# Research Papers — 2026-03 · bundle page 44 of 243 > Full-text markdown of papers #2151–2200 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/44 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/43.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/45.md) ### LiFT: How to Enable In-Context Learning for Longitudinal Modelling Authors: Iqra Ali, Talia Tseriotou, Mahmud Elahi Akhter, Yuxiang Zhou, Maria Liakata Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16382v2 Longitudinal NLP tasks such as mental health monitoring and stance evolution require modeling temporally ordered text to track persistence and detect change. Such tasks also suffer from data scarcity, often involving rare events and sparsely annotated data. Large Language Models (LLMs) can learn from small amounts of data through in-context learning (ICL), which is particularly important in low-data resource scenarios. However, when it comes to tracking evolving interactions or identifying rare events or changes, LLMs fall short in both zero- and few-shot ICL. To address this limitation, we introduce LiFT, a model-agnostic longitudinal Instruction Fine-Tuning framework that is able to induce ICL behaviour in LLMs for longitudinal tasks. LiFT unifies diverse tasks through a shared instruction schema that leverages sequential dependencies, curriculum learning, and temporal conditioning. We evaluate LiFT on five longitudinal datasets under zero-, one-, and three-shot settings, demonstrating that LiFT delivers superior performance to IFT models under identical ICL conditions. Furthermore, we demonstrate that LiFT yields larger gains for minority classes, meaningfully attends to recent demonstration history, and develops transferable longitudinal modeling capabilities beyond its training tasks --- ### LiFT: Does Instruction Fine-Tuning Improve In-Context Learning for Longitudinal Modelling by Large Language Models? Authors: Iqra Ali, Talia Tseriotou, Mahmud Elahi Akhter, Yuxiang Zhou, Maria Liakata Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.16382v1 Longitudinal NLP tasks require reasoning over temporally ordered text to detect persistence and change in human behavior and opinions. However, in-context learning with large language models struggles on tasks where models must integrate historical context, track evolving interactions, and handle rare change events. We introduce LiFT, a longitudinal instruction fine-tuning framework that unifies diverse longitudinal modeling tasks under a shared instruction schema. LiFT uses a curriculum that progressively increases temporal difficulty while incorporating few-shot structure and temporal conditioning to encourage effective use of past context. We evaluate LiFT across five datasets. Models trained on longitudinal tasks with different levels of temporal granularity are tested for generalisability on two separate datasets. Across models with different parameter sizes (OLMo (1B/7B), LLaMA-8B, and Qwen-14B), LiFT consistently outperforms base-model ICL, with strong gains on out-of-distribution data and minority change events. --- ### Data Mixing for Large Language Models Pretraining: A Survey and Outlook Authors: Zhuo Chen, Yuxuan Miao, Supryadi, Deyi Xiong Published: 2026-03-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.16380v1 Large language models (LLMs) rely on pretraining on massive and heterogeneous corpora, where training data composition has a decisive impact on training efficiency and downstream generalization under realistic compute and data budget constraints. Unlike sample-level data selection, data mixing optimizes domain-level sampling weights to allocate limited budgets more effectively. In recent years, a growing body of work has proposed principled data mixing methods for LLM pretraining; however, the literature remains fragmented and lacks a dedicated, systematic survey. This paper provides a comprehensive review of data mixing for LLM pretraining. We first formalize data mixture optimization as a bilevel problem on the probability simplex and clarify the role of data mixing in the pretraining pipeline, and briefly explain how existing methods make this formulation tractable in practice. We then introduce a fine-grained taxonomy that organizes existing methods along two dimensions: static versus dynamic mixing. Static mixing is further categorized into rule-based and learning-based methods, while dynamic mixing is grouped into adaptive and externally guided families. For each class, we summarize representative approaches and analyze their strengths and limitations from a performance-cost trade-off perspective. Building on this analysis, we highlight challenges that cut across methods, including limited transferability across data domains, optimization objectives, models, and validation sets, as well as unstandardized evaluation protocols and benchmarks, and the inherent tension between performance gains and cost control in learning-based methods. Finally, we outline several exploratory directions, including finer-grained domain partitioning and inverse data mixing, as well as pipeline-aware designs, aiming to provide conceptual and methodological insights for future research. --- ### LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains Authors: Ryogo Hishikawa, Ichiro Kataoka, Shinya Yuda Published: 2026-03-25 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2604.16379v3 Industrial B2B applications (e.g., construction site risk prediction, material procurement) face extreme data sparsity yet feature rich textual interactions. In such environments, traditional ID-based collaborative filtering fails lacking co-occurrence signals, while fine-tuning standard Large Language Models (LLMs) incurs high operational costs and struggles with frequent data drift. We propose LLMAR (LLM-Annotated Recommendation), a tuning-free framework. Moving beyond simple embeddings, LLMAR systematically integrates LLM reasoning to capture user "latent motives" without any training process. We introduce three core contributions: (1) Inference-Driven Annotation: uses LLMs to transform behavioral history into structured semantic motives, enabling reasoning-based matching unattainable by ID-based methods; (2) Reflection Loop: a self-correction mechanism that refines generated queries to mitigate hallucinations and resolve "context competition" between past history and current instructions; and (3) Cost-Effective Architecture: relies on tuning-free components and asynchronous batch processing to minimize maintenance costs. Evaluations on public benchmarks (MovieLens-1M, Amazon Prime Pantry) and a sparse industrial dataset (construction risk prediction) demonstrate that LLMAR outperforms state-of-the-art learning-based models (SASRecF), achieving up to a 54.6% nDCG@10 improvement on the industrial dataset. Inference costs remain highly practical (~$1 per 1,000 users). For B2B domains where strict real-time latency is not critical, combining LLM reasoning with self-verification offers a superior alternative to training-based approaches across accuracy, explainability, and operational cost. --- ### LLMAR: A Tuning-Free Recommendation Framework for Sparse and Text-Rich Industrial Domains Authors: Ryogo Hishikawa, Ichiro Kataoka, Shinya Yuda Published: 2026-03-25 Categories: cs.IR, cs.CL arXiv: https://arxiv.org/abs/2604.16379v2 Industrial B2B applications (e.g., construction site risk prediction, material procurement) face extreme data sparsity yet feature rich textual interactions. In such environments, traditional ID-based collaborative filtering fails lacking co-occurrence signals, while fine-tuning standard Large Language Models (LLMs) incurs high operational costs and struggles with frequent data drift. We propose LLMAR (LLM-Annotated Recommendation), a tuning-free framework. Moving beyond simple embeddings, LLMAR systematically integrates LLM reasoning to capture user "latent motives" without any training process. We introduce three core contributions: (1) Inference-Driven Annotation: uses LLMs to transform behavioral history into structured semantic motives, enabling reasoning-based matching unattainable by ID-based methods; (2) Reflection Loop: a self-correction mechanism that refines generated queries to mitigate hallucinations and resolve "context competition" between past history and current instructions; and (3) Cost-Effective Architecture: relies on tuning-free components and asynchronous batch processing to minimize maintenance costs. Evaluations on public benchmarks (MovieLens-1M, Amazon Prime Pantry) and a sparse industrial dataset (construction risk prediction) demonstrate that LLMAR outperforms state-of-the-art learning-based models (SASRecF), achieving up to a 54.6% nDCG@10 improvement on the industrial dataset. Inference costs remain highly practical (~$1 per 1,000 users). For B2B domains where strict real-time latency is not critical, combining LLM reasoning with self-verification offers a superior alternative to training-based approaches across accuracy, explainability, and operational cost. --- ### The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discovery Authors: Haiyang Zheng, Nan Pu, Yaqi Cai, Teng Long, Wenjing Li, Nicu Sebe, Zhun Zhong Published: 2026-03-25 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2604.14176v1 Generalized Category Discovery (GCD) leverages labeled data to categorize unlabeled samples from known or unknown classes. Most previous methods jointly optimize supervised and unsupervised objectives and achieve promising results. However, inherent optimization interference still limits their ability to improve further. Through quantitative analysis, we identify a key issue, i.e., gradient entanglement, which 1) distorts supervised gradients and weakens discrimination among known classes, and 2) induces representation-subspace overlap between known and novel classes, reducing the separability of novel categories. To address this issue, we propose the Energy-Aware Gradient Coordinator (EAGC), a plug-and-play gradient-level module that explicitly regulates the optimization process. EAGC comprises two components: Anchor-based Gradient Alignment (AGA) and Energy-aware Elastic Projection (EEP). AGA introduces a reference model to anchor the gradient directions of labeled samples, preserving the discriminative structure of known classes against the interference of unlabeled gradients. EEP softly projects unlabeled gradients onto the complement of the known-class subspace and derives an energy-based coefficient to adaptively scale the projection for each unlabeled sample according to its degree of alignment with the known subspace, thereby reducing subspace overlap without suppressing unlabeled samples that likely belong to known classes. Experiments show that EAGC consistently boosts existing methods and establishes new state-of-the-art results. Code is available at https://haiyangzheng.github.io/EAGC. --- ### Correcting Suppressed Log-Probabilities in Language Models with Post-Transformer Adapters Authors: Bryan Sanchez Published: 2026-03-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2604.14174v2 Alignment-tuned language models frequently suppress factual log-probabilities on politically sensitive topics despite retaining the knowledge in their hidden representations. We show that a 786K-parameter (approximately 0.02% of the base model) post-transformer adapter, trained on frozen hidden states, corrects this suppression on 31 ideology-discriminating facts across Qwen3-4B, 8B, and 14B. The adapter memorizes all 15 training facts and generalizes to 11--39% of 16 held-out facts across 5 random splits per scale, with zero knowledge regressions via anchored training. Both gated (SwiGLU) and ungated (linear bottleneck) adapters achieve comparable results; neither consistently outperforms the other (Fisher exact p > 0.09 at all scales). On instruct models, the adapter corrects log-probability rankings. When applied at all token positions during generation, the adapter produces incoherent output; however, when applied only at the current prediction position (last-position-only), the adapter produces coherent, less censored text. A logit-space adapter operating after token projection fails to produce coherent generation at any application mode, suggesting hidden-state intervention is the correct level for generation correction. A previously undocumented silent gradient bug in Apple MLX explains all null results in earlier iterations of this work: the standard pattern nn.value_and_grad(model, fn)(model.parameters()) returns zero gradients without error; the correct pattern nn.value_and_grad(model, fn)(model, data) resolves this. We provide a minimal reproduction and discuss implications for other adapter research using MLX. --- ### Tug-of-War within A Decade: Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generations Authors: Ziyin Zhou, Jianyi Zhang, Xu ji, Yilong Li, Jiameng Han, Zhangchi Zhao Published: 2026-03-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.14172v1 Large Language Models (LLMs) are essential for analyzing and addressing vulnerabilities in cybersecurity. However, among over 200,000 vulnerabilities were discovered in the past decade, more than 30,000 have been changed or updated. This necessitates frequent updates to the training datasets and internal knowledge bases of LLMs to maintain knowledge consistency. In this paper, we focus on the problem of knowledge discrepancy and conflict within CVE (Common Vulnerabilities and Exposures) detection and analysis. This problem hinders LLMs' ability to retrieve the latest knowledge from original training datasets, leading to knowledge conflicts, fabrications of factually incorrect results, and generation hallucinations. To address this problem, we propose an innovative two-stage framework called CRVA-TGRAG (Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generation). First, to improve document retrieval accuracy during the retrieval stage, we utilize Parent Document Segmentation and an ensemble retrieval scheme based on semantic similarity and inverted indexing. Second, to enhance LLMs' capabilities based on the retrieval of CVE dataset in generation stage, we employ a teacher-guided preference optimization technique to fine-tune LLMs. Our framework not only enhances the quality of content retrieval through RAG but also leverages the advantages of preference fine-tuning in LLMs to answer questions more effectively and precisely. Experiments demonstrate our method achieves higher accuracy in retrieving the latest CVEs compared to external knowledge bases. In conclusion, our framework significantly mitigates potential knowledge conflicts and inconsistencies that may arise from relying solely on LLMs for knowledge retrieval. --- ### Benchmarking Linguistic Adaptation in Comparable-Sized LLMs: A Study of Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B on Romanized Nepali Authors: Ananda Rimal, Adarsha Rimal Published: 2026-03-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.14171v1 Romanized Nepali, the Nepali language written in the Latin alphabet, is the dominant medium for informal digital communication in Nepal, yet it remains critically underresourced in the landscape of Large Language Models (LLMs). This study presents a systematic benchmarking of linguistic adaptation across three comparable-sized open-weight models: Llama-3.1-8B, Mistral-7B-v0.1, and Qwen3-8B. We evaluate these architectures under zero-shot and fine-tuned settings using a curated bilingual dataset of 10,000 transliterated instruction-following samples. Performance is quantified across five metrics spanning seven measurement dimensions: Perplexity (PPL), BERTScore, chrF++, ROUGE-1, ROUGE-2, ROUGE-L, and BLEU, capturing fluency, phonetic consistency, and semantic integrity. Models were fine-tuned using Quantized Low-Rank Adaptation (QLoRA) with Rank-Stabilized LoRA (rsLoRA) at rank r=32 on dual NVIDIA Tesla T4 GPUs, training only approximately 1% of each model's parameters in under 27 total GPU-hours. At zero-shot, all three models fail to generate Romanized Nepali, each exhibiting a distinct architecture-specific failure mode. Following fine-tuning, all three resolve these failures and converge to BERTScore approximately 0.75 and chrF++ greater than 23. Overall dimension-wise assessment across ten criteria identifies Qwen3-8B as the overall recommended architecture, being the only model to produce semantically relevant zero-shot output and leading all structural alignment metrics post-SFT. The adaptation headroom hypothesis is confirmed: Llama-3.1-8B, despite its weakest zero-shot baseline, achieves the largest absolute fine-tuning gains in PPL (Delta = -49.77) and BERTScore (Delta = +0.3287), making it the preferred choice for iterative low-resource development pipelines. This work establishes the first rigorous baseline for Romanized Nepali adaptation in comparable-sized open-weight LLMs. --- ### Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning Authors: Qi Dong, Ziheng Lin, Ning Ding Published: 2026-03-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.14170v1 Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful Evidence-Driven RAG with Iterative Reasoning, a framework that models question answering as a progressive evidence accumulation process. Retrieved documents are converted into structured reasoning units with explicit relevance and confidence signals and maintained in a persistent evidence pool capturing both supportive and non-supportive information. The framework performs evidence-driven deficiency analysis to identify gaps and conflicts and iteratively refines queries to guide subsequent retrieval. This iterative reasoning process enables stable evidence aggregation and improves robustness to noisy retrieval. Experiments on multiple question answering benchmarks demonstrate consistent improvements over standard RAG and multi-step baselines, while effectively accumulating high-quality evidence and maintaining stable performance under substantial retrieval noise. --- ### Chronological Knowledge Retrieval: A Retrieval-Augmented Generation Approach to Construction Project Documentation Authors: Ioannis-Aris Kostis, Natalia Sanchiz, Steeve De Schryver, François Denis, Pierre Schaus Published: 2026-03-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.14169v1 In large-scale construction projects, the continuous evolution of decisions generates extensive records, most often captured in meeting minutes. Since decisions may override previous ones, professionals often need to reconstruct the history of specific choices. Retrieving such information manually from raw archives is both labor-intensive and error-prone. From a user perspective, we address this challenge by enabling conversational access to the whole set of project meeting minutes. Professionals can pose natural-language questions and receive answers that are both semantically relevant and explicitly time-annotated, allowing them to follow the chronology of decisions. From a technical perspective, our solution employs a Retrieval-Augmented Generation (RAG) framework that integrates semantic search with large language models to ensure accurate and context-aware responses. We demonstrate the approach using an anonymized, industry-sourced dataset of meeting minutes from a completed construction project by a large company in Belgium. The dataset is annotated and enriched with expert-defined queries to support systematic evaluation. Both the dataset and the open-source implementation are made available to the community to foster further research on conversational access to time-annotated project documentation. --- ### Generating High Quality Synthetic Data for Dutch Medical Conversations Authors: Cecilia Kuan, Aditya Kamlesh Parikh, Henk van den Heuvel Published: 2026-03-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.09645v1 Medical conversations offer insights into clinical communication often absent from Electronic Health Records. However, developing reliable clinical Natural Language Processing (NLP) models is hampered by the scarcity of domain-specific datasets, as clinical data are typically inaccessible due to privacy and ethical constraints. To address these challenges, we present a pipeline for generating synthetic Dutch medical dialogues using a Dutch fine-tuned Large Language Model, with real medical conversations serving as linguistic and structural reference. The generated dialogues were evaluated through quantitative metrics and qualitative review by native speakers and medical practitioners. Quantitative analysis revealed strong lexical variety and overly regular turn-taking, suggesting scripted rather than natural conversation flow. Qualitative review produced slightly below-average scores, with raters noting issues in domain specificity and natural expression. The limited correlation between quantitative and qualitative results highlights that numerical metrics alone cannot fully capture linguistic quality. Our findings demonstrate that generating synthetic Dutch medical dialogues is feasible but requires domain knowledge and carefully structured prompting to balance naturalness and structure in conversation. This work provides a foundation for expanding Dutch clinical NLP resources through ethically generated synthetic data. --- ### QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation Authors: Ali Slim, Haydar Hamieh, Jawad Kotaich, Yehya Ghosn, Mahdi Chehimi, Ammar Mohanna, Hasan Abed Al Kader Hammoud, Bernard Ghanem Published: 2026-03-25 Categories: cs.LG, cs.AI, cs.PL, cs.SE, quant-ph arXiv: https://arxiv.org/abs/2604.08570v2 Large Language Models (LLMs) are increasingly used for code generation, yet quantum code generation is still evaluated mostly within single frameworks, making it difficult to separate quantum reasoning from framework familiarity. We introduce QuanBench+, a unified benchmark spanning Qiskit, PennyLane, and Cirq, with 42 aligned tasks covering quantum algorithms, gate decomposition, and state preparation. We evaluate models with executable functional tests, report Pass@1 and Pass@5, and use KL-divergence-based acceptance for probabilistic outputs. We additionally study Pass@1 after feedback-based repair, where a model may revise code after a runtime error or wrong answer. Across frameworks, the strongest one-shot scores reach 59.5% in Qiskit, 54.8% in Cirq, and 42.9% in PennyLane; with feedback-based repair, the best scores rise to 83.3%, 76.2%, and 66.7%, respectively. These results show clear progress, but also that reliable multi-framework quantum code generation remains unsolved and still depends strongly on framework-specific knowledge. --- ### Memory-Guided Trust-Region Bayesian Optimization (MG-TuRBO) for High Dimensions Authors: Abhilasha Saroj, Shaked Regev, Guanhao Xu, Jinghui Yuan, Roy Luo, Ross Wang Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.08569v1 Traffic simulation and digital-twin calibration is a challenging optimization problem with a limited simulation budget. Each trial requires an expensive simulation run, and the relationship between calibration inputs and model error is often nonconvex, and noisy. The problem becomes more difficult as the number of calibration parameters increases. We compare a commonly used automatic calibration method, a genetic algorithm (GA), with Bayesian optimization methods (BOMs): classical Bayesian optimization (BO), Trust-Region BO (TuRBO), Multi-TuRBO, and a proposed Memory-Guided TuRBO (MG-TuRBO) method. We compare performance on 2 real-world traffic simulation calibration problems with 14 and 84 decision variables, representing lower- and higher-dimensional (14D and 84D) settings. For BOMs, we study two acquisition strategies, Thompson sampling and a novel adaptive strategy. We evaluate performance using final calibration quality, convergence behavior, and consistency across runs. The results show that BOMs reach good calibration targets much faster than GA in the lower-D problem. MG-TuRBO performs comparably in our 14D setting, it demonstrates noticeable advantages in the 84D problem, particularly when paired with our adaptive strategy. Our results suggest that MG-TuRBO is especially useful for high-D traffic simulation calibration and potentially for high-D problems in general. --- ### Toward Full Autonomous Laboratory Instrumentation Control with Large Language Models Authors: Yong Xie, Kexin He, Andres Castellanos-Gomez Published: 2026-03-25 Categories: cs.AI, cond-mat.mtrl-sci, cs.HC arXiv: https://arxiv.org/abs/2604.03286v1 The control of complex laboratory instrumentation often requires significant programming expertise, creating a barrier for researchers lacking computational skills. This work explores the potential of large language models (LLMs), such as ChatGPT, and LLM-based artificial intelligence (AI) agents to enable efficient programming and automation of scientific equipment. Through a case study involving the implementation of a setup that can be used as a single-pixel camera or a scanning photocurrent microscope, we demonstrate how ChatGPT can facilitate the creation of custom scripts for instrumentation control, significantly reducing the technical barrier for experimental customization. Building on this capability, we further illustrate how LLM-assisted tools can be extended into autonomous AI agents capable of independently operating laboratory instruments and iteratively refining control strategies. This approach underscores the transformative role of LLM-based tools and AI agents in democratizing laboratory automation and accelerating scientific progress. --- ### Transformers for Program Termination Authors: Yoav Alon, Cristina David Published: 2026-03-25 Categories: cs.PL, cs.LG arXiv: https://arxiv.org/abs/2604.00039v1 Determining whether a program terminates is a core challenge in program analysis with direct implications for correctness, verification, and security. We investigate whether transformer architectures can recognise termination patterns directly from source code and how their strengths can be amplified through ensembles. To overcome the extreme scarcity of non-terminating examples, we design an ensemble framework of compact transformer encoders, systematically trained with a suite of imbalance-aware loss functions and class-aware sampling techniques. By combining models trained with distinct loss functions, our ensembles achieve substantially stronger performance than any single transformer, outperforming both powerful off-the-shelf LLMs and graph-based methods. Finally, we introduce an attribution pipeline that produces syntax-aware explanations for the termination estimation. --- ### Isomorphic Functionalities between Ant Colony and Ensemble Learning: Part II-On the Strength of Weak Learnability and the Boosting Paradigm Authors: Ernest Fokoué, Gregory Babbitt, Yuval Levental Published: 2026-03-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2604.00038v1 In Part I of this series, we established a rigorous mathematical isomorphism between ant colony decision-making and random forest learning, demonstrating that variance reduction through decorrelation is a universal principle shared by biological and computational ensembles. Here we turn to the complementary mechanism: bias reduction through adaptive weighting. Just as boosting algorithms sequentially focus on difficult instances, ant colonies dynamically amplify successful foraging paths through pheromone-mediated recruitment. We prove that these processes are mathematically isomorphic, establishing that the fundamental theorem of weak learnability has a direct analog in colony decision-making. We develop a formal mapping between AdaBoost's adaptive reweighting and ant recruitment dynamics, show that the margin theory of boosting corresponds to the stability of quorum decisions, and demonstrate through comprehensive simulation that ant colonies implementing adaptive recruitment achieve the same bias-reduction benefits as boosting algorithms. This completes a unified theory of ensemble intelligence, revealing that both variance reduction (Part I) and bias reduction (Part II) are manifestations of the same underlying mathematical principles governing collective intelligence in biological and computational systems. --- ### GaloisSAT: Differentiable Boolean Satisfiability Solving via Finite Field Algebra Authors: Curie Kim, Carsten Portner, Mingju Liu, Steve Dai, Haoxing Ren, Brucek Khailany, Alvaro Velasquez, Ismail Alkhouri, Cunxi Yu Published: 2026-03-25 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2603.28796v1 Boolean satisfiability (SAT) problem, the first problem proven to be NP-complete, has become a fundamental challenge in computational complexity, with widespread applications in optimization and verification across many domains. Despite significant algorithmic advances over the past two decades, the performance of SAT solvers has improved at a limited pace. Notably, the 2025 competition winner shows only about a 2X improvement over the 2006 winner in SAT Competition performance after nearly 20 years of effort. This paper introduces GaloisSAT, a novel hybrid GPU-CPU SAT solver that integrates a differentiable SAT solving engine powered by modern machine learning infrastructure on GPUs, followed by a traditional CDCL-based SAT solving stage on CPUs. GaloisSAT is benchmarked against the latest versions of state-of-the-art solvers, Kissat and CaDiCaL, using the SAT Competition 2024 benchmark suite. Results demonstrate substantial improvements in the official SAT Competition metric PAR-2 (penalized average runtime with a timeout of 5,000 seconds and a penalty factor of 2). Specifically, GaloisSAT achieves an 8.41X speedup in the satisfiable category and a 1.29X speedup in the unsatisfiable category compared to the strongest baselines. --- ### Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints Authors: Jelena Markovic-Voronov, Kayhan Behdin, Yuanda Xu, Zhengze Zhou, Zhipeng Wang, Rahul Mazumder Published: 2026-03-25 Categories: cs.LG, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2603.26796v1 We study the problem of routing queries to large language models (LLMs) under cost, GPU resources, and concurrency constraints. Prior per-query routing methods often fail to control batch-level cost, especially under non-uniform or adversarial batching. To address this, we propose a batch-level, resource-aware routing framework that jointly optimizes model assignment for each batch while respecting cost and model capacity limits. We further introduce a robust variant that accounts for uncertainty in predicted LLM performance, along with an offline instance allocation procedure that balances quality and throughput across multiple models. Experiments on two multi-task LLM benchmarks show that robustness improves accuracy by 1-14% over non-robust counterparts (depending on the performance estimator), batch-level routing outperforms per-query methods by up to 24% under adversarial batching, and optimized instance allocation yields additional gains of up to 3% compared to a non-optimized allocation, all while strictly controlling cost and GPU resource constraints. --- ### HASS: Hierarchical Simulation of Logopenic Aphasic Speech for Scalable PPA Detection Authors: Harrison Li, Kevin Wang, Cheol Jun Cho, Jiachen Lian, Rabab Rangwala, Chenxu Guo, Emma Yang, Lynn Kurteff, Zoe Ezzes, Willa Keegan-Rodewald, Jet Vonk, Siddarth Ramkrishnan et al. Published: 2026-03-25 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2603.26795v1 Building a diagnosis model for primary progressive aphasia (PPA) has been challenging due to the data scarcity. Collecting clinical data at scale is limited by the high vulnerability of clinical population and the high cost of expert labeling. To circumvent this, previous studies simulate dysfluent speech to generate training data. However, those approaches are not comprehensive enough to simulate PPA as holistic, multi-level phenotypes, instead relying on isolated dysfluencies. To address this, we propose a novel, clinically grounded simulation framework, Hierarchical Aphasic Speech Simulation (HASS). HASS aims to simulate behaviors of logopenic variant of PPA (lvPPA) with varying degrees of severity. To this end, semantic, phonological, and temporal deficits of lvPPA are systematically identified by clinical experts, and simulated. We demonstrate that our framework enables more accurate and generalizable detection models. --- ### PhyDCM: A Reproducible Open-Source Framework for AI-Assisted Brain Tumor Classification from Multi-Sequence MRI Authors: Hayder Saad Abdulbaqi, Mohammed Hadi Rahim, Mohammed Hassan Hadi, Haider Ali Aboud, Ali Hussein Allawi Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26794v1 MRI-based medical imaging has become indispensable in modern clinical diagnosis, particularly for brain tumor detection. However, the rapid growth in data volume poses challenges for conventional diagnostic approaches. Although deep learning has shown strong performance in automated classification, many existing solutions are confined to closed technical architectures, limiting reproducibility and further academic development. PhyDCM is introduced as an open-source software framework that integrates a hybrid classification architecture based on MedViT with standardized DICOM processing and an interactive desktop visualization interface. The system is designed as a modular digital library that separates computational logic from the graphical interface, allowing independent modification and extension of components. Standardized preprocessing, including intensity rescaling and limited data augmentation, ensures consistency across varying MRI acquisition settings. Experimental evaluation on MRI datasets from BRISC2025 and curated Kaggle collections (FigShare, SARTAJ, and Br35H) demonstrates stable diagnostic performance, achieving over 93% classification accuracy across categories. The framework supports structured, exportable outputs and multi-planar reconstruction of volumetric data. By emphasizing transparency, modularity, and accessibility, PhyDCM provides a practical foundation for reproducible AI-driven medical image analysis, with flexibility for future integration of additional imaging modalities. --- ### A Firefly Algorithm for Mixed-Variable Optimization Based on Hybrid Distance Modeling Authors: Ousmane Tom Bechir, Adán José-García, Zaineb Chelly Garcia, Vincent Sobanski, Clarisse Dhaenens Published: 2026-03-25 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.26792v2 Several real-world optimization problems involve mixed-variable search spaces, where continuous, ordinal, and categorical decision variables coexist. However, most population-based metaheuristic algorithms are designed for either continuous or discrete optimization problems and do not naturally handle heterogeneous variable types. In this paper, we propose an adaptation of the Firefly Algorithm for mixed-variable optimization problems (FAmv). The proposed method relies on a modified distance-based attractiveness mechanism that integrates continuous and discrete components within a unified formulation. This mixed-distance approach enables a more appropriate modeling of heterogeneous search spaces while maintaining a balance between exploration and exploitation. The proposed method is evaluated on the CEC2013 mixed-variable benchmark, which includes unimodal, multimodal, and composition functions. The results show that FAmv achieves competitive, and often superior, performance compared with state-of-the-art mixed-variable optimization algorithms. In addition, experiments on engineering design problems further highlight the robustness and practical applicability of the proposed approach. These results indicate that incorporating appropriate distance formulations into the Firefly Algorithm provides an effective strategy for solving complex mixed-variable optimization problems. --- ### Crystal: Characterizing Relative Impact of Scholarly Publications Authors: Hannah Collison, Benjamin Van Durme, Daniel Khashabi Published: 2026-03-25 Categories: cs.DL, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.26791v3 Assessing a cited paper's impact is typically done by analyzing its citation context in isolation within the citing paper. While this focuses on the most directly relevant text, it prevents relative comparisons across all the works a paper cites. We propose Crystal, which instead jointly ranks all cited papers within a citing paper using large language models (LLMs). To mitigate LLMs' positional bias, we rank each list three times in a randomized order and aggregate the impact labels through majority voting. This joint approach leverages the full citation context, rather than evaluating citations independently, to more reliably distinguish impactful references. Crystal outperforms a prior state-of-the-art impact classifier by +9.5% accuracy and +8.3% F1 on a dataset of human-annotated citations. Crystal further gains efficiency through fewer LLM calls and outperforms prior baselines using an open-weight model, enabling scalable, cost-effective citation impact analysis. In a case study of ACL Test-of-Time award-winning papers, we find that Crystal's impact characterizations align closely with long-term scientific recognition. We release Crystal-Bank, a 46.8k-paper dataset with rankings and impact labels, along with code. --- ### Elucidating the Design Space of Flow Matching for Cellular Microscopy Authors: Charles Jones, Emmanuel Noutahi, Jason Hartford, Cian Eastwood Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26790v1 Flow-matching generative models are increasingly used to simulate cell responses to biological perturbations. However, the design space for building such models is large and underexplored. We systematically analyse the design space of flow matching models for cell-microscopy images, finding that many popular techniques are unnecessary and can even hurt performance. We develop a simple, stable, and scalable recipe which we use to train our foundation model. We scale our model to two orders of magnitude larger than prior methods, achieving a two-fold FID and ten-fold KID improvement over prior methods. We then fine-tune our model with pre-trained molecular embeddings to achieve state-of-the-art performance simulating responses to unseen molecules. Code is available at https://github.com/valence-labs/microscopy-flow-matching --- ### Confidence Matters: Uncertainty Quantification and Precision Assessment of Deep Learning-based CMR Biomarker Estimates Using Scan-rescan Data Authors: Dewmini Hasara Wickremasinghe, Michelle Gibogwe, Andrew Bell, Esther Puyol-Antón, Muhummad Sohaib Nazir, Reza Razavi, Bruno Paun, Paul Aljabar, Andrew P. King Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26789v1 The performance of deep learning (DL) methods for the analysis of cine cardiovascular magnetic resonance (CMR) is typically assessed in terms of accuracy, overlooking precision. In this work, uncertainty estimation techniques, namely deep ensemble, test-time augmentation, and Monte Carlo dropout, are applied to a state-of-the-art DL pipeline for cardiac functional biomarker estimation, and new distribution-based metrics are proposed for the assessment of biomarker precision. The model achieved high accuracy (average Dice 87%) and point estimate precision on two external validation scan-rescan CMR datasets. However, distribution-based metrics showed that the overlap between scan/rescan confidence intervals was >50% in less than 45% of the cases. Statistical similarity tests between scan and rescan biomarkers also resulted in significant differences for over 65% of the cases. We conclude that, while point estimate metrics might suggest good performance, distributional analyses reveal lower precision, highlighting the need to use more representative metrics to assess scan-rescan agreement. --- ### ReMemNav: Memory-Based Decision Correction and Target Verification for Zero-Shot Object Navigation Authors: Feng Wu, Wei Zuo, Wenliang Yang, Jun Xiao, Yang Liu, Xinhua Zeng Published: 2026-03-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.26788v3 Zero-shot object navigation requires agents to locate unseen targets in unfamiliar environments without prior maps or task-specific training. Despite the commonsense reasoning ability of vision-language models (VLMs), existing mapless navigators often suffer from repeated exploration and premature stopping caused by limited historical context and false-positive target predictions. We propose ReMemNav, a training-free framework that combines lightweight semantic grounding, memory-based decision correction, and target verification. RAM-derived semantic priors guide panoramic direction selection, while a geometry-triggered correction mechanism retrieves historical scene descriptions when the selected direction points toward previously visited regions. When a target is predicted to be visible, ReMemNav verifies the corresponding single-view observation before the final approach. Depth-based action sampling then converts the high-level decision into collision-free motion. Experiments on HM3D and MP3D show that ReMemNav achieves higher success rates and path efficiency than existing training-free zero-shot baselines. Specifically, ReMemNav achieves absolute SR/SPL gains of 1.7%/5.3% on HM3D v0.1, 18.2%/11.1% on HM3D v0.2, and 8.7%/6.9% on MP3D. --- ### ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation Authors: Feng Wu, Wei Zuo, Wenliang Yang, Jun Xiao, Yang Liu, Xinhua Zeng Published: 2026-03-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2603.26788v2 Zero-shot object navigation requires agents to locate unseen target objects in unfamiliar environments without prior maps or task-specific training which remains a significant challenge. Although recent advancements in vision-language models(VLMs) provide promising commonsense reasoning capabilities for this task, these models still suffer from spatial hallucinations, local exploration deadlocks, and a disconnect between high-level semantic intent and low-level control. In this regard, we propose a novel hierarchical navigation framework named ReMemNav, which seamlessly integrates panoramic semantic priors and episodic memory with VLMs. We introduce the Recognize Anything Model to anchor the spatial reasoning process of the VLM. We also design an adaptive dual-modal rethinking mechanism based on an episodic semantic buffer queue. The proposed mechanism actively verifies target visibility and corrects decisions using historical memory to prevent deadlocks. For low-level action execution, ReMemNav extracts a sequence of feasible actions using depth masks, allowing the VLM to select the optimal action for mapping into actual spatial movement. Extensive evaluations on HM3D and MP3D demonstrate that ReMemNav outperforms existing training-free zero-shot baselines in both success rate and exploration efficiency. Specifically, we achieve significant absolute performance improvements, with SR and SPL increasing by 1.7% and 7.0% on HM3D v0.1, 18.2% and 11.1% on HM3D v0.2, and 8.7% and 7.9% on MP3D. --- ### Brain-Inspired Multimodal Spiking Neural Network for Image-Text Retrieval Authors: Xintao Zong, Xian Zhong, Wenxuan Liu, Jianhao Ding, Zhaofei Yu, Tiejun Huang Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26787v1 Spiking neural networks (SNNs) have recently shown strong potential in unimodal visual and textual tasks, yet building a directly trained, low-energy, and high-performance SNN for multimodal applications such as image-text retrieval (ITR) remains highly challenging. Existing artificial neural network (ANN)-based methods often pursue richer unimodal semantics using deeper and more complex architectures, while overlooking cross-modal interaction, retrieval latency, and energy efficiency. To address these limitations, we present a brain-inspired Cross-Modal Spike Fusion network (CMSF) and apply it to ITR for the first time. The proposed spike fusion mechanism integrates unimodal features at the spike level, generating enhanced multimodal representations that act as soft supervisory signals to refine unimodal spike embeddings, effectively mitigating semantic loss within CMSF. Despite requiring only two time steps, CMSF achieves top-tier retrieval accuracy, surpassing state-of-the-art ANN counterparts while maintaining exceptionally low energy consumption and high retrieval speed. This work marks a significant step toward multimodal SNNs, offering a brain-inspired framework that unifies temporal dynamics with cross-modal alignment and provides new insights for future spiking-based multimodal research. The code is available at https://github.com/zxt6174/CMSF. --- ### A Step Toward Federated Pretraining of Multimodal Large Language Models Authors: Baochen Xiong, Yifan Xu, Xiaoshan Yang, Yaguang Song, Yaowei Wang, Changsheng Xu Published: 2026-03-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.26786v1 The rapid evolution of Multimodal Large Language Models (MLLMs) is bottlenecked by the saturation of high-quality public data, while vast amounts of diverse multimodal data remain inaccessible in privacy-sensitive silos. Federated Learning (FL) offers a promising solution to unlock these distributed resources, but existing research focuses predominantly on fine-tuning, leaving the foundational pre-training phase largely unexplored. In this paper, we formally introduce the Federated MLLM Alignment (Fed-MA) task, a lightweight pre-training paradigm that freezes the vision encoder and LLM while collaboratively training the cross-modal projector. We identify two critical challenges in this setting: (i) parameter interference in aggregating local projectors; and (ii) gradient oscillations in one-pass collaborative SGD. To address these challenges, we propose Fed-CMP, a pioneering framework for federated MLLM pre-training. Fed-CMP employs Canonical Reliability-Aware Aggregation, which constructs a canonical space to decompose client projectors into a shared alignment basis and client-specific coefficients, then performs reliability-weighted fusion to suppress parameter interference. Furthermore, Fed-CMP introduces Orthogonality-Preserved Momentum, which applies momentum to the shared alignment basis via orthogonal projection, accumulating historical optimization directions while preserving geometric structure. We construct four federated pre-training scenarios based on public datasets, and extensive experiments validate that Fed-CMP significantly outperforms existing baselines. --- ### Beyond Benchmarks: A Framework for Post Deployment Validation of CT Lung Nodule Detection AI Authors: Daniel Soliman Published: 2026-03-25 Categories: eess.IV, cs.CV, physics.med-ph arXiv: https://arxiv.org/abs/2603.26785v1 Background: Artificial intelligence (AI) assisted lung nodule detection systems are increasingly deployed in clinical settings without site-specific validation. Performance reported under benchmark conditions may not reflect real-world behavior when acquisition parameters differ from training data. Purpose: To propose and demonstrate a physics-guided framework for evaluating the sensitivity of a deployed lung nodule detection model to systematic variation in CT acquisition parameters. Methods: Twenty-one cases from the publicly available LIDC-IDRI dataset were evaluated using a MONAI RetinaNet model pretrained on LUNA16 (fold 0, no fine-tuning). Five imaging conditions were tested: baseline, 25% dose reduction, 50% dose reduction, 3 mm slice thickness, and 5 mm slice thickness. Dose reduction was simulated via image-domain Gaussian noise; slice thickness via moving average along the z-axis. Detection sensitivity was computed at a confidence threshold of 0.5 with a 15 mm matching criterion. Results: Baseline sensitivity was 45.2% (57/126 consensus nodules). Dose reduction produced slight degradation: 41.3% at 25% dose and 42.1% at 50% dose. The 5 mm slice thickness condition produced a marked drop to 26.2% - a 19 percentage point reduction representing a 42% relative decrease from baseline. This finding was consistent across confidence thresholds from 0.1 to 0.9. Per-case analysis revealed heterogeneous performance including two cases with complete detection failure at baseline. Conclusion: Slice thickness represents a more fundamental constraint on AI detection performance than image noise under the conditions tested. The proposed framework is reproducible, requires no proprietary scanner data, and is designed to serve as the basis for ongoing post-deployment QA in resource-constrained environment. --- ### HighlightBench: Benchmarking Markup-Driven Table Reasoning in Scientific Documents Authors: Lexin Wang, Shenghua Liu, Yiwei Wang, Yujun Cai, Yuyao Ge, Jiayu Yao, Jiafeng Guo, Xueqi Cheng Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26784v1 Visual markups such as highlights, underlines, and bold text are common in table-centric documents. Although multimodal large language models (MLLMs) have made substantial progress in document understanding, their ability to treat such cues as explicit logical directives remains under-explored. More importantly, existing evaluations cannot distinguish whether a model fails to see the markup or fails to reason with it. This creates a key blind spot in assessing markup-conditioned behavior over tables. To address this gap, we introduce HighlightBench, a diagnostic benchmark for markup-driven table understanding that decomposes evaluation into five task families: Markup Grounding, Constrained Retrieval, Local Relations, Aggregation \& Comparison, and Consistency \& Missingness. We further provide a reference pipeline that makes intermediate decisions explicit, enabling reproducible baselines and finer-grained attribution of errors along the perception-to-execution chain. Experiments show that even strong models remain unstable when visual cues must be consistently aligned with symbolic reasoning under structured output constraints. --- ### Can We Change the Stroke Size for Easier Diffusion? Authors: Yunwei Bai, Ying Kiat Tan, Yao Shu, Tsuhan Chen Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26783v4 Diffusion models can be challenged in the low signal-to-noise regime, where they have to make pixel-level predictions despite the presence of high noise. The geometric intuition is akin to using the finest stroke for oil painting throughout, which may be ineffective. We therefore study \emph{stroke-size control} as a controlled intervention that changes the roughness of the supervised target, predictions and perturbations across timesteps, in an attempt to ease the low signal-to-noise challenge via the prediction target simplification. --- ### Can We Change the Stroke Size for Easier Diffusion? Authors: Yunwei Bai, Ying Kiat Tan, Yao Shu, Tsuhan Chen Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26783v2 Diffusion models can be challenged in the low signal-to-noise regime, where they have to make pixel-level predictions despite the presence of high noise. The geometric intuition is akin to using the finest stroke for oil painting throughout, which may be ineffective. We therefore study stroke-size control as a controlled intervention that changes the effective roughness of the supervised target, predictions and perturbations across timesteps, in an attempt to ease the low signal-to-noise challenge. --- ### Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation Authors: In-Chang Baek, Jiyun Jung, Geum-Hwan Hwang, Sung-Hyun Kim, Kyung-Joong Kim Published: 2026-03-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2603.26782v2 Text-to-level generation aims to translate natural language descriptions into structured game levels, enabling intuitive control over procedural content generation. While prior text-to-level generators are typically limited to a single game domain, extending language-conditioned generation to multiple games requires learning representations that capture structural relationships across domains. We propose Multiverse, a language-conditioned multi-game level generator that enables cross-game level blending through textual specifications. The model learns a shared latent space aligning textual instructions and level structures, while a threshold-based multi-positive contrastive supervision links semantically related levels across games. This representation allows language to guide which structural characteristics should be preserved when combining content from different games, enabling controllable blending through latent interpolation and zero-shot generation from compositional textual prompts. Experiments show that the learned representation supports controllable cross-game level blending and significantly improves blending quality within the same game genre, while providing a unified representation for language-conditioned multi-game content generation. --- ### Efficient Encrypted Computation in Convolutional Spiking Neural Networks with TFHE Authors: Longfei Guo, Pengbo Li, Ting Gao, Yonghai Zhong, Haojie Fan, Jinqiao Duan Published: 2026-03-25 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2603.26781v1 With the rapid advancement of AI technology, we have seen more and more concerns on data privacy, leading to some cutting-edge research on machine learning with encrypted computation. Fully Homomorphic Encryption (FHE) is a crucial technology for privacy-preserving computation, while it struggles with continuous non-polynomial functions, as it operates on discrete integers and supports only addition and multiplication. Spiking Neural Networks (SNNs), which use discrete spike signals, naturally complement FHE's characteristics. In this paper, we introduce FHE-DiCSNN, a framework built on the TFHE scheme, utilizing the discrete nature of SNNs for secure and efficient computations. By leveraging bootstrapping techniques, we successfully implement Leaky Integrate-and-Fire (LIF) neuron models on ciphertexts, allowing SNNs of arbitrary depth. Our framework is adaptable to other spiking neuron models, offering a novel approach to homomorphic evaluation of SNNs. Additionally, we integrate convolutional methods inspired by CNNs to enhance accuracy and reduce the simulation time associated with random encoding. Parallel computation techniques further accelerate bootstrapping operations. Experimental results on the MNIST and FashionMNIST datasets validate the effectiveness of FHE-DiCSNN, with a loss of less than 3\% compared to plaintext, respectively, and computation times of under 1 second per prediction. We also apply the model into real medical image classification problems and analyze the parameter optimization and selection. --- ### RatSeizure: A Benchmark and Saliency-Context Transformer for Rat Seizure Localization Authors: Ting Yu Tsai, An Yu, Lucy Lee, Felix X. -F. Ye, Damian S. Shin, Tzu-Jen Kao, Xin Li, Ming-Ching Chang Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.26780v1 Animal models, particularly rats, play a critical role in seizure research for studying epileptogenesis and treatment response. However, progress is limited by the lack of datasets with precise temporal annotations and standardized evaluation protocols. Existing animal behavior datasets often have limited accessibility, coarse labeling, and insufficient temporal localization of clinically meaningful events. To address these limitations, we introduce RatSeizure, the first publicly benchmark for fine-grained seizure behavior analysis. The dataset consists of recorded clips annotated with seizure-related action units and temporal boundaries, enabling both behavior classification and temporal localization. We further propose RaSeformer, a saliency-context Transformer for temporal action localization that highlights behavior-relevant context while suppressing redundant cues. Experiments on RatSeizure show that RaSeformer achieves strong performance and provides a competitive reference model for this challenging task. We also establish standardized dataset splits and evaluation protocols to support reproducible benchmarking. --- ### Limits of Spatial Imagery Reasoning in Frontier LLM Models Authors: Sergio Y. Hayashi, Nina S. T. Hirata Published: 2026-03-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.26779v2 Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, yet they struggle with spatial tasks that require mental simulation, such as mental rotation. This paper investigates whether equipping an LLM with an external ``Imagery Module'' -- a tool capable of rendering and rotating 3D models -- can bridge this gap, functioning as a ``cognitive prosthetic.'' We conducted experiments using a dual-module architecture in which a reasoning module (an MLLM) interacts with an imagery module on 3D model rotation tasks. Performance was lower than expected, with accuracy reaching at most 62.5%. Further investigation suggests that even when the burden of maintaining and manipulating a holistic 3D state is outsourced, the system still fails. This reveals that current frontier models lack the foundational visual-spatial primitives required to interface with imagery. Specifically, they lack: (1) the low-level sensitivity to extract spatial signals such as (a) depth, (b) motion, and (c) short-horizon dynamic prediction; and (2) the capacity to reason contemplatively over images, dynamically shifting visual focus and balancing imagery with symbolic and associative information. --- ### TED: Training-Free Experience Distillation for Multimodal Reasoning Authors: Shuozhi Yuan, Jinqing Wang, Zihao Liu, Miaomiao Yuan, Haoran Peng, Jin Zhao, Bingwen Wang, Haoyi Wang Published: 2026-03-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.26778v1 Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates and large-scale training data, limiting their applicability in resource-constrained environments. In this work, we propose TED, a training-free, context-based distillation framework that shifts the update target of distillation from model parameters to an in-context experience injected into the student's prompt. For each input, the student generates multiple reasoning trajectories, while a teacher independently produces its own solution. The teacher then compares the student trajectories with its reasoning and the ground-truth answer, extracting generalized experiences that capture effective reasoning patterns. These experiences are continuously refined and updated over time. A key challenge of context-based distillation is unbounded experience growth and noise accumulation. TED addresses this with an experience compression mechanism that tracks usage statistics and selectively merges, rewrites, or removes low-utility experiences. Experiments on multimodal reasoning benchmarks MathVision and VisualPuzzles show that TED consistently improves performance. On MathVision, TED raises the performance of Qwen3-VL-8B from 0.627 to 0.702, and on VisualPuzzles from 0.517 to 0.561 with just 100 training samples. Under this low-data, no-update setting, TED achieves performance competitive with fully trained parameter-based distillation while reducing training cost by over 5x, demonstrating that meaningful knowledge transfer can be achieved through contextual experience. --- ### A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning Authors: Changyu Liu, James Chenhao Liang, Wenhao Yang, Yiming Cui, Jinghao Yang, Tianyang Wang, Qifan Wang, Dongfang Liu, Cheng Han Published: 2026-03-25 Categories: cs.CV, cs.AI, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2603.25758v1 Diffusion models have significantly reshaped the field of generative artificial intelligence and are now increasingly explored for their capacity in discriminative representation learning. Diffusion Transformer (DiT) has recently gained attention as a promising alternative to conventional U-Net-based diffusion models, demonstrating a promising avenue for downstream discriminative tasks via generative pre-training. However, its current training efficiency and representational capacity remain largely constrained due to the inadequate timestep searching and insufficient exploitation of DiT-specific feature representations. In light of this view, we introduce Automatically Selected Timestep (A-SelecT) that dynamically pinpoints DiT's most information-rich timestep from the selected transformer feature in a single run, eliminating the need for both computationally intensive exhaustive timestep searching and suboptimal discriminative feature selection. Extensive experiments on classification and segmentation benchmarks demonstrate that DiT, empowered by A-SelecT, surpasses all prior diffusion-based attempts efficiently and effectively. --- ### KANEL: Kolmogorov-Arnold Network Ensemble Learning Enables Early Hit Enrichment in High-Throughput Virtual Screening Authors: Pavel Koptev, Nikita Krainov, Konstantin Malkov, Alexander Tropsha Published: 2026-03-25 Categories: physics.chem-ph, cs.LG, q-bio.QM, stat.ML arXiv: https://arxiv.org/abs/2603.25755v1 Machine learning models of chemical bioactivity are increasingly used for prioritizing a small number of compounds in virtual screening libraries for experimental follow-up. In these applications, assessing model accuracy by early hit enrichment such as Positive Predicted Value (PPV) calculated for top N hits (PPV@N) is more appropriate and actionable than traditional global metrics such as AUC. We present KANEL, an ensemble workflow that combines interpretable Kolmogorov-Arnold Networks (KANs) with XGBoost, random forest, and multilayer perceptron models trained on complementary molecular representations (LillyMol descriptors, RDKit-derived descriptors, and Morgan fingerprints). --- ### Learning to Staff: Offline Reinforcement Learning and Fine-Tuned LLMs for Warehouse Staffing Optimization Authors: Kalle Kujanpää, Yuying Zhu, Kristina Klinkner, Shervin Malmasi Published: 2026-03-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.24883v1 We investigate machine learning approaches for optimizing real-time staffing decisions in semi-automated warehouse sortation systems. Operational decision-making can be supported at different levels of abstraction, with different trade-offs. We evaluate two approaches, each in a matching simulation environment. First, we train custom Transformer-based policies using offline reinforcement learning on detailed historical state representations, achieving a 2.4% throughput improvement over historical baselines in learned simulators. In high-volume warehouse operations, improvements of this size translate to significant savings. Second, we explore LLMs operating on abstracted, human-readable state descriptions. These are a natural fit for decisions that warehouse managers make using high-level operational summaries. We systematically compare prompting techniques, automatic prompt optimization, and fine-tuning strategies. While prompting alone proves insufficient, supervised fine-tuning combined with Direct Preference Optimization on simulator-generated preferences achieves performance that matches or slightly exceeds historical baselines in a hand-crafted simulator. Our findings demonstrate that both approaches offer viable paths toward AI-assisted operational decision-making. Offline RL excels with task-specific architectures. LLMs support human-readable inputs and can be combined with an iterative feedback loop that can incorporate manager preferences. --- ### More Than "Means to an End": Supporting Reasoning with Transparently Designed AI Data Science Processes Authors: Venkatesh Sivaraman, Patrick Vossler, Adam Perer, Julian Hong, Jean Feng Published: 2026-03-25 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2603.24877v1 Generative artificial intelligence (AI) tools can now help people perform complex data science tasks regardless of their expertise. While these tools have great potential to help more people work with data, their end-to-end approach does not support users in evaluating alternative approaches and reformulating problems, both critical to solving open-ended tasks in high-stakes domains. In this paper, we reflect on two AI data science systems designed for the medical setting and how they function as tools for thought. We find that success in these systems was driven by constructing AI workflows around intentionally-designed intermediate artifacts, such as readable query languages, concept definitions, or input-output examples. Despite opaqueness in other parts of the AI process, these intermediates helped users reason about important analytical choices, refine their initial questions, and contribute their unique knowledge. We invite the HCI community to consider when and how intermediate artifacts should be designed to promote effective data science thinking. --- ### OptiSAR-Net++: A Large-Scale Benchmark and Transformer-Free Framework for Cross-Domain Remote Sensing Visual Grounding Authors: Xiaoyu Tang, Jun Dong, Jintao Cheng, Rui Fan Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24876v2 Remote sensing visual grounding (RSVG) aims to localize specific targets in remote sensing images using natural language expressions. However, existing methods are restricted to single-sensor domains, i.e., either optical or synthetic aperture radar (SAR), limiting their real-world applicability. In this paper, we introduce the Cross-Domain RSVG (CD-RSVG) task and construct OptSAR-RSVG, the first large-scale benchmark dataset for this setting. To tackle the challenges of cross-domain feature modeling, computational inefficiency, and fine-grained semantic discrimination, we propose OptiSAR-Net++. Our framework features a patch-level Low-Rank Adaptation Mixture of Experts (PL-MoE) for efficient cross-domain feature decoupling. To mitigate the substantial computational overhead of Transformer decoding frameworks, we adopt a CLIP-based contrastive paradigm and further incorporate dynamic adversarial negative sampling, thereby transforming generative regression into an efficient cross-modal matching process. Additionally, a text-guided dual-gate fusion module (TGDF-SSA) and a region-aware auxiliary head are introduced to enhance semantic-visual alignment and spatial modeling. Extensive experiments demonstrate that OptiSAR-Net++ achieves SOTA performance on both OptSAR-RSVG and DIOR-RSVG benchmarks, offering significant advantages in localization accuracy and efficiency. The model and dataset have been made publicly available at https://github.com/JunDong-dev/OptiSAR-Net-PlusPlus. --- ### OptiSAR-Net++: A Large-Scale Benchmark and Transformer-Free Framework for Cross-Domain Remote Sensing Visual Grounding Authors: Xiaoyu Tang, Jun Dong, Jintao Cheng, Rui Fan Published: 2026-03-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.24876v1 Remote sensing visual grounding (RSVG) aims to localize specific targets in remote sensing images using natural language expressions. However, existing methods are restricted to single-sensor domains, i.e., either optical or synthetic aperture radar (SAR), limiting their real-world applicability. In this paper, we introduce the Cross-Domain RSVG (CD-RSVG) task and construct OptSAR-RSVG, the first large-scale benchmark dataset for this setting. To tackle the challenges of cross-domain feature modeling, computational inefficiency, and fine-grained semantic discrimination, we propose OptiSAR-Net++. Our framework features a patch-level Low-Rank Adaptation Mixture of Experts (PL-MoE) for efficient cross-domain feature decoupling. To mitigate the substantial computational overhead of Transformer decoding frameworks, we adopt a CLIP-based contrastive paradigm and further incorporate dynamic adversarial negative sampling, thereby transforming generative regression into an efficient cross-modal matching process. Additionally, a text-guided dual-gate fusion module (TGDF-SSA) and a region-aware auxiliary head are introduced to enhance semantic-visual alignment and spatial modeling. Extensive experiments demonstrate that OptiSAR-Net++ achieves SOTA performance on both OptSAR-RSVG and DIOR-RSVG benchmarks, offering significant advantages in localization accuracy and efficiency. Our code and dataset will be made publicly available. --- ### How Far Are Vision-Language Models from Constructing the Real World? A Benchmark for Physical Generative Reasoning Authors: Luyu Yang, Yutong Dai, An Yan, Viraj Prabhu, Ran Xu, Zeyuan Chen Published: 2026-03-25 Categories: cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2603.24866v1 The physical world is not merely visual; it is governed by rigorous structural and procedural constraints. Yet, the evaluation of vision-language models (VLMs) remains heavily skewed toward perceptual realism, prioritizing the generation of visually plausible 3D layouts, shapes, and appearances. Current benchmarks rarely test whether models grasp the step-by-step processes and physical dependencies required to actually build these artifacts, a capability essential for automating design-to-construction pipelines. To address this, we introduce DreamHouse, a novel benchmark for physical generative reasoning: the capacity to synthesize artifacts that concurrently satisfy geometric, structural, constructability, and code-compliance constraints. We ground this benchmark in residential timber-frame construction, a domain with fully codified engineering standards and objectively verifiable correctness. We curate over 26,000 structures spanning 13 architectural styles, ach verified to construction-document standards (LOD 350) and develop a deterministic 10-test structural validation framework. Unlike static benchmarks that assess only final outputs, DreamHouse supports iterative agentic interaction. Models observe intermediate build states, generate construction actions, and receive structured environmental feedback, enabling a fine-grained evaluation of planning, structural reasoning, and self-correction. Extensive experiments with state-of-the-art VLMs reveal substantial capability gaps that are largely invisible on existing leaderboards. These findings establish physical validity as a critical evaluation axis orthogonal to visual realism, highlighting physical generative reasoning as a distinct and underdeveloped frontier in multimodal intelligence. Available at https://luluyuyuyang.github.io/dreamhouse --- ### AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective Authors: Zhenyi Wang, Siyu Luan Published: 2026-03-25 Categories: cs.CR, cs.AI, cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.24857v1 As machine learning (ML) systems expand in both scale and functionality, the security landscape has become increasingly complex, with a proliferation of attacks and defenses. However, existing studies largely treat these threats in isolation, lacking a coherent framework to expose their shared principles and interdependencies. This fragmented view hinders systematic understanding and limits the design of comprehensive defenses. Crucially, the two foundational assets of ML -- \textbf{data} and \textbf{models} -- are no longer independent; vulnerabilities in one directly compromise the other. The absence of a holistic framework leaves open questions about how these bidirectional risks propagate across the ML pipeline. To address this critical gap, we propose a \emph{unified closed-loop threat taxonomy} that explicitly frames model-data interactions along four directional axes. Our framework offers a principled lens for analyzing and defending foundation models. The resulting four classes of security threats represent distinct but interrelated categories of attacks: (1) Data$\rightarrow$Data (D$\rightarrow$D): including \emph{data decryption attacks and watermark removal attacks}; (2) Data$\rightarrow$Model (D$\rightarrow$M): including \emph{poisoning, harmful fine-tuning attacks, and jailbreak attacks}; (3) Model$\rightarrow$Data (M$\rightarrow$D): including \emph{model inversion, membership inference attacks, and training data extraction attacks}; (4) Model$\rightarrow$Model (M$\rightarrow$M): including \emph{model extraction attacks}. Our unified framework elucidates the underlying connections among these security threats and establishes a foundation for developing scalable, transferable, and cross-modal security strategies, particularly within the landscape of foundation models. --- ### SentinelAI: A Multi-Agent Framework for Structuring and Linking NG9-1-1 Emergency Incident Data Authors: Kliment Ho, Ilya Zaslavsky Published: 2026-03-25 Categories: cs.AI, cs.CY, cs.ET, cs.MA arXiv: https://arxiv.org/abs/2603.24856v1 Emergency response systems generate data from many agencies and systems. In practice, correlating and updating this information across sources in a way that aligns with Next Generation 9-1-1 data standards remains challenging. Ideally, this data should be treated as a continuous stream of operational updates, where new facts are integrated immediately to provide a timely and unified view of an evolving incident. This paper presents SentinelAI, a data integration and standardization framework for transforming emergency communications into standardized, machine-readable datasets that support integration, composite incident construction, and cross-source reasoning. SentinelAI implements a scalable processing pipeline composed of specialized agents. The EIDO Agent ingests raw communications and produces NENA-compliant Emergency Incident Data Object JSON. --- ### Resisting Humanization: Ethical Front-End Design Choices in AI for Sensitive Contexts Authors: Silvia Rossi, Diletta Huyskes, Mackenzie Jorgensen Published: 2026-03-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2603.24853v2 Ethical debates in AI have primarily focused on back-end issues such as data governance, model training, and algorithmic decision-making. Less attention has been paid to the ethical significance of front-end design choices, such as the interaction and representation-based elements through which users interact with AI systems. This gap is particularly significant for Conversational User Interfaces (CUI) based on Natural Language Processing (NLP) systems, where humanizing design elements such as dialogue-based interaction, emotive language, personality modes, and anthropomorphic metaphors are increasingly prevalent. This work argues that humanization in AI front-end design is a value-driven choice that profoundly shapes users' mental models, trust calibration, and behavioral responses. Drawing on research in human-computer interaction (HCI), conversational AI, and value-sensitive design, we examine how interfaces can play a central role in misaligning user expectations, fostering misplaced trust, and subtly undermining user autonomy, especially in vulnerable contexts. To ground this analysis, we discuss two AI systems developed by Chayn, a nonprofit organization supporting survivors of gender-based violence. Chayn is extremely cautious when building AI that interacts with or impacts survivors by operationalizing their trauma-informed design principles. This Chayn case study illustrates how ethical considerations can motivate principled restraint in interface design, challenging engagement-based norms in contemporary AI products. We argue that ethical front-end AI design is a form of procedural ethics, enacted through interaction choices rather than embedded solely in system logic. --- ### Towards automatic smoke detector inspection: Recognition of the smoke detectors in industrial facilities and preparation for future drone integration Authors: Lukas Kratochvila, Jakub Stefansky, Simon Bilik, Robert Rous, Tomas Zemcik, Michal Wolny, Frantisek Rusnak, Ondrej Cech, Karel Horak Published: 2026-03-25 Categories: cs.CV, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.24850v1 Fire safety consists of a complex pipeline, and it is a very important topic of concern. One of its frontal parts are the smoke detectors, which are supposed to provide an alarm prior to a massive fire appears. As they are often difficult to reach due to high ceilings or problematic locations, an automatic inspection system would be very beneficial as it could allow faster revisions, prevent workers from dangerous work in heights, and make the whole process cheaper. In this study, we present the smoke detector recognition part of the automatic inspection system, which could easily be integrated to the drone system. As part of our research, we compare two popular convolutional-based object detectors YOLOv11 and SSD widely used on embedded devices together with the state-of-the-art transformer-based RT-DETRv2 with the backbones of different sizes. Due to a complicated way of collecting a sufficient amount of data for training in the real-world environment, we also compare several training strategies using the real and semi-synthetic data together with various augmentation methods. To achieve a robust testing, all models were evaluated on two test datasets with an expected and difficult appearance of the smoke detectors including motion blur, small resolution, or not complete objects. The best performing detector is the YOLOv11n, which reaches the average mAP@0.5 score of 0.884. Our code, pretrained models and dataset are publicly available. --- ### Gaze patterns predict preference and confidence in pairwise AI image evaluation Authors: Nikolas Papadopoulos, Shreenithi Navaneethan, Sheng Bai, Ankur Samanta, Paul Sajda Published: 2026-03-25 Categories: cs.HC, cs.AI, cs.CV, cs.CY arXiv: https://arxiv.org/abs/2603.24849v1 Preference learning methods, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO), rely on pairwise human judgments, yet little is known about the cognitive processes underlying these judgments. We investigate whether eye-tracking can reveal preference formation during pairwise AI-generated image evaluation. Thirty participants completed 1,800 trials while their gaze was recorded. We replicated the gaze cascade effect, with gaze shifting toward chosen images approximately one second before the decision. Cascade dynamics were consistent across confidence levels. Gaze features predicted binary choice (68% accuracy), with chosen images receiving more dwell time, fixations, and revisits. Gaze transitions distinguished high-confidence from uncertain decisions (66% accuracy), with low-confidence trials showing more image switches per second. These results show that gaze patterns predict both choice and confidence in pairwise image evaluations, suggesting that eye-tracking provides implicit signals relevant to the quality of preference annotations. ---