# Research Papers — 2026-03 · bundle page 70 of 243 > Full-text markdown of papers #3451–3500 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/70 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/69.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/71.md) ### Sharper Generalization Bounds for Transformer Authors: Yawen Li, Tao Hu, Zhouhui Lian, Wan Tian, Yijie Peng, Huiming Zhang, Zhongyi Li Published: 2026-03-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.21541v1 This paper studies generalization error bounds for Transformer models. Based on the offset Rademacher complexity, we derive sharper generalization bounds for different Transformer architectures, including single-layer single-head, single-layer multi-head, and multi-layer Transformers. We first express the excess risk of Transformers in terms of the offset Rademacher complexity. By exploiting its connection with the empirical covering numbers of the corresponding hypothesis spaces, we obtain excess risk bounds that achieve optimal convergence rates up to constant factors. We then derive refined excess risk bounds by upper bounding the covering numbers of Transformer hypothesis spaces using matrix ranks and matrix norms, leading to precise, architecture-dependent generalization bounds. Finally, we relax the boundedness assumption on feature mappings and extend our theoretical results to settings with unbounded (sub-Gaussian) features and heavy-tailed distributions. --- ### Generalization Limits of In-Context Operator Networks for Higher-Order Partial Differential Equations Authors: Jamie Mahowald, Tan Bui-Thanh Published: 2026-03-23 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2603.21534v1 We investigate the generalization capabilities of In-Context Operator Networks (ICONs), a new class of operator networks that build on the principles of in-context learning, for higher-order partial differential equations. We extend previous work by expanding the type and scope of differential equations handled by the foundation model. We demonstrate that while processing complex inputs requires some new computational methods, the underlying machine learning techniques are largely consistent with simpler cases. Our implementation shows that although point-wise accuracy degrades for higher-order problems like the heat equation, the model retains qualitative accuracy in capturing solution dynamics and overall behavior. This demonstrates the model's ability to extrapolate fundamental solution characteristics to problems outside its training regime. --- ### LLM-Based Test Case Generation in DBMS through Monte Carlo Tree Search Authors: Yujia Chen, Yingli Zhou, Fangyuan Zhang, Cuiyun Gao Published: 2026-03-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.21530v1 Database Management Systems (DBMSs) are fundamental infrastructure for modern data-driven applications, where thorough testing with high-quality SQL test cases is essential for ensuring system reliability. Traditional approaches such as fuzzing can be effective for specific DBMSs, but adapting them to different proprietary dialects requires substantial manual effort. Large Language Models (LLMs) present promising opportunities for automated SQL test generation, but face critical challenges in industrial environments. First, lightweight models are widely used in organizations due to security and privacy constraints, but they struggle to generate syntactically valid queries for proprietary SQL dialects. Second, LLM-generated queries are often semantically similar and exercise only shallow execution paths, thereby quickly reaching a coverage plateau. To address these challenges, we propose MIST, an LLM-based test case generatIon framework for DBMS through Monte Carlo Tree search. MIST consists of two stages: Feature-Guided Error-Driven Test Case Synthetization, which constructs a hierarchical feature tree and uses error feedback to guide LLM generation, aiming to produce syntactically valid and semantically diverse queries for different DBMS dialects, and Monte Carlo Tree Search-Based Test Case Mutation, which jointly optimizes seed query selection and mutation rule application guided by coverage feedback, aiming at boosting code coverage by exploring deeper execution paths. Experiments on three widely-used DBMSs with four lightweight LLMs show that MIST achieves average improvements of 43.3% in line coverage, 32.3% in function coverage, and 46.4% in branch coverage compared to the baseline approach with the highest line coverage of 69.3% in the Optimizer module. --- ### SynSym: A Synthetic Data Generation Framework for Psychiatric Symptom Identification Authors: Migyeong Kang, Jihyun Kim, Hyolim Jeon, Sunwoo Hwang, Jihyun An, Yonghoon Kim, Haewoon Kwak, Jisun An, Jinyoung Han Published: 2026-03-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.21529v1 Psychiatric symptom identification on social media aims to infer fine-grained mental health symptoms from user-generated posts, allowing a detailed understanding of users' mental states. However, the construction of large-scale symptom-level datasets remains challenging due to the resource-intensive nature of expert labeling and the lack of standardized annotation guidelines, which in turn limits the generalizability of models to identify diverse symptom expressions from user-generated text. To address these issues, we propose SynSym, a synthetic data generation framework for constructing generalizable datasets for symptom identification. Leveraging large language models (LLMs), SynSym constructs high-quality training samples by (1) expanding each symptom into sub-concepts to enhance the diversity of generated expressions, (2) producing synthetic expressions that reflect psychiatric symptoms in diverse linguistic styles, and (3) composing realistic multi-symptom expressions, informed by clinical co-occurrence patterns. We validate SynSym on three benchmark datasets covering different styles of depressive symptom expression. Experimental results demonstrate that models trained solely on the synthetic data generated by SynSym perform comparably to those trained on real data, and benefit further from additional fine-tuning with real data. These findings underscore the potential of synthetic data as an alternative resource to real-world annotations in psychiatric symptom modeling, and SynSym serves as a practical framework for generating clinically relevant and realistic symptom expressions. --- ### PEARL: Geometry Aligns Semantics for Training-Free Open-Vocabulary Semantic Segmentation Authors: Gensheng Pei, Xiruo Jiang, Xinhao Cai, Tao Chen, Yazhou Yao, Byeungwoo Jeon Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21528v1 Training-free open-vocabulary semantic segmentation (OVSS) promises rapid adaptation to new label sets without retraining. Yet, many methods rely on heavy post-processing or handle text and vision in isolation, leaving cross-modal geometry underutilized. Others introduce auxiliary vision backbones or multi-model pipelines, which increase complexity and latency while compromising design simplicity. We present PEARL, \textbf{\underline{P}}rocrust\textbf{\underline{e}}s \textbf{\underline{a}}lignment with text-awa\textbf{\underline{r}}e \textbf{\underline{L}}aplacian propagation, a compact two-step inference that follows an align-then-propagate principle. The Procrustes alignment step performs an orthogonal projection inside the last self-attention block, rotating keys toward the query subspace via a stable polar iteration. The text-aware Laplacian propagation then refines per-pixel logits on a small grid through a confidence-weighted, text-guided graph solve: text provides both a data-trust signal and neighbor gating, while image gradients preserve boundaries. In this work, our method is fully training-free, plug-and-play, and uses only fixed constants, adding minimal latency with a small per-head projection and a few conjugate-gradient steps. Our approach, PEARL, sets a new state-of-the-art in training-free OVSS without extra data or auxiliary backbones across standard benchmarks, achieving superior performance under both with-background and without-background protocols. --- ### VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection Authors: Xinghan Li, Junhao Xu, Jingjing Chen Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21526v2 Multimodal large language models (MLLMs) offer a promising path toward interpretable deepfake detection by generating textual explanations. However, the reasoning process of current MLLM-based methods combines evidence generation and manipulation localization into a unified step. This combination blurs the boundary between faithful observations and hallucinated explanations, leading to unreliable conclusions. Building on this, we present VIGIL, a part-centric structured forensic framework inspired by expert forensic practice through a plan-then-examine pipeline: the model first plans which facial parts warrant inspection based on global visual cues, then examines each part with independently sourced forensic evidence. A stage-gated injection mechanism delivers part-level forensic evidence only during examination, ensuring that part selection remains driven by the model's own perception rather than biased by external signals. We further propose a progressive three-stage training paradigm whose reinforcement learning stage employs part-aware rewards to enforce anatomical validity and evidence--conclusion coherence. To enable rigorous generalizability evaluation, we construct OmniFake, a hierarchical 5-Level benchmark where the model, trained on only three foundational generators, is progressively tested up to in-the-wild social-media data. Extensive experiments on OmniFake and cross-dataset evaluations demonstrate that VIGIL consistently outperforms both expert detectors and concurrent MLLM-based methods across all generalizability levels. --- ### BOxCrete: A Bayesian Optimization Open-Source AI Model for Concrete Strength Forecasting and Mix Optimization Authors: Bayezid Baten, M. Ayyan Iqbal, Sebastian Ament, Julius Kusuma, Nishant Garg Published: 2026-03-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.21525v1 Modern concrete must simultaneously satisfy evolving demands for mechanical performance, workability, durability, and sustainability, making mix designs increasingly complex. Recent studies leveraging Artificial Intelligence (AI) and Machine Learning (ML) models show promise for predicting compressive strength and guiding mix optimization, but most existing efforts are based on proprietary industrial datasets and closed-source implementations. Here we introduce BOxCrete, an open-source probabilistic modeling and optimization framework trained on a new open-access dataset of over 500 strength measurements (1-15 ksi) from 123 mixtures - 69 mortar and 54 concrete mixes tested at five curing ages (1, 3, 5, 14, and 28 days). BOxCrete leverages Gaussian Process (GP) regression to predict strength development, achieving average R$^2$ = 0.94 and RMSE = 0.69 ksi, quantify uncertainty, and carry out multi-objective optimization of compressive strength and embodied carbon. The dataset and model establish a reproducible open-source foundation for data-driven development of AI-based optimized mix designs. --- ### CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs Authors: Ravi Ranjan, Utkarsh Grover, Mayur Akewar, Xiaomin Lin, Agoritsa Polyzou Published: 2026-03-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.21524v1 Large Language Models (LLMs) are deployed in high-stakes settings but can show demographic, gender, and geographic biases that undermine fairness and trust. Prior debiasing methods, including embedding-space projections, prompt-based steering, and causal interventions, often act at a single stage of the pipeline, resulting in incomplete mitigation and brittle utility trade-offs under distribution shifts. We propose CatRAG Debiasing, a dual-pronged framework that integrates functor with Retrieval-Augmented Generation (RAG) guided structural debiasing. The functor component leverages category-theoretic structure to induce a principled, structure-preserving projection that suppresses bias-associated directions in the embedding space while retaining task-relevant semantics. On the Bias Benchmark for Question Answering (BBQ) across three open-source LLMs (Meta Llama-3, OpenAI GPT-OSS, and Google Gemma-3), CatRAG achieves state-of-the-art results, improving accuracy by up to 40% over the corresponding base models and by more than 10% over prior debiasing methods, while reducing bias scores to near zero (from 60% for the base models) across gender, nationality, race, and intersectional subgroups. --- ### SafePilot: A Framework for Assuring LLM-enabled Cyber-Physical Systems Authors: Weizhe Xu, Mengyu Liu, Fanxin Kong Published: 2026-03-23 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2603.21523v1 Large Language Models (LLMs), deep learning architectures with typically over 10 billion parameters, have recently begun to be integrated into various cyber-physical systems (CPS) such as robotics, industrial automation, and autopilot systems. The abstract knowledge and reasoning capabilities of LLMs are employed for tasks like planning and navigation. However, a significant challenge arises from the tendency of LLMs to produce "hallucinations" - outputs that are coherent yet factually incorrect or contextually unsuitable. This characteristic can lead to undesirable or unsafe actions in the CPS. Therefore, our research focuses on assuring the LLM-enabled CPS by enhancing their critical properties. We propose SafePilot, a novel hierarchical neuro-symbolic framework that provides end-to-end assurance for LLM-enabled CPS according to attribute-based and temporal specifications. Given a task and its specification, SafePilot first invokes a hierarchical planner with a discriminator that assesses task complexity. If the task is deemed manageable, it is passed directly to an LLM-based task planner with built-in verification. Otherwise, the hierarchical planner applies a divide-and-conquer strategy, decomposing the task into sub-tasks, each of which is individually planned and later merged into a final solution. The LLM-based task planner translates natural language constraints into formal specifications and verifies the LLM's output against them. If violations are detected, it identifies the flaw, adjusts the prompt accordingly, and re-invokes the LLM. This iterative process continues until a valid plan is produced or a predefined limit is reached. Our framework supports LLM-enabled CPS with both attribute-based and temporal constraints. Its effectiveness and adaptability are demonstrated through two illustrative case studies. --- ### Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation Authors: Lingzhe Zhang, Tong Jia, Mingyu Wang, Weijie Hong, Chiming Duan, Minghua He, Rongqian Wang, Xi Peng, Meiling Wang, Gong Zhang, Renhai Chen, Ying Li Published: 2026-03-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.21522v1 Large Language Models (LLM)-based Multi-Agent Systems (MASs) have emerged as a new paradigm in software system design, increasingly demonstrating strong reasoning and collaboration capabilities. As these systems become more complex and autonomous, effective failure management is essential to ensure reliability and availability. However, existing approaches often rely on per-trace reasoning, which leads to low efficiency, and neglect historical failure patterns, limiting diagnostic accuracy. In this paper, we conduct a preliminary empirical study to demonstrate the necessity, potential, and challenges of leveraging historical failure patterns to enhance failure management in MASs. Building on this insight, we propose \textbf{EAGER}, an efficient failure management framework for multi-agent systems based on reasoning trace representation. EAGER employs unsupervised reasoning-scoped contrastive learning to encode both intra-agent reasoning and inter-agent coordination, enabling real-time step-wise failure detection, diagnosis, and reflexive mitigation guided by historical failure knowledge. Preliminary evaluations on three open-source MASs demonstrate the effectiveness of EAGER and highlight promising directions for future research in reliable multi-agent system operations. --- ### Generalizable Self-Evolving Memory for Automatic Prompt Optimization Authors: Guanbao Liang, Yuanchen Bei, Sheng Zhou, Yuheng Qin, Huan Zhou, Bingxin Jia, Bin Li, Jiajun Bu Published: 2026-03-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.21520v1 Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits generalization across heterogeneous queries and prevents models from accumulating reusable prompting knowledge over time. In this paper, we propose MemAPO, a memory-driven framework that reconceptualizes prompt optimization as generalizable and self-evolving experience accumulation. MemAPO maintains a dual-memory mechanism that distills successful reasoning trajectories into reusable strategy templates while organizing incorrect generations into structured error patterns that capture recurrent failure modes. Given a new prompt, the framework retrieves both relevant strategies and failure patterns to compose prompts that promote effective reasoning while discouraging known mistakes. Through iterative self-reflection and memory editing, MemAPO continuously updates its memory, enabling prompt optimization to improve over time rather than restarting from scratch for each task. Experiments on diverse benchmarks show that MemAPO consistently outperforms representative prompt optimization baselines while substantially reducing optimization cost. --- ### Triangulating Temporal Dynamics in Multilingual Swiss Online News Authors: Bros Victor, Dufraisse Evan, Popescu Adrian, Gatica-Perez Daniel Published: 2026-03-23 Categories: cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.21519v2 Analyzing news coverage in multilingual societies can offer valuable insights into the dynamics of public discourse and the development of collective narratives, yet comprehensive studies that account for linguistic and cultural diversity within national media ecosystems remain limited, particularly in complex contexts such as Switzerland. This paper studies temporal trends in Swiss digital media across the country's three main linguistic regions, French, German, and Italian, using a triangulated methodology that combines quantitative analyses with qualitative insights. We collected and processed over 1.7 million news articles, applying lexical metrics, named entity recognition and Wikidata-based linking, targeted sentiment analysis, and consensus-based change-point detection. To enable principled cross-language comparisons and to connect to theories of domestication and cultural proximity, we derive domestication profiles together with a proximity salience ratio. Our analysis spans thematic, recurrent, and singular events. By integrating quantitative data with qualitative interpretation, we provide new insights into the dynamics of Swiss digital media and demonstrate the usefulness of triangulation in media studies. The findings reveal distinct temporal patterns and highlight how linguistic and cultural contexts influence reporting. Our approach offers a framework applicable to other multilingual or culturally diverse media environments, contributing to a deeper understanding of how news is shaped by linguistic and cultural factors. --- ### Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection Authors: Kaiqiang Li, Gang Li, Mingle Zhou, Min Li, Delong Han, Jin Wan Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21511v3 Zero-shot (ZS) 3D anomaly detection is crucial for reliable industrial inspection, as it enables detecting and localizing defects without requiring any target-category training data. Existing approaches render 3D point clouds into 2D images and leverage pre-trained Vision-Language Models (VLMs) for anomaly detection. However, such strategies inevitably discard geometric details and exhibit limited sensitivity to local anomalies. In this paper, we revisit intrinsic 3D representations and explore the potential of pre-trained Point-Language Models (PLMs) for ZS 3D anomaly detection. We propose BTP (Back To Point), a novel framework that effectively aligns 3D point cloud and textual embeddings. Specifically, BTP aligns multi-granularity patch features with textual representations for localized anomaly detection, while incorporating geometric descriptors to enhance sensitivity to structural anomalies. Furthermore, we introduce a joint representation learning strategy that leverages auxiliary point cloud data to improve robustness and enrich anomaly semantics. Extensive experiments on Real3D-AD and Anomaly-ShapeNet demonstrate that BTP achieves superior performance in ZS 3D anomaly detection. Code will be available at \href{https://github.com/wistful-8029/BTP-3DAD}{https://github.com/wistful-8029/BTP-3DAD}. --- ### Unregistered Spectral Image Fusion: Unmixing, Adversarial Learning, and Recoverability Authors: Jiahui Song, Sagar Shrestha, Xiao Fu Published: 2026-03-23 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2603.21510v3 This paper addresses the fusion of a pair of spatially unregistered hyperspectral image (HSI) and multispectral image (MSI) covering roughly overlapping regions. HSIs offer high spectral but low spatial resolution, while MSIs provide the opposite. The goal is to integrate their complementary information to enhance both HSI spatial resolution and MSI spectral resolution. While hyperspectral-multispectral fusion (HMF) has been widely studied, the unregistered setting remains challenging. Many existing methods focus solely on MSI super-resolution, leaving HSI unchanged. Supervised deep learning approaches were proposed for HSI super-resolution, but rely on accurate training data, which is often unavailable. Moreover, theoretical analyses largely address the co-registered case, leaving unregistered HMF poorly understood. In this work, an unsupervised framework is proposed to simultaneously super-resolve both MSI and HSI. The method integrates coupled spectral unmixing for MSI super-resolution with latent-space adversarial learning for HSI super-resolution. Theoretical guarantees on the recoverability of the super-resolution MSI and HSI are established under reasonable generative models -- providing, to our best knowledge, the first such insights for unregistered HMF. The approach is validated on semi-real and real HSI-MSI pairs across diverse conditions. --- ### Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences Authors: Chen Gong, Zhenzhe Zheng, Yiliu Chen, Sheng Wang, Fan Wu, Guihai Chen Published: 2026-03-23 Categories: cs.LG, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2603.21508v1 Machine learning models are widely integrated into modern mobile apps to analyze user behaviors and deliver personalized services. Ensuring low-latency on-device model execution is critical for maintaining high-quality user experiences. While prior research has primarily focused on accelerating model inference with given input features, we identify an overlooked bottleneck in real-world on-device model execution pipelines: extracting input features from raw application logs. In this work, we explore a new direction of feature extraction optimization by analyzing and eliminating redundant extraction operations across different model features and consecutive model inferences. We then introduce AutoFeature, an automated feature extraction engine designed to accelerate on-device feature extraction process without compromising model inference accuracy. AutoFeature comprises three core designs: (1) graph abstraction to formulate the extraction workflows of different input features as one directed acyclic graph, (2) graph optimization to identify and fuse redundant operation nodes across different features within the graph; (3) efficient caching to minimize operations on overlapping raw data between consecutive model inferences. We implement a system prototype of AutoFeature and integrate it into five industrial mobile services spanning search, video and e-commerce domains. Online evaluations show that AutoFeature reduces end-to-end on-device model execution latency by 1.33x-3.93x during daytime and 1.43x-4.53x at night. --- ### Parameter-efficient Prompt Tuning and Hierarchical Textual Guidance for Few-shot Whole Slide Image Classification Authors: Jayanie Bogahawatte, Sachith Seneviratne, Saman Halgamuge Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21504v1 Whole Slide Images (WSIs) are giga-pixel in scale and are typically partitioned into small instances in WSI classification pipelines for computational feasibility. However, obtaining extensive instance level annotations is costly, making few-shot weakly supervised WSI classification (FSWC) crucial for learning from limited slide-level labels. Recently, pre-trained vision-language models (VLMs) have been adopted in FSWC, yet they exhibit several limitations. Existing prompt tuning methods in FSWC substantially increase both the number of trainable parameters and inference overhead. Moreover, current methods discard instances with low alignment to text embeddings from VLMs, potentially leading to information loss. To address these challenges, we propose two key contributions. First, we introduce a new parameter efficient prompt tuning method by scaling and shifting features in text encoder, which significantly reduces the computational cost. Second, to leverage not only the pre-trained knowledge of VLMs, but also the inherent hierarchical structure of WSIs, we introduce a WSI representation learning approach with a soft hierarchical textual guidance strategy without utilizing hard instance filtering. Comprehensive evaluations on pathology datasets covering breast, lung, and ovarian cancer types demonstrate consistent improvements up-to 10.9%, 7.8%, and 13.8% respectively, over the state-of-the-art methods in FSWC. Our method reduces the number of trainable parameters by 18.1% on both breast and lung cancer datasets, and 5.8% on the ovarian cancer dataset, while also excelling at weakly-supervised tumor localization. Code at https://github.com/Jayanie/HIPSS. --- ### Quotient Geometry, Effective Curvature, and Implicit Bias in Simple Shallow Neural Networks Authors: Hang-Cheng Dong, Pengcheng Cheng Published: 2026-03-23 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.21502v1 Overparameterized shallow neural networks admit substantial parameter redundancy: distinct parameter vectors may represent the same predictor due to hidden-unit permutations, rescalings, and related symmetries. As a result, geometric quantities computed directly in the ambient Euclidean parameter space can reflect artifacts of representation rather than intrinsic properties of the predictor. In this paper, we develop a differential-geometric framework for analyzing simple shallow networks through the quotient space obtained by modding out parameter symmetries on a regular set. We first characterize the symmetry and quotient structure of regular shallow-network parameters and show that the finite-sample realization map induces a natural metric on the quotient manifold. This leads to an effective notion of curvature that removes degeneracy along symmetry orbits and yields a symmetry-reduced Hessian capturing intrinsic local geometry. We then study gradient flows on the quotient and show that only the horizontal component of parameter motion contributes to first-order predictor evolution, while the vertical component corresponds purely to gauge variation. Finally, we formulate an implicit-bias viewpoint at the quotient level, arguing that meaningful complexity should be assigned to predictor classes rather than to individual parameter representatives. Our experiments confirm that ambient flatness is representation-dependent, that local dynamics are better organized by quotient-level curvature summaries, and that in underdetermined regimes, implicit bias is most naturally described in quotient coordinates. --- ### A Framework for Closed-Loop Robotic Assembly, Alignment and Self-Recovery of Precision Optical Systems Authors: Seou Choi, Sachin Vaidya, Caio Silva, Shiekh Zia Uddin, Sajib Biswas Shuvo, Shrish Choudhary, Marin Soljačić Published: 2026-03-23 Categories: cs.RO, cs.AI, physics.optics arXiv: https://arxiv.org/abs/2603.21496v1 Robotic automation has transformed scientific workflows in domains such as chemistry and materials science, yet free-space optics, which is a high precision domain, remains largely manual. Optical systems impose strict spatial and angular tolerances, and their performance is governed by tightly coupled physical parameters, making generalizable automation particularly challenging. In this work, we present a robotics framework for the autonomous construction, alignment, and maintenance of precision optical systems. Our approach integrates hierarchical computer vision systems, optimization routines, and custom-built tools to achieve this functionality. As a representative demonstration, we perform the fully autonomous construction of a tabletop laser cavity from randomly distributed components. The system performs several tasks such as laser beam centering, spatial alignment of multiple beams, resonator alignment, laser mode selection, and self-recovery from induced misalignment and disturbances. By achieving closed-loop autonomy for highly sensitive optical systems, this work establishes a foundation for autonomous optical experiments for applications across technical domains. --- ### RuntimeSlicer: Towards Generalizable Unified Runtime State Representation for Failure Management Authors: Lingzhe Zhang, Tong Jia, Weijie Hong, Mingyu Wang, Chiming Duan, Minghua He, Rongqian Wang, Xi Peng, Meiling Wang, Gong Zhang, Renhai Chen, Ying Li Published: 2026-03-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2603.21495v1 Modern software systems operate at unprecedented scale and complexity, where effective failure management is critical yet increasingly challenging. Metrics, traces, and logs provide complementary views of system runtime behavior, but existing failure management approaches typically rely on task-oriented pipelines that tightly couple modality-specific preprocessing, representation learning, and downstream models, resulting in limited generalization across tasks and systems. To fill this gap, we propose RuntimeSlicer, a unified runtime state representation model towards generalizable failure management. RuntimeSlicer pre-trains a task-agnostic representation model that directly encodes metrics, traces, and logs into a single, aligned system-state embedding capturing the holistic runtime condition of the system. To train RuntimeSlicer, we introduce Unified Runtime Contrastive Learning, which integrates heterogeneous training data sources and optimizes complementary objectives for cross-modality alignment and temporal consistency. Building upon the learned system-state embeddings, we further propose State-Aware Task-Oriented Tuning, which performs unsupervised partitioning of runtime states and enables state-conditioned adaptation for downstream tasks. This design allows lightweight task-oriented models to be trained on top of the unified embedding without redesigning modality-specific encoders or preprocessing pipelines. Preliminary experiments on the AIOps 2022 dataset demonstrate the feasibility and effectiveness of RuntimeSlicer for system state modeling and failure management tasks. --- ### Agentic Automation of BT-RADS Scoring: End-to-End Multi-Agent System for Standardized Brain Tumor Follow-up Assessment Authors: Mohamed Sobhi Jabal, Jikai Zhang, Dominic LaBella, Jessica L. Houk, Dylan Zhang, Jeffrey D. Rudie, Kirti Magudia, Maciej A. Mazurowski, Evan Calabrese Published: 2026-03-23 Categories: cs.CL, cs.MA arXiv: https://arxiv.org/abs/2603.21494v2 The Brain Tumor Reporting and Data System (BT-RADS) standardizes post-treatment MRI response assessment in patients with diffuse gliomas but requires complex integration of imaging trends, medication effects, and radiation timing. This study evaluates an end-to-end multi-agent large language model (LLM) and convolutional neural network (CNN) system for automated BT-RADS classification. A multi-agent LLM system combined with automated CNN-based tumor segmentation was retrospectively evaluated on 509 consecutive post-treatment glioma MRI examinations from a single high-volume center. An extractor agent identified clinical variables (steroid status, bevacizumab status, radiation date) from unstructured clinical notes, while a scorer agent applied BT-RADS decision logic integrating extracted variables with volumetric measurements. Expert reference standard classifications were established by an independent board-certified neuroradiologist. Of 509 examinations, 492 met inclusion criteria. The system achieved 374/492 (76.0%; 95% CI, 72.1%-79.6%) accuracy versus 283/492 (57.5%; 95% CI, 53.1%-61.8%) for initial clinical assessments (+18.5 percentage points; P<.001). Context-dependent categories showed high sensitivity (BT-1b 100%, BT-1a 92.7%, BT-3a 87.5%), while threshold-dependent categories showed moderate sensitivity (BT-3c 74.8%, BT-2 69.2%, BT-4 69.3%, BT-3b 57.1%). For BT-4, positive predictive value was 92.9%. The multi-agent LLM system achieved higher BT-RADS classification agreement with expert reference standard compared to initial clinical scoring, with high accuracy for context-dependent scores and high positive predictive value for BT-4 detection. --- ### StreamingEval: A Unified Evaluation Protocol towards Realistic Streaming Video Understanding Authors: Guowei Tang, Tianwen Qian, Huanran Zheng, Yifei Wang, Xiaoling Wang Published: 2026-03-23 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2603.21493v1 Real-time, continuous understanding of visual signals is essential for real-world interactive AI applications, and poses a fundamental system-level challenge. Existing research on streaming video understanding, however, typically focuses on isolated aspects such as question-answering accuracy under limited visual context or improvements in encoding efficiency, while largely overlooking practical deployability under realistic resource constraints. To bridge this gap, we introduce StreamingEval, a unified evaluation framework for assessing the streaming video understanding capabilities of Video-LLMs under realistic constraints. StreamingEval benchmarks both mainstream offline models and recent online video models under a standardized protocol, explicitly characterizing the trade-off between efficiency, storage and accuracy. Specifically, we adopt a fixed-capacity memory bank to normalize accessible historical visual context, and jointly evaluate visual encoding efficiency, text decoding latency, and task performance to quantify overall system deployability. Extensive experiments across multiple datasets reveal substantial gaps between current Video-LLMs and the requirements of realistic streaming applications, providing a systematic basis for future research in this direction. Codes will be released at https://github.com/wwgTang-111/StreamingEval1. --- ### Multinoulli Extension: A Lossless Continuous Relaxation for Partition-Constrained Subset Selection Authors: Qixin Zhang, Wei Huang, Yan Sun, Yao Shu, Yi Yu, Dacheng Tao Published: 2026-03-23 Categories: cs.LG, math.OC arXiv: https://arxiv.org/abs/2603.21492v1 Identifying the most representative subset for a close-to-submodular objective while satisfying the predefined partition constraint is a fundamental task with numerous applications in machine learning. However, the existing distorted local-search methods are often hindered by their prohibitive query complexities and the rigid requirement for prior knowledge of difficult-to-obtain structural parameters. To overcome these limitations, we introduce a novel algorithm titled Multinoulli-SCG, which not only is parameter-free, but also can achieve the same approximation guarantees as the distorted local-search methods with significantly fewer function evaluations. More specifically, when the objective function is monotone $α$-weakly DR-submodular or $(γ,β)$-weakly submodular, our Multinoulli-SCG algorithm can attain a value of $(1-e^{-α})\text{OPT}-ε$ or $(\frac{γ^{2}(1-e^{-(β(1-γ)+γ^2)})}{β(1-γ)+γ^2})\text{OPT}-ε$ with only $O(1/ε^{2})$ function evaluations, where OPT denotes the optimal value. The cornerstone of our Multinoulli-SCG algorithm is an innovative continuous-relaxation framework named Multinoulli Extension(ME), which can effectively convert the discrete subset selection problem subject to partition constraints into a solvable continuous maximization focused on learning the optimal multinoulli priors across the concerned partition. In sharp contrast with the well-established multi-linear extension for submodular subset selection, a notable advantage of our proposed ME is its intrinsic capacity to provide a lossless rounding scheme for any set function. Furthermore, based on our proposed ME, we also present two novel online algorithms, namely, Multinoulli-OSCG and Multinoulli-OSGA, for the unexplored online subset selection problems over partition constraints. --- ### Stable but Wrong: When Learning Stabilizes Away from the Truth Authors: Zhipeng Zhang Published: 2026-03-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.21491v2 Stable training is often treated as evidence that learning is succeeding, but stability characterizes optimization behavior rather than correctness relative to an external objective. We study what happens when the signal being optimized remains persistently biased. We define Stable but Wrong (SBW) as a learning state in which the learning process remains stable under a task-appropriate operational criterion while the learned outcome remains systematically displaced from an independently defined objective. A minimal strongly convex model shows that a persistent bias in the update direction can shift the unique convergence point away from the true optimum. Controlled experiments in reinforcement learning, supervised learning, and continual fine-tuning of a large language model reveal a recurring separation between apparently normal optimization and correctness under static and feedback-coupled biases. Recovery-stage clean-data access and exploration interventions further show that subsequent trajectories can remain modifiable, although the interventions differ in protocol and do not imply a shared mechanism. The results expose a basic limit of optimization stability as a reliability signal in persistent and feedback-coupled learning systems. --- ### Learning Can Converge Stably to the Wrong Belief under Latent Reliability Authors: Zhipeng Zhang, Zhenjie Yao, Kai Li, Lei Yang Published: 2026-03-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.21491v1 Learning systems are typically optimized by minimizing loss or maximizing reward, assuming that improvements in these signals reflect progress toward the true objective. However, when feedback reliability is unobservable, this assumption can fail, and learning algorithms may converge stably to incorrect solutions. This failure arises because single-step feedback does not reveal whether an experience is informative or persistently biased. When information is aggregated over learning trajectories, however, systematic differences between reliable and unreliable regimes can emerge. We propose a Monitor-Trust-Regulator (MTR) framework that infers reliability from learning dynamics and modulates updates through a slow-timescale trust variable. Across reinforcement learning and supervised learning settings, standard algorithms exhibit stable optimization behavior while learning incorrect solutions under latent unreliability, whereas trust-modulated systems reduce bias accumulation and improve recovery. These results suggest that learning dynamics are not only optimization traces but also a source of information about feedback reliability. --- ### Effective Strategies for Asynchronous Software Engineering Agents Authors: Jiayi Geng, Graham Neubig Published: 2026-03-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.21489v2 AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon tasks involving multiple interdependent subtasks still pose challenges both with respect to accuracy, and with respect to timely completion. A natural approach to solving these long-horizon tasks in a timely manner is asynchronous multi-agent collaboration, where multiple agents work on different parts of the task at the same time. But effective application of multi-agent systems has proven surprisingly difficult: concurrent edits by multiple agents interfere with each other, dependencies are difficult to synchronize, and combining partial progress into a coherent whole is challenging. On the other hand, human developers have long relied on mature collaboration infrastructure to manage these challenges in large software projects. Inspired by these collaboration primitives, we introduce Centralized Asynchronous Isolated Delegation (CAID), a structured multi-agent coordination paradigm grounded in three core SWE primitives: centralized task delegation, asynchronous execution, and isolated workspaces. CAID constructs dependency-aware task plans through a central manager, executes subtasks concurrently in isolated workspaces, and consolidates progress via structured integration with executable test-based verification. In empirical evaluation, we find that CAID improves accuracy over single-agent baselines by 25.6% absolute on paper reproduction tasks (PaperBench) and 14.7% on Python library development tasks (Commit0). Through systematic analysis, we find that branch-and-merge is a central coordination mechanism for multi-agent collaboration, and that SWE primitives such as git worktree, git commit, and git merge enable it to be realized in a reliable and executable manner. --- ### Learning Trajectory-Aware Multimodal Large Language Models for Video Reasoning Segmentation Authors: Jingnan Luo, Mingqi Gao, Jun Liu, Bin-Bin Gao, Feng Zheng Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21488v1 The prosperity of Multimodal Large Language Models (MLLMs) has stimulated the demand for video reasoning segmentation, which aims to segment video objects based on human instructions. Previous studies rely on unidirectional and implicit text-trajectory alignment, which struggles with trajectory perception when faced with severe video dynamics. In this work, we propose TrajSeg, a simple and unified framework built upon MLLMs. Concretely, we introduce bidirectional text-trajectory alignment, where MLLMs accept grounding-intended (text-to-trajectory) and captioning-intended (trajectory-to-text) instructions. This way, MLLMs can benefit from enhanced correspondence and better perceive object trajectories in videos. The mask generation from trajectories is achieved via a frame-level content integration (FCI) module and a unified mask decoder. The former adapts the MLLM-parsed trajectory-level token to frame-specific information. The latter unifies segmentation for all frames into a single structure, enabling the proposed framework to be simplified and end-to-end trainable. Extensive experiments on referring and reasoning video segmentation datasets demonstrate the effectiveness of TrajSeg, which outperforms all video reasoning segmentation methods on all metrics. The code will be publicly available at https://github.com/haodi19/TrajSeg. --- ### GaussianSSC: Triplane-Guided Directional Gaussian Fields for 3D Semantic Completion Authors: Ruiqi Xian, Jing Liang, He Yin, Xuewei Qi, Dinesh Manocha Published: 2026-03-23 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.21487v1 We present \emph{GaussianSSC}, a two-stage, grid-native and triplane-guided approach to semantic scene completion (SSC) that injects the benefits of Gaussians without replacing the voxel grid or maintaining a separate Gaussian set. We introduce \emph{Gaussian Anchoring}, a sub-pixel, Gaussian-weighted image aggregation over fused FPN features that tightens voxel--image alignment and improves monocular occupancy estimation. We further convert point-like voxel features into a learned per-voxel Gaussian field and refine triplane features via a triplane-aligned \emph{Gaussian--Triplane Refinement} module that combines \emph{local gathering} (target-centric) and \emph{global aggregation} (source-centric). This directional, anisotropic support captures surface tangency, scale, and occlusion-aware asymmetry while preserving the efficiency of triplane representations. On SemanticKITTI~\cite{behley2019semantickitti}, GaussianSSC improves Stage~1 occupancy by +1.0\% Recall, +2.0\% Precision, and +1.8\% IoU over state-of-the-art baselines, and improves Stage~2 semantic prediction by +1.8\% IoU and +0.8\% mIoU. --- ### Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies Authors: Koichi Tanaka, Kazuki Kawamura, Takanori Muroi, Yusuke Narita, Yuki Sasamoto, Kei Tateno, Takuma Udagawa, Wei-Wei Du, Yuta Saito Published: 2026-03-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.21485v1 Off-Policy Evaluation (OPE) is an important practical problem in algorithmic ranking systems, where the goal is to estimate the expected performance of a new ranking policy using only offline logged data collected under a different, logging policy. Existing estimators, such as the ranking-wise and position-wise inverse propensity score (IPS) estimators, require the data collection policy to be sufficiently stochastic and suffer from severe bias when the logging policy is fully deterministic. In this paper, we propose novel estimators, Click-based Inverse Propensity Score (CIPS), exploiting the intrinsic stochasticity of user click behavior to address this challenge. Unlike existing methods that rely on the stochasticity of the logging policy, our approach uses click probability as a new form of importance weighting, enabling low-bias OPE even under deterministic logging policies where existing methods incur substantial bias. We provide theoretical analyses of the bias and variance properties of the proposed estimators and show, through synthetic and real-world experiments, that our estimators achieve significantly lower bias compared to strong baselines, for a range of experimental settings with completely deterministic logging policies. --- ### Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models Authors: Hyundong Jin, Dongyoon Han, Eunwoo Kim Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21484v1 Continual unlearning poses the challenge of enabling large vision-language models to selectively refuse specific image-instruction pairs in response to sequential deletion requests, while preserving general utility. However, sequential unlearning updates distort shared representations, creating spurious associations between vision-language pairs and refusal behaviors that hinder precise identification of refusal targets, resulting in inappropriate refusals. To address this challenge, we propose a novel continual unlearning framework that grounds refusal behavior in fine-grained descriptions of visual and textual concepts decomposed from deletion targets. We first identify which visual-linguistic concept combinations characterize each forget category through a concept modulator, then determine how to generate appropriate refusal responses via a mixture of refusal experts, termed refusers, each specialized for concept-aligned refusal generation. To generate concept-specific refusal responses across sequential tasks, we introduce a multimodal, concept-driven routing scheme that reuses refusers for tasks sharing similar concepts and adapts underutilized ones for novel concepts. Extensive experiments on vision-language benchmarks demonstrate that the proposed framework outperforms existing methods by generating concept-grounded refusal responses and preserving the general utility across unlearning sequences. --- ### ALADIN:Attribute-Language Distillation Network for Person Re-Identification Authors: Wang Zhou, Boran Duan, Haojun Ai, Ruiqi Lan, Ziyue Zhou Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21482v2 Recent vision-language models such as CLIP provide strong cross-modal alignment, but current CLIP-guided ReID pipelines rely on global features and fixed prompts. This limits their ability to capture fine-grained attribute cues and adapt to diverse appearances. We propose ALADIN, an attribute-language distillation network that distills knowledge from a frozen CLIP teacher to a lightweight ReID student. ALADIN introduces fine-grained attribute-local alignment to establish adaptive text-visual correspondence and robust representation learning. A Scene-Aware Prompt Generator produces image-specific soft prompts to facilitate adaptive alignment. Attribute-local distillation enforces consistency between textual attributes and local visual features, significantly enhancing robustness under occlusions. Furthermore, we employ cross-modal contrastive and relation distillation to preserve the inherent structural relationships among attributes. To provide precise supervision, we leverage Multimodal LLMs to generate structured attribute descriptions, which are then converted into localized attention maps via CLIP. At inference, only the student is used. Experiments on Market-1501, DukeMTMC-reID, and MSMT17 show improvements over CNN-, Transformer-, and CLIP-based methods, with better generalization and interpretability. --- ### TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild Authors: Kai-Wei Chang, Yi-Cheng Lin, Huang-Cheng Chou, Wenze Ren, Yu-Han Huang, Yun-Shao Tsai, Chien-Cheng Chen, Yu Tsao, Yuan-Fu Liao, Shrikanth Narayanan, James Glass, Hung-yi Lee Published: 2026-03-23 Categories: cs.CL, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2603.21478v2 Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limited resources. In this paper, we introduce \textbf{TaigiSpeech}, a real-world speech intent dataset in Taiwanese Taigi (aka Taiwanese Hokkien/Southern Min), which is a low-resource and primarily spoken language. The dataset is collected from older adults, comprising 21 speakers with a total of 3k utterances. It is designed for practical intent detection scenarios, including healthcare and home assistant applications. To address the scarcity of labeled data, we explore two data mining strategies with two levels of supervision: keyword match data mining with LLM pseudo labeling via an intermediate language and an audio-visual framework that leverages multimodal cues with minimal textual supervision. This design enables scalable dataset construction for low-resource and unwritten spoken languages. TaigiSpeech will be released under the CC BY 4.0 license to facilitate broad adoption and research on low-resource and unwritten languages. The project website and the dataset can be found on https://kwchang.org/taigispeech. --- ### Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems Authors: Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin Published: 2026-03-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.21475v2 Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked when applied to knowledge-intensive domains (e.g., healthcare and law). They either rely on a static library of general nodes like Chain-of-Thought, which lack specialized expertise, or attempt to generate nodes on the fly. In the latter case, the orchestrator is not only bound by its internal knowledge limits but must also simultaneously generate domain-specific logic and optimize high-level topology, leading to a severe architectural coupling that degrades overall system efficacy. To bridge this gap, we propose Unified-MAS that decouples granular node implementation from topological orchestration via offline node synthesis. Unified-MAS operates in two stages: (1) Search-Based Node Generation retrieves external open-world knowledge to synthesize specialized node blueprints, overcoming the internal knowledge limits of LLMs; and (2) Reward-Based Node Optimization utilizes a perplexity-guided reward to iteratively enhance the internal logic of bottleneck nodes. Extensive experiments across four specialized domains demonstrate that integrating Unified-MAS into four Automatic-MAS baselines yields a better performance-cost trade-off, achieving up to a 14.2% gain while significantly reducing costs. Further analysis reveals its robustness across different designer LLMs and its effectiveness on conventional tasks such as mathematical reasoning. --- ### Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems Authors: Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin Published: 2026-03-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.21475v1 Automatic Multi-Agent Systems (MAS) generation has emerged as a promising paradigm for solving complex reasoning tasks. However, existing frameworks are fundamentally bottlenecked when applied to knowledge-intensive domains (e.g., healthcare and law). They either rely on a static library of general nodes like Chain-of-Thought, which lack specialized expertise, or attempt to generate nodes on the fly. In the latter case, the orchestrator is not only bound by its internal knowledge limits but must also simultaneously generate domain-specific logic and optimize high-level topology, leading to a severe architectural coupling that degrades overall system efficacy. To bridge this gap, we propose Unified-MAS that decouples granular node implementation from topological orchestration via offline node synthesis. Unified-MAS operates in two stages: (1) Search-Based Node Generation retrieves external open-world knowledge to synthesize specialized node blueprints, overcoming the internal knowledge limits of LLMs; and (2) Reward-Based Node Optimization utilizes a perplexity-guided reward to iteratively enhance the internal logic of bottleneck nodes. Extensive experiments across four specialized domains demonstrate that integrating Unified-MAS into four Automatic-MAS baselines yields a better performance-cost trade-off, achieving up to a 14.2% gain while significantly reducing costs. Further analysis reveals its robustness across different designer LLMs and its effectiveness on conventional tasks such as mathematical reasoning. --- ### Beyond Correlation: Refutation-Validated Aspect-Based Sentiment Analysis for Explainable Energy Market Returns Authors: Wihan van der Heever, Keane Ong, Ranjan Satapathy, Erik Cambria Published: 2026-03-23 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.21473v1 This paper proposes a refutation-validated framework for aspect-based sentiment analysis in financial markets, addressing the limitations of correlational studies that cannot distinguish genuine associations from spurious ones. Using X data for the energy sector, we test whether aspect-level sentiment signals show robust, refutation-validated relationships with equity returns. Our pipeline combines net-ratio scoring with z-normalization, OLS with Newey West HAC errors, and refutation tests including placebo, random common cause, subset stability, and bootstrap. Across six energy tickers, only a few associations survive all checks, while renewables show aspect and horizon specific responses. While not establishing causality, the framework provides statistically robust, directionally interpretable signals, with limited sample size (six stocks, one quarter) constraining generalizability and framing this work as a methodological proof of concept. --- ### DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation Authors: Siqi Guo, Ming Lin, Tianbao Yang Published: 2026-03-23 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.21465v2 Developing efficient CUDA kernels is a fundamental yet challenging task in the generative AI industry. Recent research leverages Large Language Models (LLMs) to automatically convert PyTorch reference implementations to CUDA kernels, significantly reducing engineering effort. State-of-the-art LLMs, such as GPT-5.2 and Claude-Sonnet-4.5, still struggle with this task. To address this challenge, we propose DRTriton, a scalable learning framework for training LLMs to convert PyTorch programs into highly optimized Triton kernels, which are then compiled to CUDA kernels at runtime. DRTriton consists of three key components: (i) a data synthetic algorithm CSP-DAG that guarantees full coverage and unbiased uniform sampling over the operator space with controlled difficulty; (ii) a curriculum RL framework with decoupled rewards that jointly optimizes conversion success rate and execution speed; and (iii) a test-time search algorithm that further improves the execution speed of the generated Triton kernels. With a warmup stage of SFT on limited PyTorch-Triton pairs curated using existing LLMs, DRTriton trained by RL on synthesized PyTorch programs generalizes effectively to real-world CUDA kernels that are challenging even for human experts. Experimental results show that DRTriton-7B achieves speedup over PyTorch on 92% of KernelBench Level 2 tasks, compared to 23% for GPT-5.2 and 19% for Claude-Sonnet-4.5. --- ### EpiMask: Leveraging Epipolar Distance Based Masks in Cross-Attention for Satellite Image Matching Authors: Rahul Deshmukh, Aditya Chauhan, Avinash Kak Published: 2026-03-23 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.21463v2 The deep-learning based image matching networks can now handle significantly larger variations in viewpoints and illuminations while providing matched pairs of pixels with sub-pixel precision. These networks have been trained with ground-based image datasets and, implicitly, their performance is optimized for the pinhole camera geometry. Consequently, you get suboptimal performance when such networks are used to match satellite images since those images are synthesized as a moving satellite camera records one line at a time of the points on the ground. In this paper, we present EpiMask, a semi-dense image matching network for satellite images that (1) Incorporates patch-wise affine approximations to the camera modeling geometry; (2) Uses an epipolar distance-based attention mask to restrict cross-attention to geometrically plausible regions; and (3) That fine-tunes a foundational pretrained image encoder for robust feature extraction. Experiments on the SatDepth dataset demonstrate up to 30% improvement in matching accuracy compared to re-trained ground-based models. --- ### DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment Authors: James Wedgwood, Aashiq Muhamed, Mona T. Diab, Virginia Smith Published: 2026-03-23 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.21461v2 Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility. We propose Dynamic SAE Steering for Preference Alignment (DSPA), an inference-time method that makes sparse autoencoder (SAE) steering prompt-conditional. From preference triples, DSPA computes a conditional-difference map linking prompt features to generation-control features; during decoding, it modifies only token-active latents, without base-model weight updates. Across Gemma-2-2B/9B and Qwen3-8B, DSPA improves MT-Bench and is competitive on AlpacaEval while preserving multiple-choice accuracy. Under restricted preference data, DSPA remains robust and can rival the two-stage RAHF-SCIT pipeline while requiring up to $4.47\times$ fewer alignment-stage FLOPs. Finally, we audit the SAE features DSPA modifies, finding that preference directions are dominated by discourse and stylistic signals, and provide theory clarifying the conditional-difference map estimate and when top-$k$ ablation is principled. --- ### DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment Authors: James Wedgwood, Aashiq Muhamed, Mona T. Diab, Virginia Smith Published: 2026-03-23 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.21461v1 Preference alignment is usually achieved by weight-updating training on preference data, which adds substantial alignment-stage compute and provides limited mechanistic visibility. We propose Dynamic SAE Steering for Preference Alignment (DSPA), an inference-time method that makes sparse autoencoder (SAE) steering prompt-conditional. From preference triples, DSPA computes a conditional-difference map linking prompt features to generation-control features; during decoding, it modifies only token-active latents, without base-model weight updates. Across Gemma-2-2B/9B and Qwen3-8B, DSPA improves MT-Bench and is competitive on AlpacaEval while preserving multiple-choice accuracy. Under restricted preference data, DSPA remains robust and can rival the two-stage RAHF-SCIT pipeline while requiring up to $4.47\times$ fewer alignment-stage FLOPs. Finally, we audit the SAE features DSPA modifies, finding that preference directions are dominated by discourse and stylistic signals, and provide theory clarifying the conditional-difference map estimate and when top-$k$ ablation is principled. --- ### When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models Authors: Yubo Li, Ramayya Krishnan, Rema Padman Published: 2026-03-23 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2603.21460v1 Patient education materials for solid-organ transplantation vary substantially across U.S. centers, yet no systematic method exists to quantify this heterogeneity at scale. We introduce a framework that grounds the same patient questions in different centers' handbooks using retrieval-augmented language models and compares the resulting answers using a five-label consistency taxonomy. Applied to 102 handbooks from 23 centers and 1,115 benchmark questions, the framework quantifies heterogeneity across four dimensions: question, topic, organ, and center. We find that 20.8% of non-absent pairwise comparisons exhibit clinically meaningful divergence, concentrated in condition monitoring and lifestyle topics. Coverage gaps are even more prominent: 96.2% of question-handbook pairs miss relevant content, with reproductive health at 95.1% absence. Center-level divergence profiles are stable and interpretable, where heterogeneity reflects systematic institutional differences, likely due to patient diversity. These findings expose an information gap in transplant patient education materials, with document-grounded medical question answering highlighting opportunities for content improvement. --- ### Compressive single-pixel imaging via a wavelength-multiplexed spatially incoherent diffractive optical processor Authors: Xiao Wang, Yiyang Wu, Yuntian Wang, Md Sadman Sakib Rahman, Paloma Casteleiro Costa, Guangdong Ma, Shiqi Chen, Yuzhu Li, Jingxi Li, Cagatay Isil, Aydogan Ozcan Published: 2026-03-23 Categories: physics.optics, cs.NE arXiv: https://arxiv.org/abs/2603.21456v1 Despite offering high sensitivity, a high signal-to-noise ratio, and a broad spectral range, single-pixel imaging (SPI) is limited by low measurement efficiency and long data-acquisition times. To address this, we propose a wavelength-multiplexed, spatially incoherent diffractive optical processor combined with a compact/shallow digital artificial neural network (ANN) to implement compressive SPI. Specifically, we model the bucket detection process in conventional SPI as a linear intensity transformation with spatially and spectrally varying point-spread functions. This transformation matrix is treated as a learnable parameter and jointly optimized with a shallow digital ANN composed of 2 hidden nonlinear layers. The wavelength-multiplexed diffractive processor is then configured via data-free optimization to approximate this pre-trained transformation matrix; after this optimization, the diffractive processor remains static/fixed. Upon multi-wavelength illumination and diffractive modulation, the target spatial information of the input object is spectrally encoded. A single-pixel detector captures the output spectral power at each illumination band, which is then rapidly decoded by the jointly trained digital ANN to reconstruct the input image. In addition to our numerical analyses demonstrating the feasibility of this approach, we experimentally validated its proof-of-concept using an array of light-emitting diodes (LEDs). Overall, this work demonstrates a computational imaging framework for compressive SPI that can be useful in applications such as biomedical imaging, autonomous devices, and remote sensing. --- ### Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis Authors: Tae-Eun Song Published: 2026-03-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.21454v2 LLM coding benchmarks face a credibility crisis: widespread solution leakage and test quality issues undermine SWE-bench Verified, while existing detection methods--paraphrase consistency, n-gram overlap, perplexity analysis--never directly observe whether a model reasons or recalls. Meanwhile, simply repeating verification degrades accuracy: multi-turn review generates false positives faster than it discovers true errors, suggesting that structural approaches are needed. We introduce Cross-Context Verification (CCV), a black-box method that solves the same benchmark problem in N independent sessions and measures solution diversity, combined with the Hierarchical Cross-Context Architecture (HCCA), a multi-agent analysis framework that prevents confirmation bias through intentional information restriction across specialized analytical roles. On 9 SWE-bench Verified problems (45 trials, Claude Opus 4.6, temperature 0), CCV achieves perfect separation between contaminated and genuine reasoning (Mann-Whitney U=0, p approx 0.012, r = 1.0). Key findings: (1) contamination is binary--models either recall perfectly or not at all; (2) reasoning absence is a perfect discriminator; (3) 33% of prior contamination labels are false positives; (4) HCCA's independent analysis structure discovers contamination-flaw composite cases that single-analyst approaches miss. A pilot experiment extending HCCA to multi-stage verification (Worker to Verifier to Director) yields a negative result--100% sycophantic confirmation--providing further evidence that information restriction, not structural complexity, is the key mechanism. We release all code and data. --- ### LLM-Based Intelligent Notification Composition: From Static Personalization to Context-Aware Persuasive Messaging Authors: Nilesh Agrawal Published: 2026-03-22 Categories: cs.HC, cs.CL arXiv: https://arxiv.org/abs/2605.16264v1 Push notifications remain among the most direct channels through which digital platforms engage users, yet existing approaches have invested heavily in who to notify, when to notify, and what to recommend, while leaving how to communicate as the least-optimized stage. This paper argues that message quality is an independent, underinvested lever, and that LLMs create their most differentiated value precisely at this layer. We make three contributions. First, we define notification message quality along six dimensions (contextual relevance, clarity, actionability, novelty handling, linguistic freshness, and persuasive appropriateness) and show how LLM-based composition improves each relative to templates. Across reviewed deployments, reported improvements range from +8% to +14.5% CTR over static templates and +1% to +2.5% over mature slot-filling systems, though these span heterogeneous systems and should not be treated as directly comparable. Second, we provide an architectural attribution analysis disentangling message generation from adjacent components (targeting, ranking, timing), arguing that observed gains are frequently misattributed to text generation alone. Third, we introduce a three-criterion decision framework specifying when LLM generation is and is not the binding constraint. We support these arguments through a PRISMA-guided survey (28 sources from 142 screened), examine domain-specific applications across social media, food delivery, and e-commerce, and propose a unified architectural framework with budget-aware routing, grounded generation, candidate ranking, diversity controls, and online learning. --- ### WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experience Authors: Ruocan Wei, Shufeng Wang, Ziwei Shi Published: 2026-03-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.19756v1 Large language model (LLM) agents often suffer from high reasoning overhead, excessive token consumption, unstable execution, and inability to reuse past experiences in complex tasks like business queries, tool use, and workflow orchestration. Traditional methods generate workflows from scratch for every query, leading to high cost, slow response, and poor robustness. We propose WorkflowGen, an adaptive, trajectory experience-driven framework for automatic workflow generation that reduces token usage and improves efficiency and success rate. Early in execution, WorkflowGen captures full trajectories and extracts reusable knowledge at both node and workflow levels, including error fingerprints, optimal tool mappings, parameter schemas, execution paths, and exception-avoidance strategies. It then employs a closed-loop mechanism that performs lightweight generation only on variable nodes via trajectory rewriting, experience updating, and template induction. A three-tier adaptive routing strategy dynamically selects among direct reuse, rewriting-based generation, and full initialization based on semantic similarity to historical queries. Without large annotated datasets, we qualitatively compare WorkflowGen against real-time planning, static single trajectory, and basic in-context learning baselines. Our method reduces token consumption by over 40 percent compared to real-time planning, improves success rate by 20 percent on medium-similarity queries through proactive error avoidance and adaptive fallback, and enhances deployability via modular, traceable experiences and cross-scenario adaptability. WorkflowGen achieves a practical balance of efficiency, robustness, and interpretability, addressing key limitations of existing approaches. --- ### Explainable AML Triage with LLMs: Evidence Retrieval and Counterfactual Checks Authors: Dorothy Torres, Wei Cheng, Ke Hu Published: 2026-03-22 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2604.19755v2 Anti-money laundering (AML) transaction monitoring generates large volumes of alerts that must be rapidly triaged by investigators under strict audit and governance constraints. While large language models (LLMs) can summarize heterogeneous evidence and draft rationales, unconstrained generation is risky in regulated workflows due to hallucinations, weak provenance, and explanations that are not faithful to the underlying decision. We propose an explainable AML triage framework that treats triage as an evidence-constrained decision process. Our method combines (i) retrieval-augmented evidence bundling from policy/typology guidance, customer context, alert triggers, and transaction subgraphs, (ii) a structured LLM output contract that requires explicit citations and separates supporting from contradicting or missing evidence, and (iii) counterfactual checks that validate whether minimal, plausible perturbations lead to coherent changes in both the triage recommendation and its rationale. We evaluate on public synthetic AML benchmarks and simulators and compare against rules, tabular and graph machine-learning baselines, and LLM-only/RAG-only variants. Results show that evidence grounding substantially improves auditability and reduces numerical and policy hallucination errors, while counterfactual validation further increases decision-linked explainability and robustness, yielding the best overall triage performance (PR-AUC 0.75; Escalate F1 0.62) and strong provenance and faithfulness metrics (citation validity 0.98; evidence support 0.88; counterfactual faithfulness 0.76). These findings indicate that governed, verifiable LLM systems can provide practical decision support for AML triage without sacrificing compliance requirements for traceability and defensibility. --- ### Why AI Readiness Is an Organizational Learning Problem, Not a Technology Purchase Authors: Jeanne McClure, Gregg Gerdau Published: 2026-03-22 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.16369v2 Global corporate AI investment reached $252.3 billion in 2024, yet only 6% of firms report significant earnings impact. This article argues that AI project failure is fundamentally an organizational learning problem rather than a technology deficit. Drawing on a systematic synthesis of 19 large-scale industry and academic sources, including surveys of nearly 10,000 organizational leaders, we identify two categories of failure: organizational (culture, leadership alignment, governance, and human-AI learning deficits) and technical (semantic bottlenecks and output management challenges). We introduce the Siloed-Integrated-Orchestrated (SIO) progression model, which maps enterprise AI capability across five pillars -- Culture & Leadership, Human Capital & Operations, Data Architecture, Systems Infrastructure, and Governance & Regulatory Compliance -- and provides prescriptive guidance for advancing between stages. The implications challenge organizations to reframe AI investment as capability development rather than technology procurement. --- ### Cross-Family Speculative Decoding for Polish Language Models on Apple~Silicon: An Empirical Evaluation of Bielik~11B with UAG-Extended MLX-LM Authors: Krzysztof Fonal Published: 2026-03-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16368v2 Speculative decoding accelerates LLM inference by using a small draft model to propose k candidate tokens for a target model to verify. While effective for same-tokenizer pairs on high-bandwidth GPUs, its applicability to cross-family pairs with mismatched tokenizers and consumer-grade unified memory remains underexplored. We extend the MLX-LM framework with Universal Assisted Generation (UAG) to enable cross-tokenizer speculative decoding on Apple Silicon. We evaluate Bielik 11B-Instruct (Mistral-based) as the target model, paired with three draft models: Bielik 1.5B (Qwen-based with custom tokenizer), Qwen2.5-1.5B, and Llama 3.2-1B. Experiments on three Polish-language datasets (Wikipedia, pl_alpaca, synthetic) use draft lengths k in {2, 4, 6} to compare naive and context-aware token translation. Results show: (1) context-aware translation consistently improves acceptance rates across all configurations; (2) the Polish-specialized Bielik 1.5B achieves lower acceptance than general-purpose Qwen2.5 and Llama 3.2 drafters; (3) throughput on Apple Silicon is content-dependent, reaching 1.7x speedup for structured text but failing for varied instructions; and (4) verification cost on unified memory does not amortize as theory predicts because both models are memory-bandwidth bound, making sequential drafting expensive relative to batched verification. We propose a hardware-aware speedup formula and characterize conditions for cross-family speculative decoding on Apple Silicon. This is the first systematic evaluation of cross-family speculative decoding for Polish LLMs and the first empirical study of UAG-based decoding on unified memory architectures. --- ### Talk, Walk, and Market Response: Multimodal Measurement of AI Washing and Its Capital Market Consequences in China Authors: Wen Zhanjie, Guo Jingqiao Published: 2026-03-22 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2604.16367v1 As artificial intelligence and generative large language models drive industrial upgrading, capital markets increasingly focus on AI-themed listed firms. Information asymmetry and technological opacity lower the cost of exaggerating AI capabilities relative to genuine R&D, spurring widespread AI Washing. Using China's A-share market from 2018Q1 to 2025Q2, we advance literature in measurement and mechanism testing. We construct a multimodal AI Washing Risk Score (AWRS) via Qwen-VL to assess text-image consistency in annual reports and roadshows, and a Material Real-Investment Matching Index (MRMI) from patent quality, AI intangible asset capitalization, and technical personnel compensation using PCA. Four findings emerge: (1) AWRS lacks predictive power for future MRMI, with a wider rhetoric-action gap among financially constrained firms; (2) substantive AI investment boosts high-quality patents, while empty rhetoric crowds out industry innovation; (3) long-horizon institutional investors detect AI Washing through site visits and reduce holdings; (4) such divestment triggers analyst downgrades, retail selling, and sharp valuation corrections within 180 days. Results are robust to IV-2SLS and staggered DID using the ChatGPT shock. This study enhances disclosure and pricing-efficiency research and supports RegTech for curbing thematic speculation. --- ### Decoding AI Tutor Effects for Educational Measurement: Temporal, Multi-Outcome, and Behavior-Cognitive Analysis Authors: Yiyao Yang, Yasemin Gulbahar Published: 2026-03-22 Categories: cs.CY, cs.LG arXiv: https://arxiv.org/abs/2604.16366v1 Artificial intelligence (AI) tutors have become increasingly popular in learning environments. In this study, we propose an AI agent prototype framework for exploring AI-assisted learning with temporal interaction patterns, multiple outcomes analysis, and behavioral-cognitive learner profiling. Based on three research questions, this study aims to investigate whether early interaction patterns can predict later performance and trust, how multiple outcomes can be traded off with different AI tutor feedback conditions, and if learner profiles can be identified with behavioral and cognitive indicators. An AI tutor agent has been developed to provide various feedback forms to learners, including hints, explanations, examples, and code. A neural policy model and a stochastic simulation framework are used to produce artificial student-AI tutor interaction records, which include response time, attempts, hint requests, correctness, quiz results, improvement, satisfaction, and trust. Temporal features are used to predict later correctness and trust with early interaction patterns, and clustering methods are used to find learner profiles. The results showed that early interaction patterns were predictive of later performance and trust, that student behavior changed over time with AI-based tutoring, and that latent student profiles could be identified based on their behavioral and cognitive differences. --- ### Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models Authors: Andrew Kiruluta Published: 2026-03-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14156v1 Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and structured sparsity can preserve accuracy under substantial compression, while prompt-compression methods reduce latency by removing redundant input tokens. However, these two directions remain largely separate. Most model-compression methods are static and optimized offline, and they do not exploit the fact that different prompts and decoding steps activate different latent computational pathways. Prompt-compression methods reduce sequence length, but they do not adapt the executed model subnetwork. We propose a unified compressed-sensing-guided framework for dynamic LLM execution. Random measurement operators probe latent model usage, sparse recovery estimates task-conditioned and token-adaptive support sets, and the recovered supports are compiled into hardware-efficient sparse execution paths over blocks, attention heads, channels, and feed-forward substructures. The framework introduces five key contributions: task-conditioned measurements, so different prompts induce different sparse supports; token-adaptive recovery, so active substructures are re-estimated during decoding; formal sample-complexity bounds under restricted isometry or mutual incoherence assumptions; compile-to-hardware constraints that restrict recovery to GPU-efficient structures; and a joint objective that unifies prompt compression with model reduction. Together, these components recast LLM inference as a measurement-and-recovery problem with explicit approximation guarantees and deployment-oriented speedup constraints. --- ### 3D Multi-View Stylization with Pose-Free Correspondences Matching for Robust 3D Geometry Preservation Authors: Shirsha Bose Published: 2026-03-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.09639v1 Artistic style transfer is well studied for images and videos, but extending it to multi-view 3D scenes remains difficult because stylization can disrupt correspondences needed by geometry-aware pipelines. Independent per-view stylization often causes texture drift, warped edges, and inconsistent shading, degrading SLAM, depth prediction, and multi-view reconstruction. This thesis addresses multi-view stylization that remains usable for downstream 3D tasks without assuming camera poses or an explicit 3D representation during training. We introduce a feed-forward stylization network trained with per-scene test-time optimization under a composite objective coupling appearance transfer with geometry preservation. Stylization is driven by an AdaIN-inspired loss from a frozen VGG-19 encoder, matching channel-wise moments to a style image. To stabilize structure across viewpoints, we propose a correspondence-based consistency loss using SuperPoint and SuperGlue, constraining descriptors from a stylized anchor view to remain consistent with matched descriptors from the original multi-view set. We also impose a depth-preservation loss using MiDaS/DPT and use global color alignment to reduce depth-model domain shift. A staged weight schedule introduces geometry and depth constraints. We evaluate on Tanks and Temples and Mip-NeRF 360 using image and reconstruction metrics. Style adherence and structure retention are measured by Color Histogram Distance (CHD) and Structure Distance (DSD). For 3D consistency, we use monocular DROID-SLAM trajectories and symmetric Chamfer distance on back-projected point clouds. Across ablations, correspondence and depth regularization reduce structural distortion and improve SLAM stability and reconstructed geometry; on scenes with MuVieCAST baselines, our method yields stronger trajectory and point-cloud consistency while maintaining competitive stylization. ---