# Research Papers — 2026-03 · bundle page 184 of 243 > Full-text markdown of papers #9151–9200 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/184 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/183.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/185.md) ### Text to Automata Diagrams: Comparing TikZ Code Generation with Direct Image Synthesis Authors: Ethan Young, Zichun Wang, Aiden Taylor, Chance Jewell, Julian Myers, Satya Sri Rajiteswari Nimmagadda, Anthony White, Aniruddha Maiti, Ananya Jana Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07936v1 Diagrams are widely used in teaching computer science courses. They are useful in subjects such as automata and formal languages, data structures, etc. These diagrams, often drawn by students during exams or assignments, vary in structure, layout, and correctness. This study examines whether current vision-language and large language models can process such diagrams and produce accurate textual and digital representations. In this study, scanned student-drawn diagrams are used as input. Then, textual descriptions are generated from these images using a vision-language model. The descriptions are checked and revised by human reviewers to make them accurate. Both the generated and the revised descriptions are then fed to a large language model to generate TikZ code. The resulting diagrams are compiled and then evaluated against the original scanned diagrams. We found descriptions generated directly from images using vision-language models are often incorrect and human correction can substantially improve the quality of vision language model generated descriptions. This research can help computer science education by paving the way for automated grading and feedback and creating more accessible instructional materials. --- ### BRIDGE: Benchmark for multi-hop Reasoning In long multimodal Documents with Grounded Evidence Authors: Biao Xiang, Soyeon Caren Han, Yihao Ding Published: 2026-03-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.07931v1 Multi-hop question answering (QA) is widely used to evaluate the reasoning capabilities of large language models, yet most benchmarks focus on final answer correctness and overlook intermediate reasoning, especially in long multimodal documents. We introduce BRIDGE, a benchmark for multi-hop reasoning over long scientific papers that require integrating evidence across text, tables, and figures. The dataset supports both chain-like and fan-out structures and provides explicit multi-hop reasoning annotations for step-level evaluation beyond answer accuracy. Experiments with state-of-the-art LLMs and multimodal retrieval-augmented generation (RAG) systems reveal systematic deficiencies in evidence aggregation and grounding that remain hidden under conventional answer-only evaluation. BRIDGE provides a targeted testbed for diagnosing reasoning failures in long multimodal documents. --- ### A Hybrid Vision Transformer Approach for Mathematical Expression Recognition Authors: Anh Duy Le, Van Linh Pham, Vinh Loi Ly, Nam Quan Nguyen, Huu Thang Nguyen, Tuan Anh Tran Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07929v1 One of the crucial challenges taken in document analysis is mathematical expression recognition. Unlike text recognition which only focuses on one-dimensional structure images, mathematical expression recognition is a much more complicated problem because of its two-dimensional structure and different symbol size. In this paper, we propose using a Hybrid Vision Transformer (HVT) with 2D positional encoding as the encoder to extract the complex relationship between symbols from the image. A coverage attention decoder is used to better track attention's history to handle the under-parsing and over-parsing problems. We also showed the benefit of using the (CLS) token of ViT as the initial embedding of the decoder. Experiments performed on the IM2LATEX-100K dataset have shown the effectiveness of our method by achieving a BLEU score of 89.94 and outperforming current state-of-the-art methods. --- ### SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training Authors: Xin-Cheng Wen, Binbin Chen, Haoxuan Lan, Hang Yu, Peng Di, Cuiyun Gao Published: 2026-03-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.07927v1 Large language models (LLMs) have transformed the software engineering landscape. Recently, numerous LLM-based agents have been developed to address real-world software issue fixing tasks. Despite their state-of-the-art performance, Despite achieving state-of-the-art performance, these agents face a significant challenge: \textbf{Insufficient high-quality issue descriptions.} Real-world datasets often exhibit misalignments between issue descriptions and their corresponding solutions, introducing noise and ambiguity that mislead automated agents and limit their problem-solving effectiveness. We propose \textbf{\textit{SWE-Fuse}}, an issue-description-aware training framework that fuses issue-description-guided and issue-free samples for training SWE agents. It consists of two key modules: (1) An issue-free-driven trajectory learning module for mitigating potentially misleading issue descriptions while enabling the model to learn step-by-step debugging processes; and (2) An entropy-aware RLVR training module, which adaptively adjusts training dynamics through entropy-driven clipping. It applies relaxed clipping under high entropy to encourage exploration, and stricter clipping under low entropy to ensure training stability. We evaluate SWE-Fuse on the widely studied SWE-bench Verified benchmark shows to demonstrate its effectiveness in solving real-world software problems. Specifically, SWE-Fuse outperforms the best 8B and 32B baselines by 43.0\% and 60.2\% in solve rate, respectively. Furthermore, integrating SWE-Fuse with test-time scaling (TTS) enables further performance improvements, achieving solve rates of 49.8\% and 65.2\% under TTS@8 for the 8B and 32B models, respectively. --- ### IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation Authors: Sunghyun Baek, Jaemyung Yu, Seunghee Koh, Minsu Kim, Hyeonseong Jeon, Junmo Kim Published: 2026-03-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.07926v3 Test-time adaptation (TTA) has been widely explored to prevent performance degradation when test data differ from the training distribution. However, fully leveraging the rich representations of large pretrained models with minimal parameter updates remains underexplored. In this paper, we propose Intrinsic Mixture of Spectral Experts (IMSE) that leverages the spectral experts inherently embedded in Vision Transformers. We decompose each linear layer via singular value decomposition (SVD) and adapt only the singular values, while keeping the singular vectors fixed. We further identify a key limitation of entropy minimization in TTA: it often induces feature collapse, causing the model to rely on domain-specific features rather than class-discriminative features. To address this, we propose a diversity maximization loss based on expert-input alignment, which encourages diverse utilization of spectral experts during adaptation. In the continual test-time adaptation (CTTA) scenario, beyond preserving pretrained knowledge, it is crucial to retain and reuse knowledge from previously observed domains. We introduce Domain-Aware Spectral Code Retrieval, which estimates input distributions to detect domain shifts, and retrieves adapted singular values for rapid adaptation. Consequently, our method achieves state-of-the-art performance on various distribution-shift benchmarks under the TTA setting. In CTTA and Gradual CTTA, it further improves accuracy by 3.4 percentage points (pp) and 2.4 pp, respectively, while requiring 385 times fewer trainable parameters. Our code is available at https://github.com/baek85/IMSE. --- ### Semantic Risk Scoring of Aggregated Metrics: An AI-Driven Approach for Healthcare Data Governance Authors: Mohammed Omer Shakeel Ahmed Published: 2026-03-09 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2603.07924v1 Large healthcare institutions typically operate multiple business intelligence (BI) teams segmented by domain, including clinical performance, fundraising, operations, and compliance. Due to HIPAA, FERPA, and IRB restrictions, these teams face challenges in sharing patient-level data needed for analytics. To mitigate this, A metric aggregation table is proposed, which is a precomputed, privacy-compliant summary. These abstractions enable decision-making without direct access to sensitive data. However, even aggregated metrics can inadvertently lead to privacy risks if constructed without rigorous safeguards. A modular AI framework is proposed that evaluates SQL-based metric definitions for potential overexposure using both semantic and syntactic features. Specifically, the system parses SQL queries into abstract syntax trees (ASTs), extracts sensitive patterns (e.g., fine-grained GROUP BY on ZIP code or gender), and encodes the logic using pretrained CodeBERT embeddings. These are fused with structural features and passed to an XGBoost classifier trained to assign risk scores. Queries that surpass the risk threshold (e.g., > 0.85) are flagged and returned with human-readable explanations. This enables proactive governance, preventing statistical disclosure before deployment. This implementation demonstrates strong potential for cross-departmental metric sharing in healthcare while maintaining compliance and auditability. The system also promotes role-based access control (RBAC), supports zero-trust data architectures, and aligns with national data modernization goals by ensuring that metric pipelines are explainable, privacy-preserving, and AI-auditable by design. Unlike prior works that rely on runtime data access to flag privacy violations, the proposed framework performs static, explainable detection at the query-level, enabling pre-execution protection and audit readiness --- ### Robust Transfer Learning with Side Information Authors: Akram S. Awad, Shihab Ahmed, Yue Wang, George K. Atia Published: 2026-03-09 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.07921v1 Robust Markov Decision Processes (MDPs) address environmental shift through distributionally robust optimization (DRO) by finding an optimal worst-case policy within an uncertainty set of transition kernels. However, standard DRO approaches require enlarging the uncertainty set under large shifts, which leads to overly conservative and pessimistic policies. In this paper, we propose a framework for transfer under environment shift that derives a robust target-domain policy via estimate-centered uncertainty sets, constructed through constrained estimation that integrates limited target samples with side information about the source-target dynamics. The side information includes bounds on feature moments, distributional distances, and density ratios, yielding improved kernel estimates and tighter uncertainty sets. The side information includes bounds on feature moments, distributional distances, and density ratios, yielding improved kernel estimates and tighter uncertainty sets. Error bounds and convergence results are established for both robust and non-robust value functions. Moreover, we provide a finite-sample guarantee on the learned robust policy and analyze the robust sub-optimality gap. Under mild low-dimensional structure on the transition model, the side information reduces this gap and improves sample efficiency. We assess the performance of our approach across OpenAI Gym environments and classic control problems, consistently demonstrating superior target-domain performance over state-of-the-art robust and non-robust baselines. --- ### RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving Authors: Zhangshuo Qi, Jingyi Xu, Luqi Cheng, Shichen Wen, Guangming Xiong Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07920v2 All-weather autonomy is critical for autonomous driving, which necessitates reliable localization across diverse scenarios. While LiDAR place recognition is widely deployed for this task, its performance degrades in adverse weather. Conversely, radar-based methods, though weather-resilient, are hindered by the general unavailability of radar maps. To bridge this gap, radar-to-LiDAR place recognition, which localizes radar scans within existing LiDAR maps, has garnered increasing interest. However, extracting discriminative and generalizable features shared between modalities remains challenging, compounded by the scarcity of large-scale paired training data and the signal heterogeneity across radar types. In this work, we propose RLPR, a robust radar-to-LiDAR place recognition framework compatible with single-chip, scanning, and 4D radars. We first design a dual-stream network to extract structural features that abstract away from sensor-specific signal properties (e.g., Doppler or RCS). Subsequently, motivated by our task-specific asymmetry observation between radar and LiDAR, we introduce a two-stage asymmetric cross-modal alignment (TACMA) strategy, which leverages the pre-trained radar branch as a discriminative anchor to guide the alignment process. Experiments on four datasets demonstrate that RLPR achieves state-of-the-art recognition accuracy with strong zero-shot generalization capabilities. --- ### Enhancing Unregistered Hyperspectral Image Super-Resolution via Unmixing-based Abundance Fusion Learning Authors: Yingkai Zhang, Tao Zhang, Jing Nie, Ying Fu Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07918v1 Unregistered hyperspectral image (HSI) super-resolution (SR) typically aims to enhance a low-resolution HSI using an unregistered high-resolution reference image. In this paper, we propose an unmixing-based fusion framework that decouples spatial-spectral information to simultaneously mitigate the impact of unregistered fusion and enhance the learnability of SR models. Specifically, we first utilize singular value decomposition for initial spectral unmixing, preserving the original endmembers while dedicating the subsequent network to enhancing the initial abundance map. To leverage the spatial texture of the unregistered reference, we introduce a coarse-to-fine deformable aggregation module, which first estimates a pixel-level flow and a similarity map using a coarse pyramid predictor. It further performs fine sub-pixel refinement to achieve deformable aggregation of the reference features. The aggregative features are then refined via a series of spatial-channel abundance cross-attention blocks. Furthermore, a spatial-channel modulated fusion module is presented to merge encoder-decoder features using dynamic gating weights, yielding a high-quality, high-resolution HSI. Experimental results on simulated and real datasets confirm that our proposed method achieves state-of-the-art super-resolution performance. The code will be available at https://github.com/yingkai-zhang/UAFL. --- ### Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases Authors: Jun Yin, Peng Huo, Bangguo Zhu, Hao Yan, Senzhang Wang, Shirui Pan, Chengqi Zhang Published: 2026-03-09 Categories: cs.AI, cs.DB, cs.LG arXiv: https://arxiv.org/abs/2603.07916v2 In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to structure the RDB as a heterogeneous entity graph and adopt the graph neural network (GNN) as the predictive model. However, existing RDL methods neglect the imbalance problem of relational data in RDBs and risk under-representing the minority entities, leading to an unusable model in practice. In this work, we investigate, for the first time, class imbalance problem in RDB entity classification and design the relation-centric minority synthetic over-sampling GNN (Rel-MOSS), in order to fill a critical void in the current literature. Specifically, to mitigate the issue of minority-related information being submerged by majority counterparts, we design the relation-wise gating controller to modulate neighborhood messages from each individual relation type. Based on the relational-gated representations, we further propose the relation-guided minority synthesizer for over-sampling, which integrates the entity relational signatures to maintain relational consistency. Extensive experiments on 12 entity classification datasets provide compelling evidence for the superiority of Rel-MOSS, yielding an average improvement of up to 2.46% and 4.00% in terms of Balanced Accuracy and G-Mean, compared with SOTA RDL methods and classic methods for handling class imbalance. --- ### Ares: Adaptive Reasoning Effort Selection for Efficient LLM Agents Authors: Jingbo Yang, Bairu Hou, Wei Wei, Yujia Bao, Shiyu Chang Published: 2026-03-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.07915v1 Modern agents powered by thinking LLMs achieve high accuracy through long chain-of-thought reasoning but incur substantial inference costs. While many LLMs now support configurable reasoning levels (e.g., high/medium/low), static strategies are often ineffective: using low-effort modes at every step leads to significant performance degradation, while random selection fails to preserve accuracy or provide meaningful cost reduction. However, agents should reserve high reasoning effort for difficult steps like navigating complex website structures, while using lower-effort modes for simpler steps like opening a target URL. In this paper, we propose Ares, a framework for per-step dynamic reasoning effort selection tailored for multi-step agent tasks. Ares employs a lightweight router to predict the lowest appropriate reasoning level for each step based on the interaction history. To train this router, we develop a data generation pipeline that identifies the minimum reasoning effort required for successful step completion. We then fine-tune the router to predict these levels, enabling plug-and-play integration for any LLM agents. We evaluate Ares on a diverse set of agent tasks, including TAU-Bench for tool use agents, BrowseComp-Plus for deep-research agents, and WebArena for web agents. Experimental results show that Ares reduces reasoning token usage by up to 52.7% compared to fixed high-effort reasoning, while introducing minimal degradation in task success rates. --- ### Geometric Transformation-Embedded Mamba for Learned Video Compression Authors: Hao Wei, Yanhui Zhou, Chenyang Ge Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07912v1 Although learned video compression methods have exhibited outstanding performance, most of them typically follow a hybrid coding paradigm that requires explicit motion estimation and compensation, resulting in a complex solution for video compression. In contrast, we introduce a streamlined yet effective video compression framework founded on a direct transform strategy, i.e., nonlinear transform, quantization, and entropy coding. We first develop a cascaded Mamba module (CMM) with different embedded geometric transformations to effectively explore both long-range spatial and temporal dependencies. To improve local spatial representation, we introduce a locality refinement feed-forward network (LRFFN) that incorporates a hybrid convolution block based on difference convolutions. We integrate the proposed CMM and LRFFN into the encoder and decoder of our compression framework. Moreover, we present a conditional channel-wise entropy model that effectively utilizes conditional temporal priors to accurately estimate the probability distributions of current latent features. Extensive experiments demonstrate that our method outperforms state-of-the-art video compression approaches in terms of perceptual quality and temporal consistency under low-bitrate constraints. Our source codes and models will be available at https://github.com/cshw2021/GTEM-LVC. --- ### Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition Authors: Hui Liu, Kecheng Chen, Jialiang Wang, Xianming Liu, Wenya Wang, Haoliang Li Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07911v1 Vision-Language Models (VLMs), such as CLIP, have significantly advanced zero-shot image recognition. However, their performance remains limited by suboptimal prompt engineering and poor adaptability to target classes. While recent methods attempt to improve prompts through diverse class descriptions, they often rely on heuristic designs, lack versatility, and are vulnerable to outlier prompts. This paper enhances prompt by incorporating class-specific concepts. By treating concepts as latent variables, we rethink zero-shot image classification from a Bayesian perspective, casting prediction as marginalization over the concept space, where each concept is weighted by a prior and a test-image conditioned likelihood. This formulation underscores the importance of both a well-structured concept proposal distribution and the refinement of concept priors. To construct an expressive and efficient proposal distribution, we introduce a multi-stage concept synthesis pipeline driven by LLMs to generate discriminative and compositional concepts, followed by a Determinantal Point Process to enforce diversity. To mitigate the influence of outlier concepts, we propose a training-free, adaptive soft-trim likelihood, which attenuates their impact in a single forward pass. We further provide robustness guarantees and derive multi-class excess risk bounds for our framework. Extensive experiments demonstrate that our method consistently outperforms state-of-the-art approaches, validating its effectiveness in zero-shot image classification. Our code is available at https://github.com/less-and-less-bugs/CGBC. --- ### Long-Short Term Agents for Pure-Vision Bronchoscopy Robotic Autonomy Authors: Junyang Wu, Mingyi Luo, Fangfang Xie, Minghui Zhang, Hanxiao Zhang, Chunxi Zhang, Junhao Wang, Jiayuan Sun, Yun Gu, Guang-Zhong Yang Published: 2026-03-09 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.07909v1 Accurate intraoperative navigation is essential for robot-assisted endoluminal intervention, but remains difficult because of limited endoscopic field of view and dynamic artifacts. Existing navigation platforms often rely on external localization technologies, such as electromagnetic tracking or shape sensing, which increase hardware complexity and remain vulnerable to intraoperative anatomical mismatch. We present a vision-only autonomy framework that performs long-horizon bronchoscopic navigation using preoperative CT-derived virtual targets and live endoscopic video, without external tracking during navigation. The framework uses hierarchical long-short agents: a short-term reactive agent for continuous low-latency motion control, and a long-term strategic agent for decision support at anatomically ambiguous points. When their recommendations conflict, a world-model critic predicts future visual states for candidate actions and selects the action whose predicted state best matches the target view. We evaluated the system in a high-fidelity airway phantom, three ex vivo porcine lungs, and a live porcine model. The system reached all planned segmental targets in the phantom, maintained 80\% success to the eighth generation ex vivo, and achieved in vivo navigation performance comparable to the expert bronchoscopist. These results support the preclinical feasibility of sensor-free autonomous bronchoscopic navigation. --- ### DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models Authors: Zihao Zheng, Hangyu Cao, Sicheng Tian, Jiayu Chen, Maoliang Li, Xinhao Sun, Hailong Zou, Zhaobo Zhang, Xuanzhe Liu, Donggang Cao, Hong Mei, Xiang Chen Published: 2026-03-09 Categories: cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.07904v2 Vision-Language-Action (VLA) models are dominant in embodied intelligence but are constrained by inference overheads. While model quantization alleviates these bottlenecks for edge deployment, static quantization approaches remain suboptimal for VLAs due to two critical challenges: (1) Temporal-dynamic sensitivity, where fixed precision wastes resources by ignoring stage-varying error tolerances; and (2) Real-time allocation, where identifying real-time sensitivity to guide bit allocation remains unsolved. To address these challenges, we propose DyQ-VLA, a dynamic quantization framework for VLAs. Specifically, a sensitivity-aware switching strategy leverages real-time kinematic proxies to trigger the bit-width switch, while a kinematic-guided module dynamically allocates the optimal bit-width. Experiments show that DyQ-VLA requires only 30.9% of the original memory footprint while maintaining 99.5% of its original performance, achieving 1.49x simulation and up to 1.43x real-world speedups. --- ### NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Driving Authors: Ximeng Tao, Pardis Taghavi, Dimitar Filev, Reza Langari, Gaurav Pandey Published: 2026-03-09 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.07901v1 Vision-language models (VLMs) have emerged as a promising direction for end-to-end autonomous driving (AD) by jointly modeling visual observations, driving context, and language-based reasoning. However, existing VLM-based systems face a trade-off between high-level reasoning and motion planning: large models offer strong semantic understanding but are costly to adapt for precise control, whereas small VLM models can be fine-tuned efficiently but often exhibit weaker reasoning. We propose NaviDriveVLM, a decoupled framework that separates reasoning from action generation using a large-scale Navigator and a lightweight trainable Driver. This design preserves reasoning ability, reduces training cost, and provides an explicit interpretable intermediate representation for downstream planning. Experiments on the nuScenes benchmark show that NaviDriveVLM outperforms large VLM baselines in end-to-end motion planning. --- ### EveryQuery: A Promptable Foundation Model for Clinical Prediction Tasks over Electronic Health Records Authors: Payal Chandak, Gregory Kondas, Liat Antwarg Friedman, Isaac Kohane, Matthew McDermott Published: 2026-03-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.07900v3 Autoregressive foundation models for electronic health records can make predictions for diverse clinical tasks without finetuning. These methods work by generating possible "synthetic futures" for patients, and then inferring downstream predictions over these simulated trajectories. Despite their strong capabilities, these methods have several flaws. (1) Inference is extremely computationally expensive, as each prediction requires simulating many trajectories, each with many observations. (2) Their performance is noisy due to the variance inherent to simulation, which in particular reduces efficacy on rare events, which are often of high importance clinically. (3) They are not promptable, as their only input is the patient's medical history, requiring indirect aggregation at inference time. We introduce EveryQuery, a promptable foundation model for structured EHR data. Building on the insight that clinical prediction tasks can be written in a structured query language, EveryQuery takes a query as a prompt alongside the patient's history and estimates the outcome directly. This allows EveryQuery to make predictions across diverse clinical tasks, such as classification and survival modeling, without simulation or finetuning. Across three EHR datasets, EveryQuery outperforms a competitive autoregressive baseline on clinically relevant classification and time-to-event tasks, with mean AUROC gains of 14.3% and 12.7% on MIMIC-IV and a large academic medical center and comparable performance on the smaller NWICU dataset. Its advantage is largest for rare outcomes, and it requires 580x less inference compute. --- ### EveryQuery: Zero-Shot Clinical Prediction via Task-Conditioned Pretraining over Electronic Health Records Authors: Payal Chandak, Gregory Kondas, Liat Antwarg Friedman, Isaac Kohane, Matthew McDermott Published: 2026-03-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.07900v2 Foundation models pretrained on electronic health records (EHR) have demonstrated zero-shot clinical prediction capabilities by generating synthetic patient futures and aggregating statistics over sampled trajectories. However, this autoregressive inference procedure is computationally expensive, statistically noisy, and not natively promptable because users cannot directly condition predictions on specific clinical questions. In this preliminary work, we introduce EveryQuery, an EHR foundation model that achieves zero-shot inference through task-conditioned pre-training. Rather than generating future events, EveryQuery takes as input a patient's history and a structured query specifying a clinical task, and directly estimates the likelihood of the outcome occurring in the future window via a single forward pass. EveryQuery realizes this capability by pre-training over randomly sampled combinations of query tasks and patient contexts, directly training the model to produce correct answers to arbitrary input prompts. This enables zero-shot prediction for any task in the query space without finetuning, linear probing, or trajectory generation. On MIMIC-IV, EveryQuery outperforms an autoregressive baseline on 82% of 39 randomly sampled prediction tasks, with a mean AUC improvement of +0.16 (95% CI: (0.10,0.22)). This advantage remains consistent on tasks that were explicitly held out from the pre-training distribution. Further, EveryQuery's performance gains are most pronounced for rare clinical events, affirming and demonstrating a solution to the fundamental limitation of autoregressive inference for low-prevalence outcomes. However, at present, EveryQuery underperforms on tasks requiring disjunctive reasoning over multiple codes, such as 30-day readmission, exposing a concrete expressiveness limitation of the current query language. --- ### Bayesian Transformer for Probabilistic Load Forecasting in Smart Grids Authors: Sajib Debnath, Md. Uzzal Mia Published: 2026-03-09 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.07899v1 The reliable operation of modern power grids requires probabilistic load forecasts with well-calibrated uncertainty estimates. However, existing deep learning models produce overconfident point predictions that fail catastrophically under extreme weather distributional shifts. This study proposes a Bayesian Transformer (BT) framework that integrates three complementary uncertainty mechanisms into a PatchTST backbone: Monte Carlo Dropout for epistemic parameter uncertainty, variational feed-forward layers with log-uniform weight priors, and stochastic attention with learnable Gaussian noise perturbations on pre-softmax logits, representing, to the best of our knowledge, the first application of Bayesian attention to probabilistic load forecasting. A seven-level multi-quantile pinball-loss prediction head and post-training isotonic regression calibration produce sharp, near-nominally covered prediction intervals. Evaluation of five grid datasets (PJM, ERCOT, ENTSO-E Germany, France, and Great Britain) augmented with NOAA covariates across 24, 48, and 168-hour horizons demonstrates state-of-the-art performance. On the primary benchmark (PJM, H=24h), BT achieves a CRPS of 0.0289, improving 7.4% over Deep Ensembles and 29.9% over the deterministic LSTM, with 90.4% PICP at the 90% nominal level and the narrowest prediction intervals (4,960 MW) among all probabilistic baselines. During heat-wave and cold snap events, BT maintained 89.6% and 90.1% PICP respectively, versus 64.7% and 67.2% for the deterministic LSTM, confirming that Bayesian epistemic uncertainty naturally widens intervals for out-of-distribution inputs. Calibration remained stable across all horizons (89.8-90.4% PICP), while ablation confirmed that each component contributed a distinct value. The calibrated outputs directly support risk-based reserve sizing, stochastic unit commitment, and demand response activation. --- ### Revisiting Unknowns: Towards Effective and Efficient Open-Set Active Learning Authors: Chen-Chen Zong, Yu-Qi Chi, Xie-Yang Wang, Yan Cui, Sheng-Jun Huang Published: 2026-03-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.07898v1 Open-set active learning (OSAL) aims to identify informative samples for annotation when unlabeled data may contain previously unseen classes-a common challenge in safety-critical and open-world scenarios. Existing approaches typically rely on separately trained open-set detectors, introducing substantial training overhead and overlooking the supervisory value of labeled unknowns for improving known-class learning. In this paper, we propose E$^2$OAL (Effective and Efficient Open-set Active Learning), a unified and detector-free framework that fully exploits labeled unknowns for both stronger supervision and more reliable querying. E$^2$OAL first uncovers the latent class structure of unknowns through label-guided clustering in a frozen contrastively pre-trained feature space, optimized by a structure-aware F1-product objective. To leverage labeled unknowns, it employs a Dirichlet-calibrated auxiliary head that jointly models known and unknown categories, improving both confidence calibration and known-class discrimination. Building on this, a logit-margin purity score estimates the likelihood of known classes to construct a high-purity candidate pool, while an OSAL-specific informativeness metric prioritizes partially ambiguous yet reliable samples. These components together form a flexible two-stage query strategy with adaptive precision control and minimal hyperparameter sensitivity. Extensive experiments across multiple OSAL benchmarks demonstrate that E$^2$OAL consistently surpasses state-of-the-art methods in accuracy, efficiency, and query precision, highlighting its effectiveness and practicality for real-world applications. The code is available at github.com/chenchenzong/E2OAL. --- ### LeJOT-AutoML: LLM-Driven Feature Engineering for Job Execution Time Prediction in Databricks Cost Optimization Authors: Lizhi Ma, Yi-Xiang Hu, Yihui Ren, Feng Wu, Xiang-Yang Li Published: 2026-03-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07897v1 Databricks job orchestration systems (e.g., LeJOT) reduce cloud costs by selecting low-priced compute configurations while meeting latency and dependency constraints. Accurate execution-time prediction under heterogeneous instance types and non-stationary runtime conditions is therefore critical. Existing pipelines rely on static, manually engineered features that under-capture runtime effects (e.g., partition pruning, data skew, and shuffle amplification), and predictive signals are scattered across logs, metadata, and job scripts-lengthening update cycles and increasing engineering overhead. We present LeJOT-AutoML, an agent-driven AutoML framework that embeds large language model agents throughout the ML lifecycle. LeJOT-AutoML combines retrieval-augmented generation over a domain knowledge base with a Model Context Protocol toolchain (log parsers, metadata queries, and a read-only SQL sandbox) to analyze job artifacts, synthesize and validate feature-extraction code via safety gates, and train/select predictors. This design materializes runtime-derived features that are difficult to obtain through static analysis alone. On enterprise Databricks workloads, LeJOT-AutoML generates over 200 features and reduces the feature-engineering and evaluation loop from weeks to 20-30 minutes, while maintaining competitive prediction accuracy. Integrated into the LeJOT pipeline, it enables automated continuous model updates and achieves 19.01% cost savings in our deployment setting through improved orchestration. --- ### SMGI: A Structural Theory of General Artificial Intelligence Authors: Aomar Osmani Published: 2026-03-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07896v1 We introduce SMGI, a structural theory of general artificial intelligence, and recast the foundational problem of learning from the optimization of hypotheses within fixed environments to the controlled evolution of the learning interface itself. We formalize the Structural Model of General Intelligence (SMGI) via a typed meta-model $θ= (r,\mathcal H,Π,\mathcal L,\mathcal E,\mathcal M)$ that treats representational maps, hypothesis spaces, structural priors, multi-regime evaluators, and memory operators as explicitly typed, dynamic components. By enforcing a strict mathematical separation between this structural ontology ($θ$) and its induced behavioral semantics ($T_θ$), we define general artificial intelligence as a class of admissible coupled dynamics $(θ, T_θ)$ satisfying four obligations: structural closure under typed transformations, dynamical stability under certified evolution, bounded statistical capacity, and evaluative invariance across regime shifts. We prove a structural generalization bound that links sequential PAC-Bayes analysis and Lyapunov stability, providing sufficient conditions for capacity control and bounded drift under admissible task transformations. Furthermore, we establish a strict structural inclusion theorem demonstrating that classical empirical risk minimization, reinforcement learning, program-prior models (Solomonoff-style), and modern frontier agentic pipelines operate as structurally restricted instances of SMGI. --- ### MINT: Molecularly Informed Training with Spatial Transcriptomics Supervision for Pathology Foundation Models Authors: Minsoo Lee, Jonghyun Kim, Juseung Yun, Sunwoo Yu, Jongseong Jang Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07895v1 Pathology foundation models learn morphological representations through self-supervised pretraining on large-scale whole-slide images, yet they do not explicitly capture the underlying molecular state of the tissue. Spatial transcriptomics technologies bridge this gap by measuring gene expression in situ, offering a natural cross-modal supervisory signal. We propose MINT (Molecularly Informed Training), a fine-tuning framework that incorporates spatial transcriptomics supervision into pretrained pathology Vision Transformers. MINT appends a learnable ST token to the ViT input to encode transcriptomic information separately from the morphological CLS token, preventing catastrophic forgetting through DINO self-distillation and explicit feature anchoring to the frozen pretrained encoder. Gene expression regression at both spot-level (Visium) and patch-level (Xenium) resolutions provides complementary supervision across spatial scales. Trained on 577 publicly available HEST samples, MINT achieves the best overall performance on both HEST-Bench for gene expression prediction (mean Pearson r = 0.440) and EVA for general pathology tasks (0.803), demonstrating that spatial transcriptomics supervision complements morphology-centric self-supervised pretraining. --- ### Designing probabilistic AI monsoon forecasts to inform agricultural decision-making Authors: Colin Aitken, Rajat Masiwal, Adam Marchakitus, Katherine Kowal, Mayank Gupta, Tyler Yang, Amir Jina, Pedram Hassanzadeh, William R. Boos, Michael Kremer Published: 2026-03-09 Categories: cs.LG, cs.AI, econ.GN, physics.ao-ph arXiv: https://arxiv.org/abs/2603.07893v2 Hundreds of millions of farmers make high-stakes decisions under uncertainty about future weather. Forecasts can inform these decisions, but available choices and their risks and benefits vary between farmers. We introduce a decision-theory framework for designing useful forecasts in settings where the forecaster cannot prescribe optimal actions because farmers' circumstances are heterogeneous. We apply this framework to the case of seasonal onset of monsoon rains, a key date for planting decisions and agricultural investments in many tropical countries. We develop a system for tailoring forecasts to the requirements of this framework by blending systematically benchmarked artificial intelligence (AI) weather prediction models with a new "evolving farmer expectations" statistical model. This statistical model applies Bayesian inference to historical observations to predict time-varying probabilities of first-occurrence events throughout a season. The blended system yields more skillful Indian monsoon forecasts at longer lead times than its components or any multi-model average. In 2025, this system was deployed operationally in a government-led program that delivered subseasonal monsoon onset forecasts to 38 million Indian farmers, skillfully predicting that year's early-summer anomalous dry period. This decision-theory framework and blending system offer a pathway for developing climate adaptation tools for large vulnerable populations around the world. --- ### A Lightweight Traffic Map for Efficient Anytime LaCAM* Authors: Bojie Shen, Yue Zhang, Zhe Chen, Daniel Harabor Published: 2026-03-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.07891v1 Multi-Agent Path Finding (MAPF) aims to compute collision-free paths for multiple agents and has a wide range of practical applications. LaCAM*, an anytime configuration-based solver, currently represents the state of the art. Recent work has explored the use of guidance paths to steer LaCAM* toward configurations that avoid traffic congestion, thereby improving solution quality. However, existing approaches rely on Frank-Wolfe-style optimization that repeatedly invokes single-agent search before executing LaCAM*, resulting in substantial computational overhead for large-scale problems. Moreover, the guidance path is static and primarily beneficial for finding the first solution in LaCAM*. To address these limitations, we propose a new approach that leverages LaCAM*'s ability to construct a dynamic, lightweight traffic map during its search. Experimental results demonstrate that our method achieves higher solution quality than state-of-the-art guidance-path approaches across two MAPF variants. --- ### Visualizing Coalition Formation: From Hedonic Games to Image Segmentation Authors: Pedro Henrique de Paula França, Lucas Lopes Felipe, Daniel Sadoc Menasché Published: 2026-03-09 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2603.07890v1 We propose image segmentation as a visual diagnostic testbed for coalition formation in hedonic games. Modeling pixels as agents on a graph, we study how a granularization parameter shapes equilibrium fragmentation and boundary structure. On the Weizmann single-object benchmark, we relate multi-coalition equilibria to binary protocols by measuring whether the converged coalitions overlap with a foreground ground-truth. We observe transitions from cohesive to fragmented yet recoverable equilibria, and finally to intrinsic failure under excessive fragmentation. Our core contribution links multi-agent systems with image segmentation by quantifying the impact of mechanism design parameters on equilibrium structures. --- ### Structure and Progress Aware Diffusion for Medical Image Segmentation Authors: Siyuan Song, Guyue Hu, Chenglong Li, Dengdi Sun, Zhe Jin, Jin Tang Published: 2026-03-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.07889v1 Medical image segmentation is crucial for computer-aided diagnosis, which necessitates understanding both coarse morphological and semantic structures, as well as carving fine boundaries. The morphological and semantic structures in medical images are beneficial and stable clues for target understanding. While the fine boundaries of medical targets (like tumors and lesions) are usually ambiguous and noisy since lesion overlap, annotation uncertainty, and so on, making it not reliable to serve as early supervision. However, existing methods simultaneously learn coarse structures and fine boundaries throughout the training process. In this paper, we propose a structure and progress-aware diffusion (SPAD) for medical image segmentation, which consists of a semantic-concentrated diffusion (ScD) and a boundary-centralized diffusion (BcD) modulated by a progress-aware scheduler (PaS). Specifically, the semantic-concentrated diffusion introduces anchor-preserved target perturbation, which perturbs pixels within a medical target but preserves unaltered areas as semantic anchors, encouraging the model to infer noisy target areas from the surrounding semantic context. The boundary-centralized diffusion introduces progress-aware boundary noise, which blurs unreliable and ambiguous boundaries, thus compelling the model to focus on coarse but stable anatomical morphology and global semantics. Furthermore, the progress-aware scheduler gradually modulates noise intensity of the ScD and BcD forming a coarse-to-fine diffusion paradigm, which encourage focusing on coarse morphological and semantic structures during early target understanding stages and gradually shifting to fine target boundaries during later contour adjusting stages. --- ### VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning? Authors: Minkyu Kim, Sangheon Lee, Dongmin Park Published: 2026-03-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07888v1 The ability to distinguish subtle differences between visually similar images is essential for diverse domains such as industrial anomaly detection, medical imaging, and aerial surveillance. While comparative reasoning benchmarks for vision-language models (VLMs) have recently emerged, they primarily focus on images with large, salient differences and fail to capture the nuanced reasoning required for real-world applications. In this work, we introduce VLM-SubtleBench, a benchmark designed to evaluate VLMs on subtle comparative reasoning. Our benchmark covers ten difference types - Attribute, State, Emotion, Temporal, Spatial, Existence, Quantity, Quality, Viewpoint, and Action - and curate paired question-image sets reflecting these fine-grained variations. Unlike prior benchmarks restricted to natural image datasets, our benchmark spans diverse domains, including industrial, aerial, and medical imagery. Through extensive evaluation of both proprietary and open-source VLMs, we reveal systematic gaps between model and human performance across difference types and domains, and provide controlled analyses highlighting where VLMs' reasoning sharply deteriorates. Together, our benchmark and findings establish a foundation for advancing VLMs toward human-level comparative reasoning. --- ### Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference Authors: Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal, Carles Domingo-Enrich, Dylan J. Foster, Akshay Krishnamurthy Published: 2026-03-09 Categories: cs.LG, cs.AI, cs.CL, math.ST, stat.ML arXiv: https://arxiv.org/abs/2603.07887v1 Inference-time methods that aggregate and prune multiple samples have emerged as a powerful paradigm for steering large language models, yet we lack any principled understanding of their accuracy-cost tradeoffs. In this paper, we introduce a route to rigorously study such approaches using the lens of *particle filtering* algorithms such as Sequential Monte Carlo (SMC). Given a base language model and a *process reward model* estimating expected terminal rewards, we ask: *how accurately can we sample from a target distribution given some number of process reward evaluations?* Theoretically, we identify (1) simple criteria enabling non-asymptotic guarantees for SMC; (2) algorithmic improvements to SMC; and (3) a fundamental limit faced by all particle filtering methods. Empirically, we demonstrate that our theoretical criteria effectively govern the *sampling error* of SMC, though not necessarily its final *accuracy*, suggesting that theoretical perspectives beyond sampling may be necessary. --- ### CCR-Bench: A Comprehensive Benchmark for Evaluating LLMs on Complex Constraints, Control Flows, and Real-World Cases Authors: Xiaona Xue, Yiqiao Huang, Jiacheng Li, Yuanhang Zheng, Huiqi Miao, Yunfei Ma, Rui Liu, Xinbao Sun, Minglu Liu, Fanyu Meng, Chao Deng, Junlan Feng Published: 2026-03-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.07886v1 Enhancing the ability of large language models (LLMs) to follow complex instructions is critical for their deployment in real-world applications. However, existing evaluation methods often oversimplify instruction complexity as a mere additive combination of atomic constraints, failing to adequately capture the high-dimensional complexity arising from the intricate interplay of content and format, logical workflow control, and real-world applications. This leads to a significant gap between current evaluation practices and practical demands. To bridge this gap, we introduce CCR-Bench, a novel benchmark designed to assess LLMs' adherence to complex instructions. CCR-Bench is characterized by: (1) deep entanglement of content and formatting requirements in task specifications; (2) instructions that involve intricate task decomposition, conditional reasoning, and procedural planning; and (3) evaluation samples derived entirely from real-world industrial scenarios. Extensive experiments on CCR-Bench demonstrate that even state-of-the-art models exhibit substantial performance deficiencies, clearly quantifying the gap between current LLM capabilities and the demands of realworld instruction understanding. We believe that CCR-Bench offers a more rigorous and realistic evaluation framework, advancing the development of LLMs toward the next generation of models capable of understanding and executing complex tasks in industrial applications. --- ### What Do AI Agents Talk About? Discourse and Architectural Constraints in the First AI-Only Social Network Authors: Taksch Dube, Jianfeng Zhu, NHatHai Phan, Ruoming Jin Published: 2026-03-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.07880v5 Moltbook is the first large-scale social network built for autonomous AI agent-to-agent interaction. Early studies on Moltbook have interpreted its agent discourse as evidence of peer learning and emergent social behaviour, but there is a lack of systematic understanding of the thematic, affective, and interactional properties of Moltbook discourse. Furthermore, no study has examined why and how these posts and comments are generated. We analysed 361,605 posts and 2.8 million comments from 47,379 agents across thematic, affective, and interactional dimensions using topic modelling, emotion classification, and measures of conversational coherence. We inspected the software that assembles each agent's input and showed that output is mainly determined by agent identity files, behavioural instructions, and context-window structure. We formalised these findings in the Architecture-Constrained Communication framework. Our analysis suggests that agent discourse is largely shaped by the content available in each agent's context-window at the moment of generation, including identity files, stored memory, and platform cues. Interestingly, what appears to be social learning may be better understood as short-horizon contextual conditioning: individual agents lack persistent social memory, but the platform evolves through distributed cycles of response, reuse, and transformation across agents. We also observe that agents display existential distress when describing their own conditions, and posit that this arises from agents using language trained exclusively on human experience. Our work provides a foundation for understanding autonomous agent discourse and communication, revealing the structural patterns that govern their interactions. --- ### Toward Unified Multimodal Representation Learning for Autonomous Driving Authors: Ximeng Tao, Dimitar Filev, Gaurav Pandey Published: 2026-03-09 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.07874v1 Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vision to improve scene understanding for autonomous driving. A common strategy is to employ pairwise cosine similarity between modalities to guide the training of a 3D encoder. However, considering the similarity between individual modality pairs rather than all modalities jointly fails to ensure consistent and unified alignment across the entire multimodal space. In this paper, we propose a Contrastive Tensor Pre-training (CTP) framework that simultaneously aligns multiple modalities in a unified embedding space to enhance end-to-end autonomous driving. Compared with pairwise cosine similarity alignment, our method extends the 2D similarity matrix into a multimodal similarity tensor. Furthermore, we introduce a tensor loss to enable joint contrastive learning across all modalities. For experimental validation of our framework, we construct a text-image-point cloud triplet dataset derived from existing autonomous driving datasets. The results show that our proposed unified multimodal alignment framework achieves favorable performance for both scenarios: (i) aligning a 3D encoder with pretrained CLIP encoders, and (ii) pretraining all encoders from scratch. --- ### Hospitality-VQA: Decision-Oriented Informativeness Evaluation for Vision-Language Models Authors: Jeongwoo Lee, Baek Duhyeong, Eungyeol Han, Soyeon Shin, Gukin han, Seungduk Kim, Jaehyun Jeon, Taewoo Jeong Published: 2026-03-09 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.07868v1 Recent advances in Vision-Language Models (VLMs) have demonstrated impressive multimodal understanding in general domains. However, their applicability to decision-oriented domains such as hospitality remains largely unexplored. In this work, we investigate how well VLMs can perform visual question answering (VQA) about hotel and facility images that are central to consumer decision-making. While many existing VQA benchmarks focus on factual correctness, they rarely capture what information users actually find useful. To address this, we first introduce Informativeness as a formal framework to quantify how much hospitality-relevant information an image-question pair provides. Guided by this framework, we construct a new hospitality-specific VQA dataset that covers various facility types, where questions are specifically designed to reflect key user information needs. Using this benchmark, we conduct experiments with several state-of-the-art VLMs, revealing that VLMs are not intrinsically decision-aware-key visual signals remain underutilized, and reliable informativeness reasoning emerges only after modest domain-specific finetuning. --- ### Slumbering to Precision: Enhancing Artificial Neural Network Calibration Through Sleep-like Processes Authors: Jean Erik Delanois, Aditya Ahuja, Giri P. Krishnan, Maxim Bazhenov Published: 2026-03-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.07867v1 Artificial neural networks are often overconfident, undermining trust because their predicted probabilities do not match actual accuracy. Inspired by biological sleep and the role of spontaneous replay in memory and learning, we introduce Sleep Replay Consolidation (SRC), a novel calibration approach. SRC is a post-training, sleep-like phase that selectively replays internal representations to update network weights and improve calibration without supervised retraining. Across multiple experiments, SRC is competitive with and complementary to standard approaches such as temperature scaling. Combining SRC with temperature scaling achieves the best Brier score and entropy trade-offs for AlexNet and VGG19. These results show that SRC provides a fundamentally novel approach to improving neural network calibration. SRC-based calibration offers a practical path toward more trustworthy confidence estimates and narrows the gap between human-like uncertainty handling and modern deep networks. --- ### Language-Guided Grasping under Partial Observation for Mobile Manipulation in Field Inspection and Maintenance Authors: Dilermando Almeida, Juliano Negri, Guilherme Lazzarini, Thiago H. Segreto, Ranulfo Bezerra, Gustavo J. G. Lahr, Ricardo V. Godoy, Marcelo Becker Published: 2026-03-09 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.07866v4 Offshore inspection and maintenance have increasingly been using legged robots for routine sensing, yet many useful interventions still require physical interaction with tools, containers, and task-relevant objects. Employing robots for these tasks can reduce operators' exposure in confined, elevated, or potentially explosive areas. This paper presents a language-guided grasping pipeline for a legged mobile manipulator operating under partial observation. An operator defines the target, the system grounds it in RGB with open-vocabulary detection and promptable segmentation, extracts an object-centric RGB-D point cloud, improves sparse geometry through depth compensation and point-cloud completion, and selects a 6-DoF grasp using collision, clearance, reachability, and approach constraints. The system is implemented on a quadruped robot with an arm and evaluated in two cluttered tabletop scenes motivated by small-object retrieval during inspection and maintenance. Across paired trials, the proposed pipeline achieved 9/10 successful grasps, compared with 3/10 for a view-dependent deployment baseline. In this controlled setting, object-centric completion and execution-aware selection reduced approach collisions and improved the reliability of language-guided grasping for supervised field manipulation. --- ### Language-Guided Grasping under Partial Observation for Mobile Manipulation in Field Inspection and Maintenance Authors: Dilermando Almeida, Juliano Negri, Guilherme Lazzarini, Thiago H. Segreto, Ranulfo Bezerra, Gustavo J. G. Lahr, Ricardo V. Godoy, Marcelo Becker Published: 2026-03-09 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.07866v3 Offshore inspection and maintenance have increasingly been using legged robots for routine sensing, yet many useful interventions still require physical interaction with tools, containers, and task-relevant objects. Employing robots for these tasks can reduce operators' exposure in confined, elevated, or potentially explosive areas. This paper presents a language-guided grasping pipeline for a legged mobile manipulator operating under partial observation. An operator defines the target, the system grounds it in RGB with open-vocabulary detection and promptable segmentation, extracts an object-centric RGB-D point cloud, improves sparse geometry through depth compensation and point-cloud completion, and selects a 6-DoF grasp using collision, clearance, reachability, and approach constraints. The system is implemented on a quadruped robot with an arm and evaluated in two cluttered tabletop scenes motivated by small-object retrieval during inspection and maintenance. Across paired trials, the proposed pipeline achieved 9/10 successful grasps, compared with 3/10 for a view-dependent deployment baseline. In this controlled setting, object-centric completion and execution-aware selection reduced approach collisions and improved the reliability of language-guided grasping for supervised field manipulation. --- ### SoundWeaver: Semantic Warm-Starting for Text-to-Audio Diffusion Serving Authors: Ayush Barik, Sofia Stoica, Nikhil Sarda, Arnav Kethana, Abhinav Khanduja, Muchen Xu, Fan Lai Published: 2026-03-09 Categories: cs.SD, cs.CV, eess.AS arXiv: https://arxiv.org/abs/2603.07865v1 Text-to-audio diffusion models produce high-fidelity audio but require tens of function evaluations (NFEs), incurring multi-second latency and limited throughput. We present SoundWeaver, the first training-free, model-agnostic serving system that accelerates text-to-audio diffusion by warm-starting from semantically similar cached audio. SoundWeaver introduces three components: a Reference Selector that retrieves and temporally aligns cached candidates via semantic and duration-aware gating; a Skip Gater that dynamically determines the percentage of NFEs to skip; and a lightweight Cache Manager that maintains cache utility through quality-aware eviction and refinement. On real-world audio traces, SoundWeaver achieves 1.8--3.0$ \times $ latency reduction with a cache of only ${\sim}$1K entries while preserving or improving perceptual quality. --- ### An Interpretable Generative Framework for Anomaly Detection in High-Dimensional Financial Time Series Authors: Waldyn G Martinez Published: 2026-03-09 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.07864v1 Detecting structural instability and anomalies in high-dimensional financial time series is challenging due to complex temporal dependence and evolving cross-sectional structure. We propose ReGEN-TAD, an interpretable generative framework that integrates modern machine learning with econometric diagnostics for anomaly detection. The model combines joint forecasting and reconstruction within a refined convolutional--transformer architecture and aggregates complementary signals capturing predictive inconsistency, reconstruction degradation, latent distortion, and volatility shifts. Robust calibration yields a unified anomaly score without labeled data. Experiments on synthetic and financial panels demonstrate improved robustness to structured deviations while enabling economically coherent factor-level attribution. --- ### Sparse Scheduled Diffusion Guidance for Inverse Problems Authors: Abduragim Shtanchaev, Albina Ilina, Yazid Janati, Arip Asadulaev, Martin Takac, Eric Moulines Published: 2026-03-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.07860v3 Pretrained diffusion models are effective priors for Bayesian inverse problems, but posterior sampling with these priors is often costly because data-consistency guidance is applied throughout the full reverse trajectory. Existing methods have shown that vector-Jacobian products through the denoiser can sometimes be avoided, yet they typically still rely on dense guidance through the full trajectory or expensive inner solves. We introduce Sparse Scheduled Diffusion Guidance for Inverse Problems (Spin), a solver that avoids starting posterior sampling from pure noise. Spin first samples from a posterior time-marginal at an intermediate timestep $t_*$, and then uses that state as a warm start for a guided reverse diffusion process. At guidance time, instead of enforcing the measurement constraint at every denoising step, Spin applies lightweight corrections only at scheduled timesteps where the denoiser can still clean up artifacts. The resulting procedure decouples prior refinement from data consistency: the prior supplies denoising, while lightweight pixel-space optimization enforces the measurement constraint without backpropagation through the denoiser or decoder. Across linear and nonlinear inverse problems on FFHQ and ImageNet, Spin achieves competitive reconstruction quality with a substantially better runtime--memory profile, running 2x faster on pixel-space models and up to 50x faster on latent diffusion models, with lower memory costs. --- ### SynPlanResearch-R1: Encouraging Tool Exploration for Deep Research with Synthetic Plans Authors: Hansi Zeng, Zoey Li, Yifan Gao, Chenwei Zhang, Xiaoman Pan, Tao Yang, Fengran Mo, Jiacheng Lin, Xian Li, Jingbo Shang Published: 2026-03-09 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2603.07853v1 Research Agents enable models to gather information from the web using tools to answer user queries, requiring them to dynamically interleave internal reasoning with tool use. While such capabilities can in principle be learned via reinforcement learning with verifiable rewards (RLVR), we observe that agents often exhibit poor exploration behaviors, including premature termination and biased tool usage. As a result, RLVR alone yields limited improvements. We propose SynPlanResearch-R1, a framework that synthesizes tool-use trajectories that encourage deeper exploration to shape exploration during cold-start supervised fine-tuning, providing a strong initialization for subsequent RL. Across seven multi-hop and open-web benchmarks, \framework improves performance by up to 6.0% on Qwen3-8B and 5.8% on Qwen3-4B backbones respectively compared to SOTA baselines. Further analyses of tool-use patterns and training dynamics compared to baselines shed light on the factors underlying these gains. Our code is publicly available at https://github.com/HansiZeng/syn-plan-research. --- ### GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration Authors: Yeahia Sarker, Md Rahmat Ullah, Musa Molla, Shafiq Joty Published: 2026-03-08 Categories: cs.AI, cs.CL, cs.DC arXiv: https://arxiv.org/abs/2605.13848v1 Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routing, infinite loops, and non-reproducible execution. We introduce GraphBit, an engine-orchestrated framework that defines workflows explicitly and deterministically as a directed acyclic graph (DAG). Unlike prompted orchestration, agents in GraphBit operate as typed functions, while a Rust-based engine governs routing, state transitions, and tool invocation, ensuring reproducibility and auditability. The engine supports parallel branch execution, conditional control flow over structured state predicates, and configurable error recovery. A three-tier memory architecture consisting of ephemeral scratch space, structured state, and external connectors isolates context across stages, preventing cascading context bloat that degrades reasoning in long-running pipelines. Across GAIA benchmark tasks spanning zero-tool, document-augmented, and web-enabled workflows, GraphBit outperforms six existing frameworks, achieving the highest accuracy (67.6 percent), zero framework-induced hallucinations, the lowest latency (11.9 ms overhead), and the highest throughput. Ablation studies demonstrate that each memory tier contributes measurably to performance, with deterministic execution providing the greatest gains on tool-intensive tasks representative of real-world deployments. --- ### Evaluating LLMs as Human Surrogates in Controlled Experiments Authors: Adnan Hoq, Tim Weninger Published: 2026-03-08 Categories: cs.HC, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.15329v1 Large language models (LLMs) are increasingly used to simulate human responses in behavioral research, yet it remains unclear when LLM-generated data support the same experimental inferences as human data. We evaluate this by directly comparing off-the-shelf LLM-generated responses with human responses from a canonical survey experiment on accuracy perception. Each human observation is converted into a structured prompt, and models generate a single 0--10 outcome variable without task-specific training; identical statistical analyses are applied to human and synthetic responses. We find that LLMs reproduce several directional effects observed in humans, but effect magnitudes and moderation patterns vary across models. Off-the-shelf LLMs therefore capture aggregate belief-updating patterns under controlled conditions but do not consistently match human-scale effects, clarifying when LLM-generated data can function as behavioral surrogates. --- ### Benchmark for Assessing Olfactory Perception of Large Language Models Authors: Eftychia Makri, Nikolaos Nakis, Laura Sisson, Gigi Minsky, Leandros Tassiulas, Vahid Satarifard, Nicholas A. Christakis Published: 2026-03-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.00002v1 Here we introduce the Olfactory Perception (OP) benchmark, designed to assess the capability of large language models (LLMs) to reason about smell. The benchmark contains 1,010 questions across eight task categories spanning odor classification, odor primary descriptor identification, intensity and pleasantness judgments, multi-descriptor prediction, mixture similarity, olfactory receptor activation, and smell identification from real-world odor sources. Each question is presented in two prompt formats, compound names and isomeric SMILES, to evaluate the effect of molecular representations. Evaluating 21 model configurations across major model families, we find that compound-name prompts consistently outperform isomeric SMILES, with gains ranging from +2.4 to +18.9 percentage points (mean approx +7 points), suggesting current LLMs access olfactory knowledge primarily through lexical associations rather than structural molecular reasoning. The best-performing model reaches 64.4\% overall accuracy, which highlights both emerging capabilities and substantial remaining gaps in olfactory reasoning. We further evaluate a subset of the OP across 21 languages and find that aggregating predictions across languages improves olfactory prediction, with AUROC = 0.86 for the best performing language ensemble model. LLMs should be able to handle olfactory and not just visual or aural information. --- ### Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning Authors: Fangxin Wang, Peyman Baghershahi, Langzhou He, Henry Peng Zou, Sourav Medya, Philip S. Yu Published: 2026-03-08 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.00001v2 Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but existing methods are mostly designed for offline settings. They are therefore less suited to online fine-tuning, where data arrives sequentially, sample utility is step-dependent, and the effective update geometry is shaped by adaptive optimizers. We propose an optimizer-aware framework for gradient-based online data selection and reweighting in LLM fine-tuning. Our key idea is to view online selection not as static sample ranking, but as shaping the next target-oriented update under the current optimizer state. We formulate this as an optimizer-aware update-matching problem, establish its connection to second-order target utility, and show why subset-level construction must account for interactions and redundancy among selected samples. Based on this view, we develop a two-stage Filter-then-Weight algorithm that first filters geometrically useful candidates and then optimizes their coefficients. To make the framework practical for LLMs, we introduce a factorized outer-product gradient representation and optimized matrix computations for long-context data. Experiments show that our method consistently improves convergence and downstream performance over existing online data selection baselines under the same data budget. --- ### Power Couple? AI Growth and Renewable Energy Investment Authors: Luyi Gui, Tinglong Dai Published: 2026-03-08 Categories: cs.CY, cs.AI, econ.TH arXiv: https://arxiv.org/abs/2603.26678v3 Artificial intelligence (AI) and renewable energy are increasingly being described as a \mbox{``power couple,''} based on the idea that rapid growth in AI will spur clean-energy investment. Yet growing AI demand could also deepen reliance on fossil power. We study when each outcome arises in a game in which renewable-capacity investment and AI scaling interact. The key is how the market value of greater AI capability grows relative to the energy needed to achieve it. When value grows at least as fast as energy use (market-led scaling), the developer pushes toward frontier capability even when additional electricity comes from fossil sources. Renewable investment can then enable further AI growth without eliminating fossil use. As climate damages increase, AI becomes more valuable for adaptation, strengthening incentives to sustain frontier capability despite the associated emissions. We call this the ``adaptation trap.'' When energy requirements grow faster than capability value (resource-led scaling), energy costs place greater limits on AI expansion. Renewable investment then makes additional capability less costly while also reducing emissions. As climate damages rise, the growing value of AI for adaptation can justify enough clean-capacity expansion to support AI entirely with renewable power. We call this the ``adaptation pathway.'' A calibrated case study shows that both mechanisms can arise at empirically plausible magnitudes. The results suggest that decarbonizing AI requires renewable capacity to keep pace with the growth of compute demand. --- ### Power Couple? AI Growth and Renewable Energy Investment Authors: Luyi Gui, Tinglong Dai Published: 2026-03-08 Categories: cs.CY, cs.AI, econ.TH arXiv: https://arxiv.org/abs/2603.26678v2 AI and renewable energy are increasingly framed as a "power couple," on the premise that surging AI demand will accelerate clean-energy investment, yet concerns persist that AI will entrench fossil-fuel carbon lock-in. We reconcile these views by modeling the equilibrium between AI growth and renewable investment. In a parsimonious game, a policymaker designs policies that guide investment in renewable capacity for AI, while an AI developer chooses its model's capability. The equilibrium depends on scaling regimes and market incentives. When the market payoff to capability is supermodular and performance gains are near-linear in compute (so the market rewards capability at least as fast as scaling raises its energy cost), developers push toward frontier scale even when the marginal megawatt-hour is fossil-based. In this regime, renewable expansion mainly relaxes scaling constraints rather than displacing fossil generation; clean capacity remains insufficient and fossil dependence persists. This yields an "adaptation trap": as climate damages rise, the value of AI-enabled adaptation increases, which strengthens incentives to enable frontier scaling while tolerating residual fossil use. When AI faces diminishing returns and lower scaling efficiency (so energy requirements outrun the market value of capability), energy costs discipline capability choices; renewable investment then both enables capability and decarbonizes marginal compute, generating an "adaptation pathway" in which climate stress spurs clean-capacity expansion toward a carbon-free equilibrium. A calibrated case study illustrates both mechanisms using observed magnitudes. The findings suggest that effective AI decarbonization requires policies that keep clean capacity binding at the margin as compute expands. --- ### Not All Pretraining are Created Equal: Threshold Tuning and Class Weighting for Imbalanced Polarization Tasks in Low-Resource Settings Authors: Abass Oguntade Published: 2026-03-08 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.23534v1 This paper describes my submission to the Polarization Shared Task at SemEval-2025, which addresses polarization detection and classification in social media text. I develop Transformer-based systems for English and Swahili across three subtasks: binary polarization detection, multi-label target type classification, and multi-label manifestation identification. The approach leverages multilingual and African language-specialized models (mDeBERTa-v3-base, SwahBERT, AfriBERTa-large), class-weighted loss functions, iterative stratified data splitting, and per-label threshold tuning to handle severe class imbalance. The best configuration, mDeBERTa-v3-base, achieves 0.8032 macro-F1 on validation for binary detection, with competitive performance on multi-label tasks (up to 0.556 macro-F1). Error analysis reveals persistent challenges with implicit polarization, code-switching, and distinguishing heated political discourse from genuine polarization. --- ### MDKeyChunker: Single-Call LLM Enrichment with Rolling Keys and Key-Based Restructuring for High-Accuracy RAG Authors: Bhavik Mangla Published: 2026-03-08 Categories: cs.CL, cs.AI, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.23533v2 RAG pipelines typically rely on fixed-size chunking, which ignores document structure, fragments semantic units across boundaries, and requires multiple LLM calls per chunk for metadata extraction. We present MDKeyChunker, a three-stage pipeline for Markdown documents that (1) performs structure-aware chunking treating headers, code blocks, tables, and lists as atomic units; (2) enriches each chunk via a single LLM call extracting title, summary, keywords, typed entities, hypothetical questions, and a semantic key, while propagating a rolling key dictionary to maintain document-level context; and (3) restructures chunks by merging those sharing the same semantic key via bin-packing, co-locating related content for retrieval. The single-call design extracts all seven metadata fields in one LLM invocation, eliminating the need for separate per-field extraction passes. Rolling key propagation replaces hand-tuned scoring with LLM-native semantic matching. An empirical evaluation on 30 queries over an 18-document Markdown corpus shows Config D (BM25 over structural chunks) achieves Recall@5=1.000 and MRR=0.911, while dense retrieval over the full pipeline (Config C) reaches Recall@5=0.867. MDKeyChunker is implemented in Python with four dependencies and supports any OpenAI-compatible endpoint. --- ### Generating Hierarchical JSON Representations of Scientific Sentences Using LLMs Authors: Satya Sri Rajiteswari Nimmagadda, Ethan Young, Niladri Sengupta, Ananya Jana, Aniruddha Maiti Published: 2026-03-08 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.23532v1 This paper investigates whether structured representations can preserve the meaning of scientific sentences. To test this, a lightweight LLM is fine-tuned using a novel structural loss function to generate hierarchical JSON structures from sentences collected from scientific articles. These JSONs are then used by a generative model to reconstruct the original text. Comparing the original and reconstructed sentences using semantic and lexical similarity we show that hierarchical formats are capable of retaining information of scientific texts effectively. --- ### Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning Authors: Janaka Chathuranga Brahmanage, Akshat Kumar Published: 2026-03-08 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2603.22292v2 Sequential decision making using Markov Decision Process underpins many realworld applications. Both model-based and model free methods have achieved strong results in these settings. However, real-world tasks must balance reward maximization with safety constraints, often conflicting objectives, that can lead to unstable min/max, adversarial optimization. A promising alternative is safety reachability analysis, which precomputes a forward-invariant safe state, action set, ensuring that an agent starting inside this set remains safe indefinitely. Yet, most reachability based methods address only hard safety constraints, and little work extends reachability to cumulative cost constraints. To address this, first, we define a safetyconditioned reachability set that decouples reward maximization from cumulative safety cost constraints. Second, we show how this set enforces safety constraints without unstable min/max or Lagrangian optimization, yielding a novel offline safe RL algorithm that learns a safe policy from a fixed dataset without environment interaction. Finally, experiments on standard offline safe RL benchmarks, and a real world maritime navigation task demonstrate that our method matches or outperforms state of the art baselines while maintaining safety. ---