs/2603.27118v1 This paper presents a smartphone-based imaging system capable of quantifying the concentration of an assortment of biological/chemical assay samples. The main objective is to construct an image database which characterizes the relationship between color information and concentrations of the biological/chemical assay sample. For this aim, a designated optical setup combined with image processing and data analyzing techniques was implemented. A series of experiments conducted on selected assays, including fluorescein, RNA Mango, homogenized milk and yeast have demonstrated that the proposed system estimates the concentration of fluorescent materials and colloidal mixtures comparable to currently used commercial and laboratory instruments. Furthermore, by utilizing the camera and computational power of smartphones, eventual development can be directed toward extremely compact, inexpensive and portable analysis and diagnostic systems which will allow experiments and tests to be conducted in remote or impoverished areas. --- ### Gender-Based Heterogeneity in Youth Privacy-Protective Behavior for Smart Voice Assistants: Evidence from Multigroup PLS-SEM Authors: Molly Campbell, Yulia Bobkova, Ajay Kumar Shrestha Published: 2026-03-28 Categories: cs.CR, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.27117v2 This paper investigates how gender shapes privacy decision-making in youth smart voice assistant (SVA) ecosystems. Using survey data from 469 Canadian youths aged 16-24, we apply multigroup Partial Least Squares Structural Equation Modeling to compare males (N=241) and females (N=174) (total N = 415) across five privacy constructs: Perceived Privacy Risks (PPR), Perceived Privacy Benefits (PPBf), Algorithmic Transparency and Trust (ATT), Privacy Self-Efficacy (PSE), and Privacy Protective Behavior (PPB). Results provide exploratory evidence of gender heterogeneity in selected pathways. The direct effect of PPR on PPB is stronger for males (Male: \b{eta} = 0.424; Female: \b{eta} = 0.233; p < 0.1), while the indirect effect of ATT on PPB via PSE is stronger for females (Female: \b{eta} = 0.229; Male: \b{eta} = 0.132; p < 0.1). Descriptive analysis of non-binary (N=15) and prefer-not-to-say participants (N=39) shows lower trust and higher perceived risk than the binary groups, motivating future work with adequately powered gender-diverse samples. Overall, the findings provide exploratory evidence that gender may moderate key privacy pathways, supporting more responsive transparency and control interventions for youth SVA use. --- ### The Price of Meaning: Why Every Semantic Memory System Forgets Authors: Sambartha Ray Barman, Andrey Starenky, Sofia Bodnar, Nikhil Narasimhan, Ashwin Gopinath Published: 2026-03-28 Categories: cs.AI, cs.IR, cs.NE arXiv: https://arxiv.org/abs/2603.27116v1 Every major AI memory system in production today organises information by meaning. That organisation enables generalisation, analogy, and conceptual retrieval -- but it comes at a price. We prove that the same geometric structure enabling semantic generalisation makes interference, forgetting, and false recall inescapable. We formalise this tradeoff for \textit{semantically continuous kernel-threshold memories}: systems whose retrieval score is a monotone function of an inner product in a semantic feature space with finite local intrinsic dimension. Within this class we derive four results: (1) semantically useful representations have finite effective rank; (2) finite local dimension implies positive competitor mass in retrieval neighbourhoods; (3) under growing memory, retention decays to zero, yielding power-law forgetting curves under power-law arrival statistics; (4) for associative lures satisfying a $δ$-convexity condition, false recall cannot be eliminated by threshold tuning. We test these predictions across five architectures: vector retrieval, graph memory, attention-based context, BM25 filesystem retrieval, and parametric memory. Pure semantic systems express the vulnerability directly as forgetting and false recall. Reasoning-augmented systems partially override these symptoms but convert graceful degradation into catastrophic failure. Systems that escape interference entirely do so by sacrificing semantic generalisation. The price of meaning is interference, and no architecture we tested avoids paying it. --- ### SJD-VP: Speculative Jacobi Decoding with Verification Prediction for Autoregressive Image Generation Authors: Bingqi Shan, Baoquan Zhang, Xiaochen Qi, Xutao Li, Yunming Ye, Liqiang Nie Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27115v1 Speculative Jacobi Decoding (SJD) has emerged as a promising method for accelerating autoregressive image generation. Despite its potential, existing SJD approaches often suffer from the low acceptance rate issue of speculative tokens due to token selection ambiguity. Recent works attempt to mitigate this issue primarily from the relaxed token verification perspective but fail to fully exploit the iterative dynamics of decoding. In this paper, we conduct an in-depth analysis and make a novel observation that tokens whose probabilities increase are more likely to match the verification-accepted and correct token. Based on this, we propose a novel Speculative Jacobi Decoding with Verification Prediction (SJD-VP). The key idea is to leverage the change in token probabilities across iterations to guide sampling, favoring tokens whose probabilities increase. This effectively predicts which tokens are likely to pass subsequent verification, boosting the acceptance rate. In particular, our SJD-VP is plug-and-play and can be seamlessly integrated into existing SJD methods. Extensive experiments on standard benchmarks demonstrate that our SJD-VP method consistently accelerates autoregressive decoding while improving image generation quality. --- ### Maximin Learning of Individualized Treatment Effect on Multi-Domain Outcomes Authors: Yuying Lu, Wenbo Fei, Yuanjia Wang, Molei Liu Published: 2026-03-28 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2603.27114v1 Precision mental health requires treatment decisions that account for heterogeneous symptoms reflecting multiple clinical domains. However, existing methods for estimating individualized treatment effects (ITE) rely on a single summary outcome or a specific set of observed symptoms or measures, which are sensitive to symptom selection and limit generalizability to unmeasured yet clinically relevant domains. We propose DRIFT, a new maximin framework for estimating robust ITEs from high-dimensional item-level data by leveraging latent factor representations and adversarial learning. DRIFT learns latent constructs via generalized factor analysis, then constructs an anchored on-target uncertainty set that extrapolates beyond the observed measures to approximate the broader hyper-population of potential outcomes. By optimizing worst-case performance over this uncertainty set, DRIFT yields ITEs that are robust to underrepresented or unmeasured domains. We further show that DRIFT is invariant to admissible reparameterizations of the latent factors and admits a closed-form maximin solution, with theoretical guarantees for identification and convergence. In analyses of a randomized controlled trial for major depressive disorder (EMBARC), DRIFT demonstrates superior performance and improved generalizability to external multi-domain outcomes, including side effects and self-reported symptoms not used during training. --- ### Hierarchy-Guided Topology Latent Flow for Molecular Graph Generation Authors: Urvi Awasthi, Alexander Arjun Lobo, Leonid Zhukov Published: 2026-03-28 Categories: cs.LG, cond-mat.mtrl-sci, stat.ML arXiv: https://arxiv.org/abs/2603.27113v1 Generating chemically valid 3D molecules is hindered by discrete bond topology: small local bond errors can cause global failures (valence violations, disconnections, implausible rings), especially for drug-like molecules with long-range constraints. Many unconditional 3D generators emphasize coordinates and then infer bonds or rely on post-processing, leaving topology feasibility weakly controlled. We propose Hierarchy-Guided Latent Topology Flow (HLTF), a planner-executor model that generates bond graphs with 3D coordinates, using a latent multi-scale plan for global context and a constraint-aware sampler to suppress topology-driven failures. On QM9, HLTF achieves 98.8% atom stability and 92.9% valid-and-unique, improving PoseBusters validity to 94.0% (+0.9 over the strongest reported baseline). On GEOM-DRUGS, HLTF attains 85.5%/85.0% validity/valid-unique-novel without post-processing and 92.2%/91.2% after standardized relaxation, within 0.9 points of the best post-processed baseline. Explicit topology generation also reduces "false-valid" samples that pass RDKit sanitization but fail stricter checks. --- ### RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation Authors: Sen Zhang, Runmei Li, Shizhuang Deng, Zhichao Zheng, Yuhe Zhang, Jiani Li, Kailun Zhang, Tao Zhang, Wenjun Wu, Qunbo Wang Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27112v2 As Automatic Train Operation (ATO) advances toward GoA4 and beyond, it increasingly depends on efficient, reliable cab-view visual perception and decision-oriented inference to ensure safe operation in complex and dynamic railway environments. However, existing approaches focus primarily on basic perception and often generalize poorly to rare yet safety-critical corner cases. They also lack the high-level reasoning and planning capabilities required for operational decision-making. Although recent Large Multi-modal Models (LMMs) show strong generalization and cognitive capabilities, their use in safety-critical ATO is hindered by high computational cost and hallucination risk. Meanwhile, reliable domain-specific benchmarks for systematically evaluating cognitive capabilities are still lacking. To address these gaps, we introduce RailVQA-bench, the first VQA benchmark for cab-view visual cognition in ATO, comprising 20,000 single-frame and 1,168 video based QA pairs to evaluate cognitive generalization and interpretability in both static and dynamic scenarios. Furthermore, we propose RailVQA-CoM, a collaborative large-small model framework that combines small-model efficiency with large-model cognition via a transparent three-module architecture and adaptive temporal sampling, improving perceptual generalization and enabling more efficient reasoning and planning. Experiments demonstrate that the proposed approach substantially improves performance, enhances interpretability, improves efficiency, and strengthens cross-domain generalization in autonomous driving systems. Code and datasets will be available at https://cybereye-bjtu.github.io/RailVQA.html. --- ### MotiMem: Motion-Aware Approximate Memory for Energy-Efficient Neural Perception in Autonomous Vehicles Authors: Haohua Que, Mingkai Liu, Jiayue Xie, Haojia Gao, Jiajun Sun, Hongyi Xu, Handong Yao, Fei Qiao Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27108v1 High-resolution sensors are critical for robust autonomous perception but impose a severe memory wall on battery-constrained electric vehicles. In these systems, data movement energy often outweighs computation. Traditional image compression is ill-suited as it is semantically blind and optimizes for storage rather than bus switching activity. We propose MotiMem, a hardware-software co-designed interface. Exploiting temporal coherence,MotiMem uses lightweight 2D Motion Propagation to dynamically identify Regions of Interest (RoI). Complementing this, a Hybrid Sparsity-Aware Coding scheme leverages adaptive inversion and truncation to induce bitlevel sparsity. Extensive experiments across nuScenes, Waymo, and KITTI with 16 detection models demonstrate that MotiMem reduces memory-interface dynamic energy by approximately 43 percent while retaining approximately 93 percent of the object detection accuracy, establishing a new Pareto frontier significantly superior to standard codecs like JPEG and WebP. --- ### UniDAC: Universal Metric Depth Estimation for Any Camera Authors: Girish Chandar Ganesan, Yuliang Guo, Liu Ren, Xiaoming Liu Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27105v2 Monocular metric depth estimation (MMDE) is a core challenge in computer vision, playing a pivotal role in real-world applications that demand accurate spatial understanding. Although prior works have shown promising zero-shot performance in MMDE, they often struggle with generalization across diverse camera types, such as fisheye and $360^\circ$ cameras. Recent advances have addressed this through unified camera representations or canonical representation spaces, but they require either including large-FoV camera data during training or separately trained models for different domains. We propose UniDAC, an MMDE framework that presents universal robustness in all domains and generalizes across diverse cameras using a single model. We achieve this by decoupling metric depth estimation into relative depth prediction and spatially varying scale estimation, enabling robust performance across different domains. We propose a lightweight Depth-Guided Scale Estimation module that upsamples a coarse scale map to high resolution using the relative depth map as guidance to account for local scale variations. Furthermore, we introduce RoPE-$φ$, a distortion-aware positional embedding that respects the spatial warping in Equi-Rectangular Projections (ERP) via latitude-aware weighting. UniDAC achieves state of the art (SoTA) in cross-camera generalization by consistently outperforming prior methods across all datasets. --- ### Autonomous Agent-Orchestrated Digital Twins (AADT): Leveraging the OpenClaw Framework for State Synchronization in Rare Genetic Disorders Authors: Hongzhuo Chen, Zhanliang Wang, Quan M. Nguyen, Gongbo Zhang, Chunhua Weng, Kai Wang Published: 2026-03-28 Categories: q-bio.QM, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2603.27104v1 Background: Medical Digital Twins (MDTs) are computational representations of individual patients that integrate clinical, genomic, and physiological data to support diagnosis, treatment planning, and outcome prediction. However, most MDTs remain static or passively updated, creating a critical synchronization gap, especially in rare genetic disorders where phenotypes, genomic interpretations, and care guidelines evolve over time. Methods: We propose an agent-orchestrated digital twin framework using OpenClaw's proactive "heartbeat" mechanism and modular Agent Skills. This Autonomous Agent-orchestrated Digital Twin (AADT) system continuously monitors local and external data streams (e.g., patient-reported phenotypes and updates in variant classification databases) and executes automated workflows for data ingestion, normalization, state updates, and trigger-based analysis. Results: A prototype implementation demonstrates that agent orchestration can continuously synchronize MDT states with both longitudinal phenotype updates and evolving genomic knowledge. In rare disease settings, this enables earlier diagnosis and more accurate modeling of disease progression. We present two case studies, including variant reinterpretation and longitudinal phenotype tracking, highlighting how AADTs support timely, auditable updates for both research and clinical care. Conclusion: The AADT framework addresses the key bottleneck of real-time synchronization in MDTs, enabling scalable and continuously updated patient models. We also discuss data security considerations and mitigation strategies through human-in-the-loop system design. --- ### LLM Enhanced Action Recognition via Hierarchical Global-Local Skeleton-Language Model Authors: Ruosi Wang, Fangwei Zuo, Lei Li, Zhaoqiang Xia Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27103v1 Skeleton-based human action recognition has achieved remarkable progress in recent years. However, most existing GCN-based methods rely on short-range motion topologies, which not only struggle to capture long-range joint dependencies and complex temporal dynamics but also limit cross-modal semantic alignment and understanding due to insufficient modeling of action semantics. To address these challenges, we propose a hierarchical global-local skeleton-language model (HocSLM), enabling the large action model be more representative of action semantics. First, we design a hierarchical global-local network (HGLNet) that consists of a composite-topology spatial module and a dual-path hierarchical temporal module. By synergistically integrating multi-level global and local modules, HGLNet achieves dynamically collaborative modeling at both global and local scales while preserving prior knowledge of human physical structure, significantly enhancing the model's representation of complex spatio-temporal relationships. Then, a large vision-language model (VLM) is employed to generate textual descriptions by passing the original RGB video sequences to this model, providing the rich action semantics for further training the skeleton-language model. Furthermore, we introduce a skeleton-language sequential fusion module by combining the features from HGLNet and the generated descriptions, which utilizes a skeleton-language model (SLM) for aligning skeletal spatio-temporal features and textual action descriptions precisely within a unified semantic space. The SLM model could significantly enhance the HGLNet's semantic discrimination capabilities and cross-modal understanding abilities. Extensive experiments demonstrate that the proposed HocSLM achieves the state-of-the-art performance on three mainstream benchmark datasets: NTU RGB+D 60, NTU RGB+D 120, and Northwestern-UCLA. --- ### PRUE: A Practical Recipe for Field Boundary Segmentation at Scale Authors: Gedeon Muhawenayo, Caleb Robinson, Subash Khanal, Zhanpei Fang, Isaac Corley, Alexander Wollam, Tianyi Gao, Leonard Strnad, Ryan Avery, Lyndon Estes, Ana M. Tárano, Nathan Jacobs et al. Published: 2026-03-28 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.27101v1 Large-scale maps of field boundaries are essential for agricultural monitoring tasks. Existing deep learning approaches for satellite-based field mapping are sensitive to illumination, spatial scale, and changes in geographic location. We conduct the first systematic evaluation of segmentation and geospatial foundation models (GFMs) for global field boundary delineation using the Fields of The World (FTW) benchmark. We evaluate 18 models under unified experimental settings, showing that a U-Net semantic segmentation model outperforms instance-based and GFM alternatives on a suite of performance and deployment metrics. We propose a new segmentation approach that combines a U-Net backbone, composite loss functions, and targeted data augmentations to enhance performance and robustness under real-world conditions. Our model achieves a 76\% IoU and 47\% object-F1 on FTW, an increase of 6\% and 9\% over the previous baseline. Our approach provides a practical framework for reliable, scalable, and reproducible field boundary delineation across model design, training, and inference. We release all models and model-derived field boundary datasets for five countries. --- ### Sovereign Context Protocol: An Open Attribution Layer for Human-Generated Content in the Age of Large Language Models Authors: Praneel Panchigar, Torlach Rush, Matthew Canabarro Published: 2026-03-28 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.27094v1 Large Language Models (LLMs) consume vast quantities of human-generated content for both training and real-time inference, yet the creators of that content remain largely invisible in the value chain. Existing approaches to data attribution operate either at the model-internals level, tracing influence through gradient signals, or at the legal-policy level through transparency mandates and copyright litigation. Neither provides a runtime mechanism for content creators to know when, by whom, and how their work is being consumed. We introduce the Sovereign Context Protocol (SCP), an open-source protocol specification and reference architecture that functions as an attribution-aware data access layer between LLMs and human-generated content. Inspired by Anthropic's Model Context Protocol (MCP), which standardizes how LLMs connect to tools, SCP standardizes how LLMs connect to creator-owned data, with every access event logged, licensed, and attributable. SCP defines six core methods (creator profiles, semantic search, content retrieval, trust/value scoring, authenticity verification, and access auditing) exposed over both REST and MCP-compatible interfaces. We formalize the protocol's message envelope, present a threat model with five adversary classes, propose a log-proportional revenue attribution model, and report preliminary latency benchmarks from a reference implementation built on FastAPI, ChromaDB, and NetworkX. We situate SCP within the emerging regulatory landscape, including the EU AI Act's Article 53 training data transparency requirements and ongoing U.S. copyright litigation, and argue that the attribution gap requires a protocol-level intervention that makes attribution a default property of data access. --- ### RDEx-MOP: Indicator-Guided Reconstructed Differential Evolution for Fixed-Budget Multiobjective Optimization Authors: Sichen Tao, Yifei Yang, Ruihan Zhao, Kaiyu Wang, Sicheng Liu, Shangce Gao Published: 2026-03-28 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2603.27092v1 Multiobjective optimisation in the CEC 2025 MOP track is evaluated not only by final IGD values but also by how quickly an algorithm reaches the target region under a fixed evaluation budget. This report documents RDEx-MOP, the reconstructed differential evolution variant used in the IEEE CEC 2025 numerical optimisation competition (C06 special session) bound-constrained multiobjective track. RDEx-MOP integrates indicator-based environmental selection, a niche-maintained Pareto-candidate set, and complementary differential evolution operators for exploration and exploitation. We evaluate RDEx-MOP on the official CEC 2025 MOP benchmark using the released checkpoint traces and the median-target U-score framework. Experimental results show that RDEx-MOP achieves the highest total score and the best average rank among all released comparison algorithms, including the earlier RDEx baseline. --- ### RDEx-CSOP: Feasibility-Aware Reconstructed Differential Evolution with Adaptive epsilon-Constraint Ranking Authors: Sichen Tao, Yifei Yang, Ruihan Zhao, Kaiyu Wang, Sicheng Liu, Shangce Gao Published: 2026-03-28 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2603.27090v1 Constrained single-objective numerical optimisation requires both feasibility maintenance and strong objective-value convergence under limited evaluation budgets. This report documents RDEx-CSOP, a constrained differential evolution variant used in the IEEE CEC 2025 numerical optimisation competition (C06 special session). RDEx-CSOP combines success-history parameter adaptation with an exploitation-biased hybrid search and an ε-constraint handling mechanism with a time-varying threshold. We evaluate RDEx-CSOP on the official CEC 2025 CSOP benchmark using the U-score framework (Speed, Accuracy, and Constraint categories). The results show that RDEx-CSOP achieves the highest total score and the best average rank among all released comparison algorithms, mainly through strong speed and competitive constraint-handling performance across the 28 benchmark functions. --- ### RDEx-SOP: Exploitation-Biased Reconstructed Differential Evolution for Fixed-Budget Bound-Constrained Single-Objective Optimization Authors: Sichen Tao, Yifei Yang, Ruihan Zhao, Kaiyu Wang, Sicheng Liu, Shangce Gao Published: 2026-03-28 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2603.27089v1 Bound-constrained single-objective numerical optimisation remains a key benchmark for assessing the robustness and efficiency of evolutionary algorithms. This report documents RDEx-SOP, an exploitation-biased success-history differential evolution variant used in the IEEE CEC 2025 numerical optimisation competition (C06 special session). RDEx-SOP combines success-history parameter adaptation, an exploitation-biased hybrid branch, and lightweight local perturbations to balance fast convergence and final solution quality under a strict evaluation budget. We evaluate RDEx-SOP on the official CEC 2025 SOP benchmark with the U-score framework (Speed and Accuracy categories). Experimental results show that RDEx-SOP achieves strong overall performance and statistically competitive final outcomes across the 29 benchmark functions. --- ### EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow Authors: Dogyun Park, Yanyu Li, Sergey Tulyakov, Anil Kag Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27086v1 Scaling video diffusion transformers is fundamentally bottlenecked by two compounding costs: the expensive quadratic complexity of attention per step, and the iterative sampling steps. In this work, we propose EFlow, an efficient few-step training framework, that tackles these bottlenecks simultaneously. To reduce sampling steps, we build on a solution-flow objective that learns a function mapping a noised state at time t to time s. Making this formulation computationally feasible and high-quality at video scale, however, demands two complementary innovations. First, we propose Gated Local-Global Attention, a token-droppable hybrid block which is efficient, expressive, and remains highly stable under aggressive random token-dropping, substantially reducing per-step compute. Second, we develop an efficient few-step training recipe. We propose Path-Drop Guided training to replace the expensive guidance target with a computationally cheap, weak path. Furthermore, we augment this with a Mean-Velocity Additivity regularizer to ensure high fidelity at extremely low step counts. Together, our EFlow enables a practical from-scratch training pipeline, achieving up to 2.5x higher training throughput over standard solution-flow, and 45.3x lower inference latency than standard iterative models with competitive performance on Kinetics and large-scale text-to-video datasets. --- ### SceneExpander: Text-Guided 3D Scene Expansion via Free-Form View Insertion Authors: Zijian He, Renjie Liu, Yihao Wang, Weizhi Zhong, Huan Yuan, Kun Gai, Guangrun Wang, Guanbin Li Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27084v3 World building with 3D scene representations is increasingly important for content creation, simulation, and interactive experiences, yet real workflows are inherently iterative: creators repeatedly extend existing scenes under user control. Motivated by this gap, we study text-guided 3D scene expansion via free-form view insertion. Starting from a real scene captured by multi-view images, a user specifies a text expansion intent, which a generative model materializes as an inserted view extending the scene coverage. Unlike simple object editing or style transfer within a fixed scene, the inserted view may be 3D-misaligned with the original reconstruction, introducing geometric shifts, hallucinated content, or view-dependent artifacts that disrupt global multi-view consistency. To address this challenge, we propose SceneExpander, which applies test-time adaptation to a parametric feed-forward 3D reconstruction model with two complementary distillation signals: anchor distillation stabilizes the captured scene using geometric cues from the captured views, while inserted-view self-distillation retains insertion-supported predictions to accommodate the misaligned view. Experiments on ETH scenes and online data demonstrate improved expansion behavior and reconstruction quality under misalignment. --- ### LightCtrl: Training-free Controllable Video Relighting Authors: Yizuo Peng, Xuelin Chen, Kai Zhang, Xiaodong Cun Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27083v1 Recent diffusion models have achieved remarkable success in image relighting, and this success has quickly been extended to video relighting. However, existing methods offer limited explicit control over illumination in the relighted output. We present LightCtrl, the first controllable video relighting method that enables explicit control of video illumination through a user-supplied light trajectory in a training-free manner. Our approach combines pre-trained diffusion models: an image relighting model processes each frame individually, followed by a video diffusion prior to enhance temporal consistency. To achieve explicit control over dynamically varying lighting, we introduce two key components. First, a Light Map Injection module samples light trajectory-specific noise and injects it into the latent representation of the source video, improving illumination coherence with the conditional light trajectory. Second, a Geometry-Aware Relighting module dynamically combines RGB and normal map latents in the frequency domain to suppress the influence of the original lighting, further enhancing adherence to the input light trajectory. Experiments show that LightCtrl produces high-quality videos with diverse illumination changes that closely follow the specified light trajectory, demonstrating improved controllability over baseline methods. Code is available at: https://github.com/GVCLab/LightCtrl. --- ### When Verification Hurts: Asymmetric Effects of Multi-Agent Feedback in Logic Proof Tutoring Authors: Tahreem Yasir, Sutapa Dey Tithi, Benyamin Tabarsi, Dmitri Droujkov, Sam Gilson Yasitha Rajapaksha, Xiaoyi Tian, Arun Ramesh, DongKuan, Xu, Tiffany Barnes Published: 2026-03-28 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.27076v1 Large language models (LLMs) are increasingly used for automated tutoring, but their reliability in structured symbolic domains remains unclear. We study step-level feedback for propositional logic proofs, which require precise symbolic reasoning aligned with a learner's current proof state. We introduce a knowledge-graph-grounded benchmark of 516 unique proof states with step-level annotations and difficulty metrics. Unlike prior tutoring evaluations that rely on model self-assessment or binary correctness, our framework enables fine-grained analysis of feedback quality against verified solution paths. We evaluate three role-specialized pipelines with varying solution access: Tutor (partial solution access), Teacher (full derivation access), and Judge (verification of Tutor feedback). Our results reveal a striking asymmetry: verification improves outcomes when upstream feedback is error-prone (<70% accuracy), but degrades performance by 4-6 percentage points through over-specification when feedback is already reliable (>85%). Critically, we identify a shared complexity ceiling; no model or pipeline reliably succeeds on proof states exceeding complexity 4-5. These findings challenge the assumption that adding verifiers or richer context universally improves tutoring, motivating adaptive, difficulty-aware architectures that route problems by estimated complexity and upstream reliability. --- ### Forecastability as an Information-Theoretic Limit on Prediction Authors: Peter Maurice Catt Published: 2026-03-28 Categories: stat.AP, cs.IT, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.27074v1 Forecasting is usually framed as a problem of model choice. This paper starts earlier, asking how much predictive information is available at each horizon. Under logarithmic loss, the answer is exact: the mutual information between the future observation and the declared information set equals the maximum achievable reduction in expected loss. This paper develops the consequences of that identity. Forecastability, defined as this mutual information evaluated across horizons, forms a profile whose shape reflects the dependence structure of the process and need not be monotone. Three structural properties are derived: compression of the information set can only reduce forecastability; the gap between the profile under a finite lag window and the full history gives an exact truncation error budget; and for processes with periodic dependence, the profile inherits the periodicity. Predictive loss decomposes into an irreducible component fixed by the information structure and an approximation component attributable to the method; their ratio defines the exploitation ratio, a normalised diagnostic for method adequacy. The exact equality is specific to log loss, but when forecastability is near zero, classical inequalities imply that no method under any loss can materially improve on the unconditional baseline. The framework provides a theoretical foundation for assessing, prior to any modelling, whether the declared information set contains sufficient predictive information at the horizon of interest. --- ### Voice-based debate with an AI adversary is associated with increased divergent ideation Authors: Neelam Modi Jain, Dan J. Wang Published: 2026-03-28 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2603.27073v1 Concerns that interacting with generative AI homogenizes human cognition are largely based on evidence from text-based interactions, potentially conflating the effects of AI systems with those of written communication. This study examines whether these patterns depend on communication modality rather than on AI itself. Analyzing 957 open-ended debates between university students and a knowledgeable AI adversary, we show that modality corresponds to distinct structural patterns in discourse. Consistent with classic distinctions between orality and literacy, spoken interactions are significantly more verbose and exhibit greater repetition of words and phrases than text-based exchanges. This redundancy, however, is functional: voice users rely on recurrent phrasing to maintain coherence while exploring a wider range of ideas. In contrast, text-based interaction favors concision and refinement but constrains conceptual breadth. These findings suggest that perceived cognitive limitations attributed to generative AI partly reflect the medium through which it is accessed. --- ### On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness Authors: Anil Kamber, Rahul Parhi Published: 2026-03-28 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.27072v1 Weight decay is ubiquitous in training deep neural network architectures. Its empirical success is often attributed to capacity control; nonetheless, our theoretical understanding of its effect on the loss landscape and the set of minimizers remains limited. In this paper, we show that $\ell^2$-regularized deep matrix factorization/deep linear network training problems with squared-error loss admit a unique end-to-end minimizer for all target matrices subject to factorization, except for a set of Lebesgue measure zero formed by the depth and the regularization parameter. This observation reveals fundamental properties of the loss landscape of regularized deep matrix factorization problems: the Hessian spectrum is constant across all minimizers of the regularized deep scalar factorization problem with squared-error loss. Moreover, we show that, in regularized deep matrix factorization problems with squared-error loss, if the target matrix does not belong to the Lebesgue measure-zero set, then the Frobenius norm of each layer is constant across all minimizers. This, in turn, yields a global lower bound on the trace of the Hessian evaluated at any minimizer of the regularized deep matrix factorization problem. Furthermore, we establish a critical threshold for the regularization parameter above which the unique end-to-end minimizer collapses to zero. --- ### Structural Graph Probing of Vision-Language Models Authors: Haoyu He, Yue Zhuo, Yu Zheng, Qi R. Wang Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27070v1 Vision-language models (VLMs) achieve strong multimodal performance, yet how computation is organized across populations of neurons remains poorly understood. In this work, we study VLMs through the lens of neural topology, representing each layer as a within-layer correlation graph derived from neuron-neuron co-activations. This view allows us to ask whether population-level structure is behaviorally meaningful, how it changes across modalities and depth, and whether it identifies causally influential internal components under intervention. We show that correlation topology carries recoverable behavioral signal; moreover, cross-modal structure progressively consolidates with depth around a compact set of recurrent hub neurons, whose targeted perturbation substantially alters model output. Neural topology thus emerges as a meaningful intermediate scale for VLM interpretability: richer than local attribution, more tractable than full circuit recovery, and empirically tied to multimodal behavior. Code is publicly available at https://github.com/he-h/vlm-graph-probing. --- ### Dynamic resource matching in manufacturing using deep reinforcement learning Authors: Saunak Kumar Panda, Yisha Xiang, Ruiqi Liu Published: 2026-03-28 Categories: cs.LG, cs.AI, math.OC arXiv: https://arxiv.org/abs/2603.27066v1 Matching plays an important role in the logical allocation of resources across a wide range of industries. The benefits of matching have been increasingly recognized in manufacturing industries. In particular, capacity sharing has received much attention recently. In this paper, we consider the problem of dynamically matching demand-capacity types of manufacturing resources. We formulate the multi-period, many-to-many manufacturing resource-matching problem as a sequential decision process. The formulated manufacturing resource-matching problem involves large state and action spaces, and it is not practical to accurately model the joint distribution of various types of demands. To address the curse of dimensionality and the difficulty of explicitly modeling the transition dynamics, we use a model-free deep reinforcement learning approach to find optimal matching policies. Moreover, to tackle the issue of infeasible actions and slow convergence due to initial biased estimates caused by the maximum operator in Q-learning, we introduce two penalties to the traditional Q-learning algorithm: a domain knowledge-based penalty based on a prior policy and an infeasibility penalty that conforms to the demand-supply constraints. We establish theoretical results on the convergence of our domain knowledge-informed Q-learning providing performance guarantee for small-size problems. For large-size problems, we further inject our modified approach into the deep deterministic policy gradient (DDPG) algorithm, which we refer to as domain knowledge-informed DDPG (DKDDPG). In our computational study, including small- and large-scale experiments, DKDDPG consistently outperformed traditional DDPG and other RL algorithms, yielding higher rewards and demonstrating greater efficiency in time and episodes. --- ### Story2Proposal: A Scaffold for Structured Scientific Paper Writing Authors: Zhuoyang Qian, Wei Shi, Xu Lin, Li Ling, Meng Luo, Ziming Wang, Zhiwei Zhang, Tengyue Xu, Gaoge Liu, Zhentao Zhang, Shuo Zhang, Ziqi Wang et al. Published: 2026-03-28 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.27065v1 Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text synthesis with validation applied only after generation, often producing structural drift, missing figures or tables, and cross-section inconsistencies. We introduce Story2Proposal, a contract-governed multi-agent framework that converts a research story into a structured manuscript through coordinated agents operating under a persistent shared visual contract. The system organizes architect, writer, refiner, and renderer agents around a contract state that tracks section structure and registered visual elements, while evaluation agents supply feedback in a generate evaluate adapt loop that updates the contract during generation. Experiments on tasks derived from the Jericho research corpus show that Story2Proposal achieved an expert evaluation score of 6.145 versus 3.963 for DirectChat (+2.182) across GPT, Claude, Gemini, and Qwen backbones. Compared with the structured generation baseline Fars, Story2Proposal obtained an average score of 5.705 versus 5.197, indicating improved structural consistency and visual alignment. --- ### ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding Authors: Jovana Kondic, Pengyuan Li, Dhiraj Joshi, Isaac Sanchez, Ben Wiesel, Shafiq Abedin, Amit Alfassy, Eli Schwartz, Daniel Caraballo, Yagmur Gizem Cinar, Florian Scheidegger, Steven I. Ross et al. Published: 2026-03-28 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.27064v2 Understanding charts requires models to jointly reason over geometric visual patterns, structured numerical data, and natural language -- a capability where current vision-language models (VLMs) remain limited. We introduce ChartNet, a high-quality, million-scale multimodal dataset designed to advance chart interpretation and reasoning. ChartNet leverages a novel code-guided synthesis pipeline to generate 1.5 million diverse chart samples spanning 24 chart types and 6 plotting libraries. Each sample consists of five aligned components: plotting code, rendered chart image, data table, natural language summary, and question-answering with reasoning, providing fine-grained cross-modal alignment. To capture the full spectrum of chart comprehension, ChartNet additionally includes specialized subsets encompassing human annotated data, real-world data, safety, and grounding. Moreover, a rigorous quality-filtering pipeline ensures visual fidelity, semantic accuracy, and diversity across chart representations. Fine-tuning on ChartNet consistently improves results across benchmarks, demonstrating its utility as large-scale supervision for multimodal models. As the largest open-source dataset of its kind, ChartNet aims to support the development of foundation models with robust and generalizable capabilities for data visualization understanding. The dataset is publicly available at https://huggingface.co/datasets/ibm-granite/ChartNet --- ### Conformalized Signal Temporal Logic Inference under Covariate Shift Authors: Yixuan Wang, Danyang Li, Matthew Cleaveland, Roberto Tron, Mingyu Cai Published: 2026-03-28 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.27062v1 Signal Temporal Logic (STL) inference learns interpretable logical rules for temporal behaviors in dynamical systems. To ensure the correctness of learned STL formulas, recent approaches have incorporated conformal prediction as a statistical tool for uncertainty quantification. However, most existing methods rely on the assumption that calibration and testing data are identically distributed and exchangeable, an assumption that is frequently violated in real-world settings. This paper proposes a conformalized STL inference framework that explicitly addresses covariate shift between training and deployment trajectories dataset. From a technical standpoint, the approach first employs a template-free, differentiable STL inference method to learn an initial model, and subsequently refines it using a limited deployment side dataset to promote distribution alignment. To provide validity guarantees under distribution shift, the framework estimates the likelihood ratio between training and deployment distributions and integrates it into an STL-robustness-based weighted conformal prediction scheme. Experimental results on trajectory datasets demonstrate that the proposed framework preserves the interpretability of STL formulas while significantly improving symbolic learning reliability at deployment time. --- ### VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation Authors: Jihwan Hong, Jaeyoung Do Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27060v1 Referring Video Object Segmentation (RVOS) aims to segment target objects in videos based on natural language descriptions. However, fixed keyframe-based approaches that couple a vision language model with a separate propagation module often fail to capture rapidly changing spatiotemporal dynamics and to handle queries requiring multi-step reasoning, leading to sharp performance drops on motion-intensive and reasoning-oriented videos beyond static RVOS benchmarks. To address these limitations, we propose VIRST (Video-Instructed Reasoning Assistant for Spatio-Temporal Segmentation), an end-to-end framework that unifies global video reasoning and pixel-level mask prediction within a single model. VIRST bridges semantic and segmentation representations through the Spatio-Temporal Fusion (STF), which fuses segmentation-aware video features into the vision-language backbone, and employs the Temporal Dynamic Anchor Updater to maintain temporally adjacent anchor frames that provide stable temporal cues under large motion, occlusion, and reappearance. This unified design achieves state-of-the-art results across diverse RVOS benchmarks under realistic and challenging conditions, demonstrating strong generalization to both referring and reasoning oriented settings. The code and checkpoints are available at https://github.com/AIDASLab/VIRST. --- ### Towards Intrinsic-Aware Monocular 3D Object Detection Authors: Zhihao Zhang, Abhinav Kumar, Xiaoming Liu Published: 2026-03-28 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.27059v1 Monocular 3D object detection (Mono3D) aims to infer object locations and dimensions in 3D space from a single RGB image. Despite recent progress, existing methods remain highly sensitive to camera intrinsics and struggle to generalize across diverse settings, since intrinsics govern how 3D scenes are projected onto the image plane. We propose MonoIA, a unified intrinsic-aware framework that models and adapts to intrinsic variation through a language-grounded representation. The key insight is that intrinsic variation is not a numeric difference but a perceptual transformation that alters apparent scale, perspective, and spatial geometry. To capture this effect, MonoIA employs large language models and vision-language models to generate intrinsic embeddings that encode the visual and geometric implications of camera parameters. These embeddings are hierarchically integrated into the detection network via an Intrinsic Adaptation Module, allowing the model to modulate its feature representations according to camera-specific configurations and maintain consistent 3D detection across intrinsics. This shifts intrinsic modeling from numeric conditioning to semantic representation, enabling robust and unified perception across cameras. Extensive experiments show that MonoIA achieves new state-of-the-art results on standard benchmarks including KITTI, Waymo, and nuScenes (e.g., +1.18% on the KITTI leaderboard), and further improves performance under multi-dataset training (e.g., +4.46% on KITTI Val). --- ### Liquid Networks with Mixture Density Heads for Efficient Imitation Learning Authors: Nikolaus Correll Published: 2026-03-28 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.27058v1 We compare liquid neural networks with mixture density heads against diffusion policies on Push-T, RoboMimic Can, and PointMaze under a shared-backbone comparison protocol that isolates policy-head effects under matched inputs, training budgets, and evaluation settings. Across tasks, liquid policies use roughly half the parameters (4.3M vs. 8.6M), achieve 2.4x lower offline prediction error, and run 1.8 faster at inference. In sample-efficiency experiments spanning 1% to 46.42% of training data, liquid models remain consistently more robust, with especially large gains in low-data and medium-data regimes. Closed-loop results on Push-T and PointMaze are directionally consistent with offline rankings but noisier, indicating that strong offline density modeling helps deployment while not fully determining closed-loop success. Overall, liquid recurrent multimodal policies provide a compact and practical alternative to iterative denoising for imitation learning. --- ### Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuning Authors: Hossein Salemi, Jitin Krishnan, Hemant Purohit Published: 2026-03-28 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.27057v1 Attribution theory explains how individuals interpret and attribute others' behavior in a social context by employing personal (dispositional) and impersonal (situational) causality. Large Language Models (LLMs), trained on human-generated corpora, may implicitly mimic this social attribution process in social contexts. However, the extent to which LLMs utilize these causal attributions in their reasoning remains underexplored. Although using reasoning paradigms, such as Chain-of-Thought (CoT), has shown promising results in various tasks, ignoring social attribution in reasoning could lead to biased responses by LLMs in social contexts. In this study, we investigate the impact of incorporating a user's goal as knowledge to infer dispositional causality and message context to infer situational causality on LLM performance. To this end, we introduce a scalable method to mitigate such biases by enriching the instruction prompts for LLMs with two prompt aids using social-attribution knowledge, based on the context and goal of a social media message. This method improves the model performance while reducing the social-attribution bias of the LLM in the reasoning on zero-shot classification tasks for behavior analytics applications. We empirically show the benefits of our method across two tasks-intent detection and theme detection on social media in the disaster domain-when considering the variability of disaster types and multiple languages of social media. Our experiments highlight the biases of three open-source LLMs: Llama3, Mistral, and Gemma, toward social attribution, and show the effectiveness of our mitigation strategies. --- ### Persona-Based Simulation of Human Opinion at Population Scale Authors: Mao Li, Frederick G. Conrad Published: 2026-03-28 Categories: cs.CY, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.27056v1 What does it mean to model a person, not merely to predict isolated responses, preferences, or behaviors, but to simulate how an individual interprets events, forms opinions, makes judgments, and acts consistently across contexts? This question matters because social science requires not only observing and predicting human outcomes, but also simulating interventions and their consequences. Although large language models (LLMs) can generate human-like answers, most existing approaches remain predictive, relying on demographic correlations rather than representations of individuals themselves. We introduce SPIRIT (Semi-structured Persona Inference and Reasoning for Individualized Trajectories), a framework designed explicitly for simulation rather than prediction. SPIRIT infers psychologically grounded, semi-structured personas from public social media posts, integrating structured attributes (e.g., personality traits and world beliefs) with unstructured narrative text reflecting values and lived experience. These personas prompt LLM-based agents to act as specific individuals when answering survey questions or responding to events. Using the Ipsos KnowledgePanel, a nationally representative probability sample of U.S. adults, we show that SPIRIT-conditioned simulations recover self-reported responses more faithfully than demographic persona and reproduce human-like heterogeneity in response patterns. We further demonstrate that persona banks can function as virtual respondent panels for studying both stable attitudes and time-sensitive public opinion. --- ### Text Data Integration Authors: Md Ataur Rahman, Dimitris Sacharidis, Oscar Romero, Sergi Nadal Published: 2026-03-28 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2603.27055v1 Data comes in many forms. From a shallow perspective, they can be viewed as being either in structured (e.g., as a relation, as key-value pairs) or unstructured (e.g., text, image) formats. So far, machines have been fairly good at processing and reasoning over structured data that follows a precise schema. However, the heterogeneity of data poses a significant challenge on how well diverse categories of data can be meaningfully stored and processed. Data Integration, a crucial part of the data engineering pipeline, addresses this by combining disparate data sources and providing unified data access to end-users. Until now, most data integration systems have leaned on only combining structured data sources. Nevertheless, unstructured data (a.k.a. free text) also contains a plethora of knowledge waiting to be utilized. Thus, in this chapter, we firstly make the case for the integration of textual data, to later present its challenges, state of the art and open problems. --- ### Restless bandits with imperfect binary feedback: PCL-indexability analysis and computation Authors: José Niño-Mora Published: 2026-03-27 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2606.11192v1 We study restless bandits with binary latent states and imperfect binary feedback, motivated by opportunistic spectrum access with sensing errors. For the associated belief-state model, we develop a partial conservation laws (PCL)-based analytical and computational framework for establishing indexability and evaluating the Whittle index, building on a verification theorem for real-state discounted restless bandits. The framework analyzes the stochastic dynamics via an associated deterministic skeleton, renewal decompositions, and combinatorics on words. It yields tractable expressions for discounted reward and resource metrics in several threshold regimes, enabling full verification of the PCL-indexability conditions there. For the remaining regime, where a complete analytic verification is not achieved in this paper, we derive efficient numerical schemes for computing the relevant marginal metrics and the marginal productivity (MP) index, which equals the Whittle index when those conditions hold. Extensive computational experiments provide strong evidence that these conditions also hold in that regime across broad parameter ranges and without the stringent parameter restrictions imposed in prior work. The experiments further show that theMP index policy typically outperforms standard benchmark policies, often by a substantial margin. --- ### Optimal Transport-based Permutation-Invariant Bayesian Optimization of Offshore Wind Farm Layouts Authors: Antonio Candelieri, Laurens Bliek Published: 2026-03-27 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.00009v1 Bayesian Optimization (BO) is widely and successfully adopted for solving optimization problems having an expensive-to-evaluate, black-box, and non-convex objective function. However, the vanilla BO algorithm is not able to exploit possible symmetries characterizing the target problem. An intuitive case is given by optimal location problems, whose decision variables refer to a finite set of points within a continuous space, with the order of points not affecting the value of the objective function. We refer to this setting as optimization over layouts to distinguish from optimization over point-clouds where, instead, the order of points counts. As an instance of optimization over layouts we consider a real-life industrial-relevant application, that is the optimization of the layout of an offshore wind farm: given identical wind turbines, switching any pair of them has not any effect on the annual energy production. Based on Optimal Transport theory, we propose a Permutation-Invariant BO approach, namely PIBO, proved to provide better wind farm layouts when compared to the vanilla BO approach while cutting computation time roughly in half. ---