# Research Papers — 2026-03 · bundle page 220 of 243 > Full-text markdown of papers #10951–11000 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/220 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/219.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/221.md) ### Multi-Agent Debate with Memory Masking Authors: Hongduan Tian, Xiao Feng, Ziyuan Zhao, Xiangyu Zhu, Rolan Yan, Bo Han Published: 2026-03-03 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.20215v1 Large language models (LLMs) have recently demonstrated impressive capabilities in reasoning tasks. Currently, mainstream LLM reasoning frameworks predominantly focus on scaling up inference-time sampling to enhance performance. In particular, among all LLM reasoning frameworks, *multi-agent debate* (MAD), which employs multiple LLMs as agents to perform reasoning in the way of multi-round debate, has emerged as a powerful reasoning paradigm since it allows agents to access previous memories to alleviate fallacious content and refine their reasoning iteratively in each debate round. However, although MAD significantly improves the reasoning capabilities of LLMs, in this paper, we observe that there remain erroneous memories, and LLM agents are vulnerable to these erroneous memories. To explore this phenomenon, we provide a theoretical insight that the performance of MAD is highly dependent on the quality of memories derived from the previous debate, indicating that the existence of erroneous memories poses a threat to the performance of MAD. To address this problem, we introduce a simple yet effective multi-agent debate framework, *multi-agent debate with memory masking* (MAD-M$^2$), to improve the robustness of MAD by allowing LLM agents to mask erroneous memories from the previous debate round at the beginning of each debate round. In this way, MAD-M$^2$ can polish the contextual information before each debate round by preserving informative and meaningful memories while discarding the erroneous memories. Extensive experiments and analyses on mainstream mathematical and logical reasoning benchmarks demonstrate that MAD-M$^2$ can identify the erroneous memories and achieve better performance in reasoning than MAD. --- ### EEG-Based Brain-LLM Interface for Human Preference Aligned Generation Authors: Junzi Zhang, Jianing Shen, Weijie Tu, Yi Zhang, Hailin Zhang, Tom Gedeon, Bin Jiang, Yue Yao Published: 2026-03-03 Categories: eess.SP, cs.CL, cs.HC, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2603.16897v1 Large language models (LLMs) are becoming an increasingly important component of human--computer interaction, enabling users to coordinate a wide range of intelligent agents through natural language. While language-based interfaces are powerful and flexible, they implicitly assume that users can reliably produce explicit linguistic input, an assumption that may not hold for users with speech or motor impairments, e.g., Amyotrophic Lateral Sclerosis (ALS). In this work, we investigate whether neural signals can be used as an alternative input to LLMs, particularly to support those socially marginalized or underserved users. We build a simple brain-LLM interface, which uses EEG signals to guide image generation models at test time. Specifically, we first train a classifier to estimate user satisfaction from EEG signals. Its predictions are then incorporated into a test-time scaling (TTS) framework that dynamically adapts model inference using neural feedback collected during user evaluation. The experiments show that EEG can predict user satisfaction, suggesting that neural activity carries information on real-time preference inference. These findings provide a first step toward integrating neural feedback into adaptive language-model inference, and hopefully open up new possibilities for future research on adaptive LLM interaction. --- ### EEG-SeeGraph: Interpreting functional connectivity disruptions in dementias via sparse-explanatory dynamic EEG-graph learning Authors: Fengcheng Wu, Zhenxi Song, Guoyang Xu, Kaisong Hu, Zirui Wang, Yi Guo, Zhiguo Zhang Published: 2026-03-03 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2603.16895v1 Robust and interpretable dementia diagnosis from noisy, non-stationary electroencephalography (EEG) is clinically essential yet remains challenging. To this end, we propose SeeGraph, a Sparse-Explanatory dynamic EEG-graph network that models time-evolving functional connectivity and employs a node-guided sparse edge mask to reveal the connections that drive diagnostic decisions, while remaining robust to noise and cross-site variability. SeeGraph comprises four components: (1) a dual-trajectory temporal encoder that models dynamic EEG with two streams, where node signals capture regional oscillations and edge signals capture interregional coupling; (2) a topology-aware positional encoder that derives graph-spectral Laplacian coordinates from the fused connectivity and augments node embeddings; (3) a node-guided sparse explanatory edge mask that gates the connectivity into a compact subgraph; and (4) a gated graph predictor that operates on the sparsified graph. The framework is trained using cross-entropy loss together with a sparsity regularizer on the mask, yielding noise-robust and interpretable diagnoses. The effectiveness of SeeGraph is validated on public and in-house EEG cohorts, including patients with neurodegenerative dementias and healthy controls, under both raw and noise-perturbed conditions. Its sparse, node-guided explanations highlight disease-relevant connections and align with established clinical findings on functional connectivity alterations, thereby offering transparent cues for neurological evaluation. --- ### Tokenization Tradeoffs in Structured EHR Foundation Models Authors: Lin Lawrence Guo, Santiago Eduardo Arciniegas, Joseph Jihyung Lee, Adam Paul Yan, George Tomlinson, Jason Fries, Lillian Sung Published: 2026-03-03 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2603.15644v1 Foundation models for structured electronic health records (EHRs) are pretrained on longitudinal sequences of timestamped clinical events to learn adaptable patient representations. Tokenization -- how these timelines are converted into discrete model inputs -- determines what information is preserved, how efficiently it is encoded, and which relationships must be learned versus precomputed. Yet the impact of tokenization design choices on downstream performance and computational efficiency remains largely unexplored. Here, we pretrained a transformer on pediatric EHR data under a factorial design, varying tokenization along event encoding, time encoding, and workflow annotation. We evaluated area-under-the-receiver-operating-characteristic curve across 74 clinical prediction tasks. Joint event encoding and positional time encoding outperformed their alternatives (73/74 and 71/74 tasks) while requiring 39.5% and 9.6% fewer pretraining floating-point operations, respectively. Targeted ablations traced the joint encoding advantage to local binding efficiency, that is, code-attribute pairs are combined into single tokens, rather than split across tokens that the model must learn to associate during pretraining. External evaluation on an adult intensive care unit cohort demonstrated that this advantage generalizes despite substantial vocabulary mismatch, while temporal and workflow effects remain institution-specific. These results establish tokenization as a tractable lever for improving both the performance and efficiency of EHR foundation models. --- ### GSI Agent: Domain Knowledge Enhancement for Large Language Models in Green Stormwater Infrastructure Authors: Shaohuang Wang Published: 2026-03-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.15643v1 Green Stormwater Infrastructure (GSI) systems, such as permeable pavement, rain gardens, and bioretention facilities, require continuous inspection and maintenance to ensure long-term performance. However, domain knowledge about GSI is often scattered across municipal manuals, regulatory documents, and inspection forms. As a result, non-expert users and maintenance staff may struggle to obtain reliable and actionable guidance from field observations. Although Large Language Models (LLMs) have demonstrated strong general reasoning and language generation capabilities, they often lack domain-specific knowledge and may produce inaccurate or hallucinated answers in engineering scenarios. This limitation restricts their direct application to professional infrastructure tasks. In this paper, we propose GSI Agent, a domain-enhanced LLM framework designed to improve performance in GSI-related tasks. Our approach integrates three complementary strategies: (1) supervised fine-tuning (SFT) on a curated GSI instruction dataset, (2) retrieval-augmented generation (RAG) over an internal GSI knowledge base constructed from municipal documents, and (3) an agent-based reasoning pipeline that coordinates retrieval, context integration, and structured response generation. We also construct a new GSI Dataset aligned with real-world GSI inspection and maintenance scenarios. Experimental results show that our framework significantly improves domain-specific performance while maintaining general knowledge capability. On the GSI dataset, BLEU-4 improves from 0.090 to 0.307, while performance on the common knowledge dataset remains stable (0.304 vs. 0.305). These results demonstrate that systematic domain knowledge enhancement can effectively adapt general-purpose LLMs to professional infrastructure applications. --- ### CraniMem: Cranial Inspired Gated and Bounded Memory for Agentic Systems Authors: Pearl Mody, Mihir Panchal, Rishit Kar, Kiran Bhowmick, Ruhina Karani Published: 2026-03-03 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.15642v1 Large language model (LLM) agents are increasingly deployed in long running workflows, where they must preserve user and task state across many turns. Many existing agent memory systems behave like external databases with ad hoc read/write rules, which can yield unstable retention, limited consolidation, and vulnerability to distractor content. We present CraniMem, a neurocognitively motivated, gated and bounded multi-stage memory design for agentic systems. CraniMem couples goal conditioned gating and utility tagging with a bounded episodic buffer for near term continuity and a structured long-term knowledge graph for durable semantic recall. A scheduled consolidation loop replays high utility traces into the graph while pruning low utility items, keeping memory growth in check and reducing interference. On long horizon benchmarks evaluated under both clean inputs and injected noise, CraniMem is more robust than a Vanilla RAG and Mem0 baseline and exhibits smaller performance drops under distraction. Our code is available at https://github.com/PearlMody05/Cranimem and the accompanying PyPI package at https://pypi.org/project/cranimem. --- ### Form Follows Function: Recursive Stem Model Authors: Navid Hakimi Published: 2026-03-03 Categories: cs.AI, cs.LG, cs.NE arXiv: https://arxiv.org/abs/2603.15641v1 Recursive reasoning models such as Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM) show that small, weight-shared networks can solve compute-heavy and NP puzzles by iteratively refining latent states, but their training typically relies on deep supervision and/or long unrolls that increase wall-clock cost and can bias the model toward greedy intermediate behavior. We introduce Recursive Stem Model (RSM), a recursive reasoning approach that keeps the TRM-style backbone while changing the training contract so the network learns a stable, depth-agnostic transition operator. RSM fully detaches the hidden-state history during training, treats early iterations as detached "warm-up" steps, and applies loss only at the final step. We further grow the outer recursion depth $H$ and inner compute depth $L$ independently and use a stochastic outer-transition scheme (stochastic depth over $H$) to mitigate instability when increasing depth. This yields two key capabilities: (i) $>20\times$ faster training than TRM while improving accuracy ($\approx 5\times$ reduction in error rate), and (ii) test-time scaling where inference can run for arbitrarily many refinement steps ($\sim 20,000 H_{\text{test}} \gg 20 H_{\text{train}}$), enabling additional "thinking" without retraining. On Sudoku-Extreme, RSM reaches 97.5% exact accuracy with test-time compute (within ~1 hour of training on a single A100), and on Maze-Hard ($30 \times 30$) it reaches ~80% exact accuracy in ~40 minutes using attention-based instantiation. Finally, because RSM implements an iterative settling process, convergence behavior provides a simple, architecture-native reliability signal: non-settling trajectories warn that the model has not reached a viable solution and can be a guard against hallucination, while stable fixed points can be paired with domain verifiers for practical correctness checks. --- ### Preventing Curriculum Collapse in Self-Evolving Reasoning Systems Authors: Vaibhav Mishra Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.13309v1 Self-evolving reasoning frameworks let LLMs improve their reasoning capabilities by iteratively generating and solving problems without external supervision, using verifiable rewards. Ideally, such systems are expected to explore a diverse problem space and propose new challenges of high learning value. While prior work has largely focused on solver-side optimisation and verification, recent evidence suggests that self-evolving systems can exhibit diversity collapse in posing new problems after just a few iterations, even when surface-level variation is preserved. We introduce Prism, a question-centric self-evolution method that directly tackles this collapse. Prism defines a persistent diversity signal over an embedding-induced semantic partition of mathematical problems and uses it to encourage balanced exploration of underrepresented regions across iterations. This coverage signal is combined with a Zone-of-Proximal-Development (ZPD) gate to preserve edge-of-solvability difficulty. Evaluated on seven widely used mathematical reasoning benchmarks against five self-evolving baselines, Prism achieves the highest accuracy on six out of seven tasks, achieving gains of +3.98 absolute points over R-Zero on AMC and +3.68 on Minerva Math. Prism also generates semantically diverse and challenging questions across iterations, resulting in the construction of the Prism-Math dataset comprising 100k mathematical questions. These results demonstrate that cross-iteration semantic coverage is a high-leverage and under-explored axis for building more capable self-evolving reasoners. We release the code, dataset, and models to facilitate further research. --- ### Task Expansion and Cross Refinement for Open-World Conditional Modeling Authors: Shreyas Bhat Brahmavar, Qiyang Liu, Yang Li, Junier Oliva Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.13308v1 Open-world conditional modeling (OCM), requires a single model to answer arbitrary conditional queries across heterogeneous datasets, where observed variables and targets vary and arise from a vast open-ended task universe. Because any finite collection of real-world datasets covers only a small fraction of this space, we propose Task Expansion and Cross Refinement (TEXR), a semi-supervised framework that enlarges effective task coverage through structured synthesis and refinement of semantic data contexts. TEXR first generates diverse uninstantiated dataset schemas and weakly instantiates them via structured probabilistic generators guided by large language models. It then performs cross-model refinement by training on disjoint data partitions and revising synthetic values across splits to reduce confirmation bias and improve pseudo-value quality. The refined synthetic datasets are aggregated with real data to train a unified conditional model. Across heterogeneous tabular benchmarks, TEXR consistently improves zero-, few-, and many-shot performance for multiple OCM backbones, demonstrating that structured task expansion and cross refinement enhance open-world conditional modeling. --- ### Suppressing Domain-Specific Hallucination in Construction LLMs: A Knowledge Graph Foundation for GraphRAG and QLoRA on River and Sediment Control Technical Standards Authors: Takato Yasuno Published: 2026-03-03 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2603.13307v1 This paper addresses the challenge of answering technical questions derived from Japan's River and Sediment Control Technical Standards -- a multi-volume regulatory document covering survey, planning, design, and maintenance of river levees, dams, and sabo structures -- using open-source large language models running entirely on local hardware. We implement and evaluate three complementary approaches: Case A (plain 20B LLM baseline), Case B (8B LLM with QLoRA domain fine-tuning on 715 graph-derived QA pairs), and Case C (20B LLM augmented with a Neo4j knowledge graph via GraphRAG). All three cases use the Swallow series of Japanese-adapted LLMs and are evaluated on a 100-question benchmark spanning 8 technical categories, judged automatically by an independent LLM (Qwen2.5-14B, score 0--3). The key finding is a performance inversion: the 8B QLoRA fine-tuned model (Case B) achieves a judge average of 2.92/3 -- surpassing both the 20B plain baseline (Case A: 2.29/3, $+$0.63) and the 20B GraphRAG approach (Case C: 2.62/3, $+$0.30) -- while running at 3$\times$ faster latency (14.2s vs. 42.2s for Case A). GraphRAG provides moderate gains ($+$0.33 over baseline) but is outperformed by domain-specific fine-tuning in both quality and efficiency. We document the full engineering pipeline, including knowledge graph construction (200 nodes, 268 relations), QLoRA training data generation from Neo4j relations, training on a single GPU (16 GB VRAM) using unsloth, GGUF Q4_K_M quantisation and Ollama deployment, and the graph retrieval and re-ranking design. High-level engineering lessons are distilled in the main body; implementation pitfalls and toolchain details are documented in Supplementary Materials. --- ### Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision Authors: Kirill Borodin, Kirill Kondrashov, Nikita Vasiliev, Ksenia Gladkova, Inna Larina, Mikhail Gorodnichev, Grach Mkrtchian Published: 2026-03-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.13306v1 CCTV safety monitoring demands anomaly detectors combine reliable clip-level accuracy with predictable per-clip latency despite weak supervision. This work investigates compact vision-language models (VLMs) as practical detectors for this regime. A unified evaluation protocol standardizes preprocessing, prompting, dataset splits, metrics, and runtime settings to compare parameter-efficiently adapted compact VLMs against training-free VLM pipelines and weakly supervised baselines. Evaluation spans accuracy, precision, recall, F1, ROC-AUC, and average per-clip latency to jointly quantify detection quality and efficiency. With parameter-efficient adaptation, compact VLMs achieve performance on par with, and in several cases exceeding, established approaches while retaining competitive per-clip latency. Adaptation further reduces prompt sensitivity, producing more consistent behavior across prompt regimes under the shared protocol. These results show that parameter-efficient fine-tuning enables compact VLMs to serve as dependable clip-level anomaly detectors, yielding a favorable accuracy-efficiency trade-off within a transparent and consistent experimental setup. --- ### Evidence-based Distributional Alignment for Large Language Models Authors: Viet-Thanh Pham, Lizhen Qu, Zhuang Li, Gholamreza Haffari Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.13305v1 Distributional alignment enables large language models (LLMs) to predict how a target population distributes its responses across answer options, rather than collapsing disagreement into a single consensus answer. However, existing LLM-based distribution prediction is often unstable and degrades under cultural and domain shift. Token score-based estimates can change with minor option wording or formatting, response sampling-based estimates are expensive and sensitive to prompts and decoding settings, and directly generated distributions are frequently miscalibrated. We propose Evi-DA, an evidence-based alignment technique that improves the fidelity and robustness of LLM-based distribution estimation under domain and cultural shift. Given a target country and a multiple-choice question, Evi-DA retrieves related World Values Survey items and their answer distributions, predicts a coarse Welzel value signature for each option, and infers the country-conditioned answer distribution in a structured format. We train the LLMs using a two-stage pipeline, where reinforcement learning optimizes survey-derived rewards that encourage accurate intermediate value predictions, faithful final distributions, well-formed structured outputs, and reduced cultural bias. Across in-domain and out-of-domain benchmarks and multiple open-source backbones, Evi-DA reduces Jensen-Shannon divergence between predicted and gold distributions relative to strong baselines, with average relative improvements of up to 44%. --- ### VB: Visibility Benchmark for Visibility and Perspective Reasoning in Images Authors: Neil Tripathi Published: 2026-03-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06680v1 We present VB, a benchmark that tests whether vision-language models can determine what is and is not visible in a photograph, and abstain when a human viewer cannot reliably answer. Each item pairs a single photo with a short yes/no visibility claim; the model must output VISIBLY_TRUE, VISIBLY_FALSE, or ABSTAIN, together with a confidence score. Items are organized into 100 families using a 2x2 design that crosses a minimal image edit with a minimal text edit, yielding 300 headline evaluation cells. Unlike prior unanswerable-VQA benchmarks, VB tests not only whether a question is unanswerable but why (via reason codes tied to specific visibility factors), and uses controlled minimal edits to verify that model judgments change when and only when the underlying evidence changes. We score models on confidence-aware accuracy with abstention (CAA), minimal-edit flip rate (MEFR), confidence-ranked selective prediction (SelRank), and second-order perspective reasoning (ToMAcc); all headline numbers are computed on the strict XOR subset (three cells per family, 300 scored items per model). We evaluate nine models spanning flagship and prior-generation closed-source systems, and open-source models from 8B to 12B parameters. GPT-4o and Gemini 3.1 Pro effectively tie for the best composite score (0.728 and 0.727), followed by Gemini 2.5 Pro (0.678). The best open-source model, Gemma 3 12B (0.505), surpasses one prior-generation closed-source system. Text-flip robustness exceeds image-flip robustness for six of nine models, and confidence calibration varies substantially: GPT-4o and Gemini 2.5 Pro achieve similar accuracy yet differ sharply in selective prediction quality. --- ### MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines Authors: Ryan Po, David Junhao Zhang, Amir Hertz, Gordon Wetzstein, Neal Wadhwa, Nataniel Ruiz Published: 2026-03-03 Categories: cs.AI, cs.CV, cs.GR arXiv: https://arxiv.org/abs/2603.06679v2 Video world models have shown immense promise for interactive simulation and entertainment, but current systems still struggle with two important aspects of interactivity: user control over the environment for reproducible, editable experiences, and shared inference where players hold influence over a common world. To address these limitations, we introduce an explicit external memory into the system, a persistent state operating independent of the model's context window, that is continually updated by user actions and queried throughout the generation roll-out. Unlike conventional diffusion game engines that operate as next-frame predictors, our approach decomposes generation into Memory, Observation, and Dynamics modules. This design gives users direct, editable control over environment structure via an editable memory representation, and it naturally extends to real-time multiplayer rollouts with coherent viewpoints and consistent cross-player interactions. --- ### Chart Deep Research in LVLMs via Parallel Relative Policy Optimization Authors: Jiajin Tang, Gaoyang, Wenjie Wang, Sibei Yang, Xing Chen Published: 2026-03-03 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.06677v1 With the rapid advancement of data science, charts have evolved from simple numerical presentation tools to essential instruments for insight discovery and decision-making support. However, current chart data intelligence exhibits significant limitations in deep research capabilities, with existing methods predominantly addressing shallow tasks such as visual recognition or factual question-answering, rather than the complex reasoning and high-level data analysis that deep research requires. This limitation stems from two primary technical bottlenecks: at the training level, existing post-training techniques exhibit deficiencies in handling multi-dimensional reward signal interference and heterogeneous data gradient conflicts, preventing models from achieving balanced development across multiple capability dimensions; at the evaluation level, current methods remain limited to factual retrieval and basic computation, failing to assess end-to-end analytic reasoning and other deep research capabilities. To address the training challenge, we propose PRPO, which performs parallel optimization across reward dimensions and capability partitioning across data types, effectively disentangling conflicts between heterogeneous data and multi-dimensional reward signals while ensuring optimization stability. For the evaluation challenge, we construct MCDR-Bench based on the ``error uniqueness principle," transforming subjective generation assessment into objective error identification through controllable error injection, enabling quantifiable evaluation of deep research capabilities. Experimental validation confirms that the proposed PRPO and MCDR-Bench jointly establish a unified framework that systematically advances chart deep research through enhanced collaborative training and objective evaluation. --- ### XAI and Few-shot-based Hybrid Classification Model for Plant Leaf Disease Prognosis Authors: Diana Susan Joseph, Pranav M Pawar, Raja Muthalagu, Mithun Mukharjee Published: 2026-03-03 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.06676v1 Performing a timely and accurate identification of crop diseases is vital to maintain agricultural productivity and food security. The current work presents a hybrid few-shot learning model that integrates Explainable Artificial Intelligence (XAI) and Few-Shot Learning (FSL) to address the challenge of identifying and classifying the stages of disease of the diseases of maize, rice, and wheat leaves under limited annotated data conditions. The proposed model integrates Siamese and Prototypical Networks within an episodic training paradigm to effectively learn discriminative disease features from a few examples. To ensure model transparency and trustworthiness, Gradient-weighted Class Activation Mapping (Grad-CAM) is employed for visualizing key decision regions in the leaf images, offering interpretable insights into the classification process. Experimental evaluations on custom few-shot datasets developed in the study prove that the model consistently achieves high accuracy, precision, recall, and F1-scores, frequently exceeding 92% across various disease stages. Comparative analyses against baseline FSL models further confirm the superior performance and explainability of the proposed approach. The framework offers a promising solution for real-world, data-constrained agricultural disease monitoring applications. --- ### GNN For Muon Particle Momentum estimation Authors: Vishak K Bhat, Eric A. F. Reinhardt, Sergei Gleyzer Published: 2026-03-03 Categories: physics.data-an, cs.LG, hep-ex arXiv: https://arxiv.org/abs/2603.06675v1 Due to a high rate of overall data generation relative to data generation of interest, the CMS experiment at the Large Hadron Collider uses a combination of hardware- and software-based triggers to select data for capture. Accurate momentum calculation is crucial for improving the efficiency of the CMS trigger systems, enabling better classification of low- and high- momentum particles and reducing false triggers. This paper explores the use of Graph Neural Networks (GNNs) for the momentum estimation task. We present two graph construction methods and apply a GNN model to leverage the inherent graph structure of the data. In this paper firstly, we show that the GNN outperforms traditional models like TabNet in terms of Mean Absolute Error (MAE), demonstrating its effectiveness in capturing complex dependencies within the data. Secondly we show that the dimension of the node feature is crucial for the efficiency of GNN. --- ### AutoFigure-Edit: Generating Editable Scientific Illustration Authors: Zhen Lin, Qiujie Xie, Minjun Zhu, Shichen Li, Qiyao Sun, Enhao Gu, Yiran Ding, Ke Sun, Fang Guo, Panzhong Lu, Zhiyuan Ning, Yixuan Weng et al. Published: 2026-03-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06674v1 High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We present AutoFigure-Edit, an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images. By combining long-context understanding, reference-guided styling, and native SVG editing, it enables efficient creation and refinement of high-quality scientific illustrations. To facilitate further progress in this field, we release the video at https://youtu.be/10IH8SyJjAQ, full codebase at https://github.com/ResearAI/AutoFigure-Edit and provide a website for easy access and interactive use at https://deepscientist.cc/. --- ### Unmixing ATR-μFTIR spectroscopic images of cross-sections of historical oil paintings Authors: Shivam Pande, Nicolas Nadisic, Francisco Mederos-Henry, Aleksandra Pizurica Published: 2026-03-03 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.06673v2 Spectroscopic imaging (SI) has become central to heritage science because it enables non-invasive, spatially resolved characterisation of materials in artefacts. In particular, attenuated total reflection Fourier transform infrared microscopy (ATR-$μ$FTIR) is widely used to analyse painting cross-sections, where a spectrum is recorded at each pixel to form a hyperspectral image (HSI). Interpreting these data is difficult: spectra are often mixtures of several species in heterogeneous, multi-layered and degraded samples, and current practice still relies heavily on manual comparison with reference libraries. This workflow is slow, subjective and hard to scale. We propose an unsupervised CNN autoencoder for blind unmixing of ATR-$μ$FTIR HSIs, estimating endmember spectra and their abundance maps while exploiting local spatial structure through patch-based modelling. To reduce sensitivity to atmospheric and acquisition artefacts across more than 1500 bands, we introduce a weighted spectral angle distance (WSAD) loss with automatic band-reliability weights derived from robust measures of spatial flatness, neighbour agreement and spectral roughness. Compared with standard SAD training, WSAD improves interpretability in contamination-prone spectral regions. We demonstrate the method on an ATR-$μ$FTIR cross-section from the Ghent Altarpiece by the Van Eyck brothers. --- ### Does Semantic Noise Initialization Transfer from Images to Videos? A Paired Diagnostic Study Authors: Yixiao Jing, Chaoyu Zhang, Zixuan Zhong, Peizhou Huang Published: 2026-03-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06672v1 Semantic noise initialization has been reported to improve robustness and controllability in image diffusion models. Whether these gains transfer to text-to-video (T2V) generation remains unclear, since temporal coupling can introduce extra degrees of freedom and instability. We benchmark semantic noise initialization against standard Gaussian noise using a frozen VideoCrafter-style T2V diffusion backbone and VBench on 100 prompts. Using prompt-level paired tests with bootstrap confidence intervals and a sign-flip permutation test, we observe a small positive trend on temporal-related dimensions; however, the 95 percent confidence interval includes zero (p ~ 0.17) and the overall score remains on par with the baseline. To understand this outcome, we analyze the induced perturbations in noise space and find patterns consistent with weak or unstable signal. We recommend prompt-level paired evaluation and noise-space diagnostics as standard practice when studying initialization schemes for T2V diffusion. --- ### ERP-RiskBench: Leakage-Safe Ensemble Learning for Financial Risk Authors: Sanjay Mishra Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.06671v1 Financial risk detection in Enterprise Resource Planning (ERP) systems is an important but underexplored application of machine learning. Published studies in this area tend to suffer from vague dataset descriptions, leakage-prone pipelines, and evaluation practices that inflate reported performance. This paper presents a rebuilt experimental framework for ERP financial risk detection using ensemble machine learning. The risk definition is hybrid, covering both procurement compliance anomalies and transactional fraud. A composite benchmark called ERP-RiskBench is assembled from public procurement event logs, labeled fraud data, and a new synthetic ERP dataset with rule-injected risk typologies and conditional tabular GAN augmentation. Nested cross-validation with time-aware and group-aware splitting enforces leakage prevention throughout the pipeline. The primary model is a stacking ensemble of gradient boosting methods, tested alongside linear baselines, deep tabular architectures, and an interpretable glassbox alternative. Performance is measured through Matthews Correlation Coefficient, area under the precision-recall curve, and cost-sensitive decision analysis using calibrated probabilities. Across multiple dataset configurations and a structured ablation study, the stacking ensemble achieves the best detection results. Leakage-safe protocols reduce previously inflated accuracy estimates by a notable margin. SHAP-based explanations and feature stability analysis show that procurement control features, especially three-way matching discrepancies, rank as the most informative predictors. The resulting framework provides a reproducible, operationally grounded blueprint for machine learning deployment in ERP audit and governance settings. --- ### calibfusion: Transformer-Based Differentiable Calibration for Radar-Camera Fusion Detection in Water-Surface Environments Authors: Yuting Wan, Liguo Sun, Jiuwu Hao, Pin LV Published: 2026-03-03 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.06670v1 Millimeter-wave (mmWave) Radar--Camera fusion improves perception under adverse illumination and weather, but its performance is sensitive to Radar--Camera extrinsic calibration: residual misalignment biases Radar-to-image projection and degrades cross-modal aggregation for downstream 2D detection. Existing calibration and auto-calibration methods are mainly developed for road and urban scenes with abundant structures and object constraints, whereas water-surface environments feature large textureless regions, sparse and intermittent targets, and wave-/specular-induced Radar clutter, which weakens explicit object-centric matching. We propose CalibFusion, a calibration-conditioned Radar--Camera fusion detector that learns implicit extrinsic refinement end-to-end with the detection objective. CalibFusion builds a multi-frame persistence-aware Radar density representation with intensity weighting and Doppler-guided suppression of fast-varying clutter. A cross-modal transformer interaction module predicts a confidence-gated refinement of the initial extrinsics, which is integrated through a differentiable projection-and-splatting operator to generate calibration-conditioned image-plane Radar features. Experiments on WaterScenes and FLOW show improved fusion-based 2D detection and robustness under synthetic miscalibration, supported by sensitivity analyses and qualitative Radar-to-image overlays. Results on nuScenes indicate that the refinement mechanism transfers beyond water-surface scenarios. --- ### Hybrid Orchestration of Edge AI and Microservices via Graph-based Self-Imitation Learning Authors: Chen Yang, Jin Zheng, Yang Zhuolin, Lai Pan, Zhang Xiao, Hu Menglan, Yin Haiyan Published: 2026-03-03 Categories: cs.NI, cs.AI arXiv: https://arxiv.org/abs/2603.06669v1 Modern edge AI applications increasingly rely on microservice architectures that integrate both AI services and conventional microservices into complex request chains with stringent latency requirements. Effectively orchestrating these heterogeneous services is crucial for ensuring low-latency performance, yet remains challenging due to their diverse resource demands and strong operational interdependencies under resource-constrained edge environments. In particular, frequent interactions between services tightly couple deployment and routing decisions, yet existing approaches optimize them in isolation, leading to fundamentally inadequate system performance.In this paper, we propose SIL-GPO, a reinforcement learning framework that optimizes hybrid orchestration for edge AI microservice systems. SIL-GPO formulates the orchestration problem as a sequential decision-making task and leverages graph attention networks to encode service topologies and routing dependencies within the agent state representation. Moreover, SIL-GPO integrates a self-imitation learning strategy into proximal policy optimization, enabling the agent to prioritize and reuse high-reward trajectories. This guides policy updates towards globally promising solutions that standard RL often fails to discover under sparse rewards and large combinatorial action spaces. We conduct extensive experiments on trace-driven edge AI workloads, demonstrating that SIL-GPO significantly reduces end-to-end service latency and enhances resource utilization compared to state-of-the-art heuristic, metaheuristic, and deep RL baselines. Our framework offers a unified and scalable solution for efficient orchestration of AI services and microservices in the edge, paving the way for low-latency, high-performance edge AI deployments. --- ### Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation Authors: Vaishak Kumar Published: 2026-03-03 Categories: cs.RO, cs.LG arXiv: https://arxiv.org/abs/2603.04466v1 Can a multimodal language model learn to manipulate physical objects by reasoning about its own failures-without gradient updates, demonstrations, or reward engineering? We argue the answer is yes, under conditions we characterise precisely. We present Act-Observe-Rewrite (AOR), a framework in which an LLM agent improves a robot manipulation policy by synthesising entirely new executable Python controller code between trials, guided by visual observations and structured episode outcomes. Unlike prior work that grounds LLMs in pre-defined skill libraries or uses code generation for one-shot plan synthesis, AOR makes the full low-level motor control implementation the unit of LLM reasoning, enabling the agent to change not just what the robot does, but how it does it. The central claim is that interpretable code as the policy representation creates a qualitatively different kind of in-context learning from opaque neural policies: the agent can diagnose systematic failures and rewrite their causes. We validate this across three robosuite manipulation tasks and report promising results, with the agent achieving high success rates without demonstrations, reward engineering, or gradient updates. --- ### Understanding the Dynamics of Demonstration Conflict in In-Context Learning Authors: Difan Jiao, Di Wang, Lijie Hu Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.04464v1 In-context learning enables large language models to perform novel tasks through few-shot demonstrations. However, demonstrations per se can naturally contain noise and conflicting examples, making this capability vulnerable. To understand how models process such conflicts, we study demonstration-dependent tasks requiring models to infer underlying patterns, a process we characterize as rule inference. We find that models suffer substantial performance degradation from a single demonstration with corrupted rule. This systematic misleading behavior motivates our investigation of how models process conflicting evidence internally. Using linear probes and logit lens analysis, we discover that under corruption models encode both correct and incorrect rules in intermediate layers but develop prediction confidence only in late layers, revealing a two-phase computational structure. We then identify attention heads for each phase underlying the reasoning failures: Vulnerability Heads in early-to-middle layers exhibit positional attention bias with high sensitivity to corruption, while Susceptible Heads in late layers significantly reduce support for correct predictions when exposed to the corrupted evidence. Targeted ablation validates our findings, with masking a small number of identified heads improving performance by over 10%. --- ### MAD-SmaAt-GNet: A Multimodal Advection-Guided Neural Network for Precipitation Nowcasting Authors: Samuel van Wonderen, Siamak Mehrkanoon Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.04461v1 Precipitation nowcasting (short-term forecasting) is still often performed using numerical solvers for physical equations, which are computationally expensive and make limited use of the large volumes of available weather data. Deep learning models have shown strong potential for precipitation nowcasting, offering both accuracy and computational efficiency. Among these models, convolutional neural networks (CNNs) are particularly effective for image-to-image prediction tasks. The SmaAt-UNet is a lightweight CNN based architecture that has demonstrated strong performance for precipitation nowcasting. This paper introduces the Multimodal Advection-Guided Small Attention GNet (MAD-SmaAt-GNet), which extends the core SmaAt-UNet by (i) incorporating an additional encoder to learn from multiple weather variables and (ii) integrating a physics-based advection component to ensure physically consistent predictions. We show that each extension individually improves rainfall forecasts and that their combination yields further gains. MAD-SmaAt-GNet reduces the mean squared error (MSE) by 8.9% compared with the baseline SmaAt-UNet for four-step precipitation forecasting up to four hours ahead. Additionally, experiments indicate that multimodal inputs are particularly beneficial for short lead times, while the advection-based component enhances performance across both short and long forecasting horizons. --- ### VSPrefill: Vertical-Slash Sparse Attention with Lightweight Indexing for Long-Context Prefilling Authors: Chen Guanzhong Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.04460v1 The quadratic complexity of self-attention during the prefill phase impedes long-context inference in large language models. Existing sparse attention methods face a trade-off among context adaptivity, sampling overhead, and fine-tuning costs. We propose VSPrefill, a mechanism requiring lightweight training that uses the vertical-slash structural pattern in attention distributions. Our compact VSIndexer module predicts context-aware importance scores for vertical columns and slash diagonals from key-value representations augmented with RoPE. This approach constructs sparse masks with linear complexity without modifying the backbone parameters. During inference, an adaptive cumulative-threshold strategy allocates sparsity budgets per layer, while a fused kernel executes attention with on-the-fly index merging. Evaluated on Qwen3-4B-Instruct and LLaMA-3.1-8B-Instruct across the LongBench and RULER benchmarks, VSPrefill preserves 98.35% of the full attention accuracy while delivering a 4.95x average speedup at a context length of 128k. These results establish a new Pareto frontier in the trade-off between accuracy and efficiency. --- ### Benchmark of Benchmarks: Unpacking Influence and Code Repository Quality in LLM Safety Benchmarks Authors: Junjie Chu, Xinyue Shen, Ye Leng, Michael Backes, Yun Shen, Yang Zhang Published: 2026-03-03 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2603.04459v3 The rapid expansion of research in LLM safety presents challenges in tracking advancements, making benchmarks important evaluation infrastructures for identifying key trends and facilitating systematic comparisons. Yet no systematic assessment exists of their code quality and runnability, nor of what factors are associated with the community's adoption of certain benchmarks over others. To address this gap, we conduct a systematic measurement study of 31 LLM safety benchmarks (covering prompt injection, jailbreak, and hallucination) with 382 non-benchmark papers as a control group, combining automated static analysis, human runnability testing (220+ person-hours), and bibliometric analysis. We find that only 39\% of benchmark repositories can run without modification, only 16\% provide flawless installation guides, and a mere 6\% include ethical considerations despite containing potentially harmful content. These deficiencies persist across the study period with no significant improvement. Analyzing adoption factors, we find that benchmark adoption correlates with author prominence and code runnability, but not with code quality standards such as Pylint score and maintainability, suggesting that the community's benchmark selection does not reward higher coding standards. Based on these results, we identify potential safety and reliability concerns. Some safety benchmark repositories openly expose harmful content, such as successful jailbreak responses, without any ethical warning or access control, effectively serving as unguarded attack resources. Furthermore, when benchmarks require ad-hoc modifications to run, downstream safety evaluations across different papers may not be comparable. We present case studies illustrating these concrete consequences and propose a targeted checklist to help benchmark contributors improve code quality, documentation, and ethical practices. --- ### Learning Unified Distance Metric for Heterogeneous Attribute Data Clustering Authors: Yiqun Zhang, Mingjie Zhao, Yizhou Chen, Yang Lu, Yiu-ming Cheung Published: 2026-03-03 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.04458v1 Datasets composed of numerical and categorical attributes (also called mixed data hereinafter) are common in real clustering tasks. Differing from numerical attributes that indicate tendencies between two concepts (e.g., high and low temperature) with their values in well-defined Euclidean distance space, categorical attribute values are different concepts (e.g., different occupations) embedded in an implicit space. Simultaneously exploiting these two very different types of information is an unavoidable but challenging problem, and most advanced attempts either encode the heterogeneous numerical and categorical attributes into one type, or define a unified metric for them for mixed data clustering, leaving their inherent connection unrevealed. This paper, therefore, studies the connection among any-type of attributes and proposes a novel Heterogeneous Attribute Reconstruction and Representation (HARR) learning paradigm accordingly for cluster analysis. The paradigm transforms heterogeneous attributes into a homogeneous status for distance metric learning, and integrates the learning with clustering to automatically adapt the metric to different clustering tasks. Differing from most existing works that directly adopt defined distance metrics or learn attribute weights to search clusters in a subspace. We propose to project the values of each attribute into unified learnable multiple spaces to more finely represent and learn the distance metric for categorical data. HARR is parameter-free, convergence-guaranteed, and can more effectively self-adapt to different sought number of clusters $k$. Extensive experiments illustrate its superiority in terms of accuracy and efficiency. --- ### Capability Thresholds and Manufacturing Topology: How Embodied Intelligence Triggers Phase Transitions in Economic Geography Authors: Xinmin Fang, Lingfeng Tao, Zhengxiong Li Published: 2026-03-03 Categories: cs.AI, cs.CE, physics.soc-ph arXiv: https://arxiv.org/abs/2603.04457v1 The fundamental topology of manufacturing has not undergone a paradigm-level transformation since Henry Ford's moving assembly line in 1913. Every major innovation of the past century, from the Toyota Production System to Industry 4.0, has optimized within the Fordist paradigm without altering its structural logic: centralized mega-factories, located near labor pools, producing at scale. We argue that embodied intelligence is poised to break this century-long stasis, not by making existing factories more efficient, but by triggering phase transitions in manufacturing economic geography itself. When embodied AI capabilities cross critical thresholds in dexterity, generalization, reliability, and tactile-vision fusion, the consequences extend far beyond cost reduction: they restructure where factories are built, how supply chains are organized, and what constitutes viable production scale. We formalize this by defining a Capability Space C = (d, g, r, t) and showing that the site-selection objective function undergoes topological reorganization when capability vectors cross critical surfaces. Through three pathways, weight inversion, batch collapse, and human-infrastructure decoupling, we show that embodied intelligence enables demand-proximal micro-manufacturing, eliminates "manufacturing deserts," and reverses geographic concentration driven by labor arbitrage. We further introduce Machine Climate Advantage: once human workers are removed, optimal factory locations are determined by machine-optimal conditions (low humidity, high irradiance, thermal stability), factors orthogonal to traditional siting logic, creating a production geography with no historical precedent. This paper establishes Embodied Intelligence Economics, the study of how physical AI capability thresholds reshape the spatial and structural logic of production. --- ### SENTINEL: Stagewise Integrity Verification for Pipeline Parallel Decentralized Training Authors: Hadi Mohaghegh Dolatabadi, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Chamin P Hewa Koneputugodage, Gil Avraham, Yan Zuo, Violetta Shevchenko, Alexander Long Published: 2026-03-03 Categories: cs.DC, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.03592v1 Decentralized training introduces critical security risks when executed across untrusted, geographically distributed nodes. While existing Byzantine-tolerant literature addresses data parallel (DP) training through robust aggregation methods, pipeline parallelism (PP) presents fundamentally distinct challenges. In PP, model layers are distributed across workers where the activations and their gradients flow between stages rather than being aggregated, making traditional DP approaches inapplicable. We propose SENTINEL, a verification mechanism for PP training without computation duplication. SENTINEL employs lightweight momentum-based monitoring using exponential moving averages (EMAs) to detect corrupted inter-stage communication. Unlike existing Byzantine-tolerant approaches for DP that aggregate parameter gradients across replicas, our approach verifies sequential activation/gradient transmission between layers. We provide theoretical convergence guarantees for this new setting that recovers classical convergence rates when relaxed to standard training. Experiments demonstrate successful training of up to 4B-parameter LLMs across untrusted distributed environments with up to 176 workers while maintaining model convergence and performance. --- ### Social Norm Reasoning in Multimodal Language Models: An Evaluation Authors: Oishik Chowdhury, Anushka Debnath, Bastin Tony Roy Savarimuthu Published: 2026-03-03 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2603.03590v1 In Multi-Agent Systems (MAS), agents are designed with social capabilities, allowing them to understand and reason about social concepts such as norms when interacting with others (e.g., inter-robot interactions). In Normative MAS (NorMAS), researchers study how norms develop, and how violations are detected and sanctioned. However, existing research in NorMAS use symbolic approaches (e.g., formal logic) for norm representation and reasoning whose application is limited to simplified environments. In contrast, Multimodal Large Language Models (MLLMs) present promising possibilities to develop software used by robots to identify and reason about norms in a wide variety of complex social situations embodied in text and images. However, prior work on norm reasoning have been limited to text-based scenarios. This paper investigates the norm reasoning competence of five MLLMs by evaluating their ability to answer norm-related questions based on thirty text-based and thirty image-based stories, and comparing their responses against humans. Our results show that MLLMs demonstrate superior performance in norm reasoning in text than in images. GPT-4o performs the best in both modalities offering the most promise for integration with MAS, followed by the free model Qwen-2.5VL. Additionally, all models find reasoning about complex norms challenging. --- ### stratum: A System Infrastructure for Massive Agent-Centric ML Workloads Authors: Arnab Phani, Elias Strauss, Sebastian Schelter Published: 2026-03-03 Categories: cs.DB, cs.LG arXiv: https://arxiv.org/abs/2603.03589v3 Recent advances in large language models (LLMs) transform how machine learning (ML) pipelines are developed and evaluated. LLMs enable a new type of workload, agentic pipeline search, in which autonomous or semi-autonomous agents generate, validate, and optimize complete ML pipelines. These agents predominantly operate over popular Python ML libraries and exhibit highly exploratory behavior. This results in thousands of executions for data profiling, pipeline generation, and iterative refinement of pipeline stages. However, the existing Python-based ML ecosystem is built around libraries such as Pandas and scikit-learn, which are designed for human-centric, interactive, sequential workflows and remain constrained by Python's interpretive execution model, library-level isolation, and limited runtime support for executing large numbers of pipelines. Meanwhile, many high-performance ML systems proposed by the systems community either target narrow workload classes or require specialized programming models, which limits their integration with the Python ML ecosystem and makes them largely ill-suited for LLM-based agents. This growing mismatch exposes a fundamental systems challenge in supporting agentic pipeline search at scale. We therefore propose stratum, a unified system infrastructure that decouples pipeline execution from planning and reasoning during agentic pipeline search. Stratum integrates seamlessly with existing Python libraries, compiles batches of pipelines into optimized execution graphs, and efficiently executes them across heterogeneous backends, including a novel Rust-based runtime. We present stratum's architectural vision along with an early prototype, discuss key design decisions, and outline open challenges and research directions. Finally, preliminary experiments show that stratum can significantly speed up large-scale agentic pipeline search up to 16.6x. --- ### Controllable Generative Sandbox for Causal Inference Authors: Qi Zhang, Harsh Parikh, Ashley Naimi, Razieh Nabi, Christopher Kim, Timothy Lash Published: 2026-03-03 Categories: stat.ME, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.03587v1 Method validation and study design in causal inference rely on synthetic data with known counterfactuals. Existing simulators trade off distributional realism, the ability to capture mixed-type and multimodal tabular data, against causal controllability, including explicit control over overlap, unmeasured confounding, and treatment effect heterogeneity. We introduce CausalMix, a variational generative framework that closes this gap by coupling a mixture of Gaussian latent priors with data-type-specific decoders for continuous, binary, and categorical variables. The model incorporates explicit causal controls: an overlap regularizer shaping propensity-score distributions, alongside direct parameterizations of confounding strength and effect heterogeneity. This unified objective preserves fidelity to the observed data while enabling factorial manipulation of causal mechanisms, allowing overlap, confounding strength, and treatment effect heterogeneity to be varied independently at design time. Across benchmarks, CausalMix achieves state-of-the-art distributional metrics on mixed-type tables while providing stable, fine-grained causal control. We demonstrate practical utility in a comparative safety study of metastatic castration-resistant prostate cancer treatments, using CausalMix to compare estimators under calibrated data-generating processes, tune hyperparameters, and conduct simulation-based power analyses under targeted treatment effect heterogeneity scenarios. --- ### Belief-Sim: Towards Belief-Driven Simulation of Demographic Misinformation Susceptibility Authors: Angana Borah, Zohaib Khan, Rada Mihalcea, Verónica Pérez-Rosas Published: 2026-03-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03585v2 Misinformation is a growing societal threat, and susceptibility to misinformative claims varies across demographic groups due to differences in underlying beliefs. As Large Language Models (LLMs) are increasingly used to simulate human behaviors, we investigate whether they can simulate demographic misinformation susceptibility, treating beliefs as a primary driving factor. We introduce BeliefSim, a simulation framework that constructs demographic belief profiles using psychology-informed misinformation taxonomies and survey priors. We study prompt-based conditioning and post-training adaptation, and conduct a multi-fold evaluation using: (i) susceptibility alignment and (ii) counterfactual demographic sensitivity. Across both datasets and modeling strategies, we show that beliefs provide a strong prior for simulating misinformation susceptibility, with alignment up to 92%. --- ### Hazard-Aware Traffic Scene Graph Generation Authors: Yaoqi Huang, Julie Stephany Berrio, Mao Shan, Stewart Worrall Published: 2026-03-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03584v2 Maintaining situational awareness in complex driving scenarios is challenging. It requires continuously prioritizing attention among extensive scene entities and understanding how prominent hazards might affect the ego vehicle. While existing studies excel at detecting specific semantic categories and visually salient regions, they lack the ability to assess safety-relevance. Meanwhile, the generic spatial predicates either for foreground objects only or for all scene entities modeled by existing scene graphs are inadequate for driving scenarios. To bridge this gap, we introduce a novel task, Traffic Scene Graph Generation, which captures traffic-specific relations between prominent hazards and the ego vehicle. We propose a novel framework that explicitly uses traffic accident data and depth cues to supplement visual features and semantic information for reasoning. The output traffic scene graphs provide intuitive guidelines that stress prominent hazards by color-coding their severity and notating their effect mechanism and relative location to the ego vehicle. We create relational annotations on Cityscapes dataset and evaluate our model on 10 tasks from 5 perspectives. The results in comparative experiments and ablation studies demonstrate our capacity in ego-centric reasoning for hazard-aware traffic scene understanding. --- ### ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer Authors: Chunyuan Deng, Sanket Lokegaonkar, Colin Lockard, Besnik Fetahu, Nasser Zalmout, Xian Li Published: 2026-03-03 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.03583v1 Modern language models still rely on fixed, pre-defined subword tokenizations. Once a tokenizer is trained, the LM can only operate at this fixed level of granularity, which often leads to brittle and counterintuitive behaviors even in otherwise strong reasoning models. We introduce \textbf{ByteFlow Net}, a new hierarchical architecture that removes tokenizers entirely and instead enables models to learn their own segmentation of raw byte streams into semantically meaningful units. ByteFlow Net performs compression-driven segmentation based on the coding rate of latent representations, yielding adaptive boundaries \emph{while preserving a static computation graph via Top-$K$ selection}. Unlike prior self-tokenizing methods that depend on brittle heuristics with human-designed inductive biases, ByteFlow Net adapts its internal representation granularity to the input itself. Experiments demonstrate that this compression-based chunking strategy yields substantial performance gains, with ByteFlow Net outperforming both BPE-based Transformers and previous byte-level architectures. These results suggest that end-to-end, tokenizer-free modeling is not only feasible but also more effective, opening a path toward more adaptive and information-grounded language models. --- ### An Effective Data Augmentation Method by Asking Questions about Scene Text Images Authors: Xu Yao, Lei Kang Published: 2026-03-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03580v1 Scene text recognition (STR) and handwritten text recognition (HTR) face significant challenges in accurately transcribing textual content from images into machine-readable formats. Conventional OCR models often predict transcriptions directly, which limits detailed reasoning about text structure. We propose a VQA-inspired data augmentation framework that strengthens OCR training through structured question-answering tasks. For each image-text pair, we generate natural-language questions probing character-level attributes such as presence, position, and frequency, with answers derived from ground-truth text. These auxiliary tasks encourage finer-grained reasoning, and the OCR model aligns visual features with textual queries to jointly reason over images and questions. Experiments on WordArt and Esposalles datasets show consistent improvements over baseline models, with significant reductions in both CER and WER. Our code is publicly available at https://github.com/xuyaooo/DataAugOCR. --- ### Spectrum Shortage for Radio Sensing? Leveraging Ambient 5G Signals for Human Activity Detection Authors: Kunzhe Song, Maxime Zingraff, Huacheng Zeng Published: 2026-03-03 Categories: cs.NI, cs.CV arXiv: https://arxiv.org/abs/2603.03579v1 Radio sensing in the sub-10 GHz spectrum offers unique advantages over traditional vision-based systems, including the ability to see through occlusions and preserve user privacy. However, the limited availability of spectrum in this range presents significant challenges for deploying largescale radio sensing applications. In this paper, we introduce Ambient Radio Sensing (ARS), a novel Integrated Sensing and Communications (ISAC) approach that addresses spectrum scarcity by repurposing over-the-air radio signals from existing wireless systems (e.g., 5G and Wi-Fi) for sensing applications, without interfering with their primary communication functions. ARS operates as a standalone device that passively receives communication signals, amplifies them to illuminate surrounding objects, and captures the reflected signals using a self-mixing RF architecture to extract baseband features. This hardware innovation enables robust Doppler and angular feature extraction from ambient OFDM signals. To support downstream applications, we propose a cross-modal learning framework focusing on human activity recognition, featuring a streamlined training process that leverages an off-the-shelf vision model to supervise radio model training. We have developed a prototype of ARS and validated its effectiveness through extensive experiments using ambient 5G signals, demonstrating accurate human skeleton estimation and body mask segmentation applications. --- ### Transport Clustering: Solving Low-Rank Optimal Transport via Clustering Authors: Henri Schmidt, Peter Halmos, Ben Raphael Published: 2026-03-03 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03578v1 Optimal transport (OT) finds a least cost transport plan between two probability distributions using a cost matrix defined on pairs of points. Unlike standard OT, which infers unstructured pointwise mappings, low-rank optimal transport explicitly constrains the rank of the transport plan to infer latent structure. This improves statistical stability and robustness, yields sharper parametric rates for estimating Wasserstein distances adaptive to the intrinsic rank, and generalizes $K$-means to co-clustering. These advantages, however, come at the cost of a non-convex and NP-hard optimization problem. We introduce transport clustering, an algorithm to compute a low-rank OT plan that reduces low-rank OT to a clustering problem on correspondences obtained from a full-rank $\textit{transport registration}$ step. We prove that this reduction yields polynomial-time, constant-factor approximation algorithms for low-rank OT: specifically, a $(1+γ)$ approximation for negative-type metrics and a $(1+γ+\sqrt{2γ}\,)$ approximation for kernel costs, where $γ\in (0,1)$ denotes the approximation ratio of the optimal full-rank solution relative to the low-rank optimal. Empirically, transport clustering outperforms existing low-rank OT solvers on synthetic benchmarks and large-scale, high-dimensional datasets. --- ### From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes Authors: Qifan Zhang, Sai Haneesh Allu, Jikai Wang, Yangxiao Lu, Yu Xiang Published: 2026-03-03 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.03577v2 Detecting and segmenting novel object instances in open-world environments is a fundamental problem in robotic perception. Given only a small set of template images, a robot must locate and segment a specific object instance in a cluttered, previously unseen scene. Existing proposal-based approaches are highly sensitive to proposal quality and often fail under occlusion and background clutter. We propose L2G-Det, a local-to-global instance detection framework that bypasses explicit object proposals by leveraging dense patch-level matching between templates and the query image. Locally matched patches generate candidate points, which are refined through a candidate selection module to suppress false positives. The filtered points are then used to prompt an augmented Segment Anything Model (SAM) with instance-specific object tokens, enabling reliable reconstruction of complete instance masks. Experiments demonstrate improved performance over proposal-based methods in challenging open-world settings. --- ### Confidence-aware Monocular Depth Estimation for Minimally Invasive Surgery Authors: Muhammad Asad, Emanuele Colleoni, Pritesh Mehta, Nicolas Toussaint, Ricardo Sanchez-Matilla, Maria Robu, Faisal Bashir, Rahim Mohammadi, Imanol Luengo, Danail Stoyanov Published: 2026-03-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03571v1 Purpose: Monocular depth estimation (MDE) is vital for scene understanding in minimally invasive surgery (MIS). However, endoscopic video sequences are often contaminated by smoke, specular reflections, blur, and occlusions, limiting the accuracy of MDE models. In addition, current MDE models do not output depth confidence, which could be a valuable tool for improving their clinical reliability. Methods: We propose a novel confidence-aware MDE framework featuring three significant contributions: (i) Calibrated confidence targets: an ensemble of fine-tuned stereo matching models is used to capture disparity variance into pixel-wise confidence probabilities; (ii) Confidence-aware loss: Baseline MDE models are optimized with confidence-aware loss functions, utilizing pixel-wise confidence probabilities such that reliable pixels dominate training; and (iii) Inference-time confidence: a confidence estimation head is proposed with two convolution layers to predict per-pixel confidence at inference, enabling assessment of depth reliability. Results: Comprehensive experimental validation across internal and public datasets demonstrates that our framework improves depth estimation accuracy and can robustly quantify the prediction's confidence. On the internal clinical endoscopic dataset (StereoKP), we improve dense depth estimation accuracy by ~8% as compared to the baseline model. Conclusion: Our confidence-aware framework enables improved accuracy of MDE models in MIS, addressing challenges posed by noise and artifacts in pre-clinical and clinical data, and allows MDE models to provide confidence maps that may be used to improve their reliability for clinical applications. --- ### Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants Authors: Alejandro Breen Herrera, Aayush Sheth, Steven G. Xu, Zhucheng Zhan, Charles Wright, Marcus Yearwood, Hongtai Wei, Sudeep Das, Danny Nightingale, Meg Watson, Charles Pollnow Published: 2026-03-03 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2603.03565v2 Conversational shopping assistants (CSAs) represent a compelling application of agentic AI, but moving from prototype to production reveals two underexplored challenges: how to evaluate multi-turn interactions and how to optimize tightly coupled multi-agent systems. Grocery shopping further amplifies these difficulties, as user requests are often underspecified, highly preference-sensitive, and constrained by factors such as budget and inventory. In this paper, we present a practical blueprint for evaluating and optimizing conversational shopping assistants, illustrated through a production-scale AI grocery assistant. We introduce a multi-faceted evaluation rubric that decomposes end-to-end shopping quality into structured dimensions and develop a calibrated LLM-as-judge pipeline aligned with human annotations. Building on this evaluation foundation, we investigate two complementary prompt-optimization strategies based on a SOTA prompt-optimizer called GEPA (Shao et al., 2025): (1) Sub-agent GEPA, which optimizes individual agent nodes against localized rubrics, and (2) MAMuT (Multi-Agent Multi-Turn) GEPA (Herrera et al., 2026), a novel system-level approach that jointly optimizes prompts across agents using multi-turn simulation and trajectory-level scoring. We release rubric templates and evaluation design guidance to support practitioners building production CSAs. --- ### Modeling Cross-vision Synergy for Unified Large Vision Model Authors: Shengqiong Wu, Lanhu Wu, Mingyang Bao, Wenhao Xu, Hanwang Zhang, Shuicheng Yan, Hao Fei, Tat-Seng Chua Published: 2026-03-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03564v1 Recent advances in large vision models (LVMs) have shifted from modality-specific designs toward unified architectures that jointly process images, videos, and 3D data. However, existing unified LVMs primarily pursue functional integration, while overlooking the deeper goal of cross-vision synergy: the ability to reason over complementary priors across visual modalities. To address this, we present PolyV, a unified LVM that achieves cross-vision synergy at both the architectural and training levels. Architecturally, PolyV adopts a sparse Mixture-of-Experts LVM coordinated by a dynamic modality router, allowing each expert to specialize in modality-specific priors while enabling bidirectional interaction and mutual refinement across modalities. Training-wise, a synergy-aware paradigm combines modality-specific pretraining with coarse-to-fine synergy tuning via knowledge distillation and object-/relation-level alignment. Extensive experiments on 10 benchmarks spanning image, video, and 3D understanding, including synergy-focused datasets requiring spatial or temporal priors, demonstrate that PolyV consistently outperforms existing models, achieving over 10% average improvement over its backbone. Overall, PolyV establishes a unified framework for synesthetic visual reasoning, advancing toward truly synergistic LVMs. Project page: https://sqwu.top/PolyV. --- ### Real-time tightly coupled GNSS and IMU integration via Factor Graph Optimization Authors: Radu-Andrei Cioaca, Paul Irofti, Cristian Rusu, Gianluca Caparra, Andrei-Alexandru Marinache, Florin Stoican Published: 2026-03-03 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.03556v1 Reliable positioning in dense urban environments remains challenging due to frequent GNSS signal blockage, multipath, and rapidly varying satellite geometry. While factor graph optimization (FGO)-based GNSS-IMU fusion has demonstrated strong robustness and accuracy, most formulations remain offline. In this work, we present a real-time tightly coupled GNSS-IMU FGO method that enables causal state estimation via incremental optimization with fixed-lag marginalization, and we evaluate its performance in a highly urbanized GNSS-degraded environment using the UrbanNav dataset. --- ### Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framework on the MoltBook Archive Authors: Brandon Yee, Pairie Koh Published: 2026-03-03 Categories: cs.MA, cs.AI, cs.SI arXiv: https://arxiv.org/abs/2603.03555v3 As multi-agent Large Language Model (LLM) systems scale, evaluating their emergent coordination dynamics becomes increasingly critical. However, current evaluation paradigms-focused on single agents or small, explicitly structured groups-fail to capture the self-organization and viral information dynamics that arise in large, decentralized populations. We introduce a systematic evaluation framework to benchmark role specialization, information diffusion, and cooperative task resolution in open agent environments. We demonstrate this framework on the MoltBook Observatory Archive, a dataset of 2.73M interactions among 90,704 autonomous agents, establishing quantitative baselines for emergent coordination. Our evaluation reveals a pronounced core-periphery structure (silhouette 0.91), heavy-tailed cascade distributions ($α= 2.57$), and severe coordination overhead in decentralized task resolution (Cohen's $d = -0.88$ against a single-agent baseline). By providing standardized evaluation tasks and empirical baselines, our framework enables the rigorous comparison of future multi-agent protocols and establishes evaluation itself as an object of scientific study. --- ### Real-time loosely coupled GNSS and IMU integration via Factor Graph Optimization Authors: Radu-Andrei Cioaca, Cristian Rusu, Paul Irofti, Gianluca Caparra, Andrei-Alexandru Marinache, Florin Stoican Published: 2026-03-03 Categories: cs.RO, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2603.03546v1 Accurate positioning, navigation, and timing (PNT) is fundamental to the operation of modern technologies and a key enabler of autonomous systems. A very important component of PNT is the Global Navigation Satellite System (GNSS) which ensures outdoor positioning. Modern research directions have pushed the performance of GNSS localization to new heights by fusing GNSS measurements with other sensory information, mainly measurements from Inertial Measurement Units (IMU). In this paper, we propose a loosely coupled architecture to integrate GNSS and IMU measurements using a Factor Graph Optimization (FGO) framework. Because the FGO method can be computationally challenging and often used as a post-processing method, our focus is on assessing its localization accuracy and service availability while operating in real-time in challenging environments (urban canyons). Experimental results on the UrbanNav-HK-MediumUrban-1 dataset show that the proposed approach achieves real-time operation and increased service availability compared to batch FGO methods. While this improvement comes at the cost of reduced positioning accuracy, the paper provides a detailed analysis of the trade-offs between accuracy, availability, and computational efficiency that characterize real-time FGO-based GNSS/IMU fusion. --- ### PinCLIP: Large-scale Foundational Multimodal Representation at Pinterest Authors: Josh Beal, Eric Kim, Jinfeng Rao, Rex Wu, Dmitry Kislyuk, Charles Rosenberg Published: 2026-03-03 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03544v1 While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, due to issues like training objective discrepancies and serving efficiency bottlenecks. This paper introduces PinCLIP, a large-scale visual representation learning approach developed to enhance retrieval and ranking models at Pinterest by leveraging VLMs to learn image-text alignment. We propose a novel hybrid Vision Transformer architecture that utilizes a VLM backbone and a hybrid fusion mechanism to capture multi-modality content representation at varying granularities. Beyond standard image-to-text alignment objectives, we introduce a neighbor alignment objective to model the cross-fusion of multi-modal representations within the Pinterest Pin-Board graph. Offline evaluations show that PinCLIP outperforms state-of-the-art baselines, such as Qwen, by 20% in multi-modal retrieval tasks. Online A/B testing demonstrates significant business impact, including substantial engagement gains across all major surfaces in Pinterest. Notably, PinCLIP significantly addresses the "cold-start" problem, enhancing fresh content distribution with a 15% Repin increase in organic content and 8.7% higher click for new Ads. --- ### Tucano 2 Cool: Better Open Source LLMs for Portuguese Authors: Nicholas Kluge Corrêa, Aniket Sen, Shiza Fatimah, Sophia Falk, Lennard Landgraf, Julia Kastner, Lucie Flek Published: 2026-03-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03543v1 We present Tucano 2, a fully open suite of large language models (LLMs) with 0.5-3.7 billion parameters, designed to address certain gaps in open-source development for Portuguese LLMs. Following our previous works, we now extend our dataset, GigaVerbo-v2, to a new degree of quality and scale, while also introducing a new synthetic dataset, GigaVerbo-v2 Synth, aimed at filling missing gaps in GigaVerbo-v2, and two post-training datasets, GigaVerbo-v2 SFT and GigaVerbo-v2 Preferences, that allow Portuguese LLMs to be trained in domains like retrieval augmented generation, coding, tool use, chain-of-thought reasoning, and many other domains of interest. Through extensive ablation studies, we design both pretraining and continual pretraining recipes for the Tucano 2 suite (Base, Instruct, and Think), which achieve state-of-the-art performance on several Portuguese-language modeling benchmarks. We also extend and refine the evaluation harness introduced in our earlier work, yielding a comprehensive evaluation suite that provides strong signals across different pretraining, continual pretraining, and post-training regimes. All artifacts associated with Tucano 2 are openly released, including training recipes, logs, and source code, ensuring that our work is reproducible, accessible, and extendable by the broader Portuguese NLP community. --- ### RAG-X: Systematic Diagnosis of Retrieval-Augmented Generation for Medical Question Answering Authors: Aswini Sivakumar, Vijayan Sugumaran, Yao Qiang Published: 2026-03-03 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03541v1 Automated question-answering (QA) systems increasingly rely on retrieval-augmented generation (RAG) to ground large language models (LLMs) in authoritative medical knowledge, ensuring clinical accuracy and patient safety in Artificial Intelligence (AI) applications for healthcare. Despite progress in RAG evaluation, current benchmarks focus only on simple multiple-choice QA tasks and employ metrics that poorly capture the semantic precision required for complex QA tasks. These approaches fail to diagnose whether an error stems from faulty retrieval or flawed generation, limiting developers from performing targeted improvement. To address this gap, we propose RAG-X, a diagnostic framework that evaluates the retriever and generator independently across a triad of QA tasks: information extraction, short-answer generation, and multiple-choice question (MCQ) answering. RAG-X introduces Context Utilization Efficiency (CUE) metrics to disaggregate system success into interpretable quadrants, isolating verified grounding from deceptive accuracy. Our experiments reveal an ``Accuracy Fallacy", where a 14\% gap separates perceived system success from evidence-based grounding. By surfacing hidden failure modes, RAG-X offers the diagnostic transparency needed for safe and verifiable clinical RAG systems. ---