# Research Papers — 2026-03 · bundle page 43 of 243

> Full-text markdown of papers #2101–2150 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/43
[← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/42.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-03/page/44.md)

### Towards Video Anomaly Detection from Event Streams: A Baseline and Benchmark Datasets

Authors: Peng Wu, Yuting Yan, Guansong Pang, Yujia Sun, Qingsen Yan, Peng Wang, Yanning Zhang
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24991v2

Event-based vision, characterized by low redundancy, focus on dynamic motion, and inherent privacy-preserving properties, naturally fits the demands of video anomaly detection (VAD). However, the absence of dedicated event-stream anomaly detection datasets and effective modeling strategies has significantly hindered progress in this field. In this work, we take the first major step toward establishing event-based VAD as a unified research direction. We first construct multiple event-stream based benchmarks for video anomaly detection, featuring synchronized event and RGB recordings. Leveraging the unique properties of events, we then propose an EVent-centric spatiotemporal Video Anomaly Detection framework, namely EWAD, with three key innovations: an event density aware dynamic sampling strategy to select temporally informative segments; a density-modulated temporal modeling approach that captures contextual relations from sparse event streams; and an RGB-to-event knowledge distillation mechanism to enhance event-based representations under weak supervision. Extensive experiments on three benchmarks demonstrate that our EWAD achieves significant improvements over existing approaches, highlighting the potential and effectiveness of event-driven modeling for video anomaly detection. The benchmark datasets will be made publicly available.

---

### Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model

Authors: Ziyan Wang, Peng Chen, Ding Li, Chiwei Li, Qichao Zhang, Zhongpu Xia, Guizhen Yu
Published: 2026-03-26
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2603.24989v1

Learning diverse and high-fidelity traffic simulations from human driving demonstrations is crucial for autonomous driving evaluation. The recent next-token prediction (NTP) paradigm, widely adopted in large language models (LLMs), has been applied to traffic simulation and achieves iterative improvements via supervised fine-tuning (SFT). However, such methods limit active exploration of potentially valuable motion tokens, particularly in suboptimal regions. Entropy patterns provide a promising perspective for enabling exploration driven by motion token uncertainty. Motivated by this insight, we propose a novel tokenized traffic simulation policy, R1Sim, which represents an initial attempt to explore reinforcement learning based on motion token entropy patterns, and systematically analyzes the impact of different motion tokens on simulation outcomes. Specifically, we introduce an entropy-guided adaptive sampling mechanism that focuses on previously overlooked motion tokens with high uncertainty yet high potential. We further optimize motion behaviors using Group Relative Policy Optimization (GRPO), guided by a safety-aware reward design. Overall, these components enable a balanced exploration-exploitation trade-off through diverse high-uncertainty sampling and group-wise comparative estimation, resulting in realistic, safe, and diverse multi-agent behaviors. Extensive experiments on the Waymo Sim Agent benchmark demonstrate that R1Sim achieves competitive performance compared to state-of-the-art methods.

---

### Rethinking Health Agents: From Siloed AI to Collaborative Decision Mediators

Authors: Ray-Yuan Chung, Xuhai Xu, Ari Pollack
Published: 2026-03-26
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2603.24986v1

Large language model based health agents are increasingly used by health consumers and clinicians to interpret health information and guide health decisions. However, most AI systems in healthcare operate in siloed configurations, supporting individual users rather than the multi-stakeholder relationships central to healthcare. Such use can fragment understanding and exacerbate misalignment among patients, caregivers, and clinicians. We reframe AI not as a standalone assistant, but as a collaborator embedded within multi-party care interactions. Through a clinically validated fictional pediatric chronic kidney disease case study, we show that breakdowns in adherence stem from fragmented situational awareness and misaligned goals, and that siloed use of general-purpose AI tools does little to address these collaboration gaps. We propose a conceptual framework for designing AI collaborators that surface contextual information, reconcile mental models, and scaffold shared understanding while preserving human decision authority.

---

### Few-Shot Left Atrial Wall Segmentation in 3D LGE MRI via Meta-Learning

Authors: Yusri Al-Sanaani, Rebecca Thornhill, Pablo Nery, Elena Pena, Robert deKemp, Calum Redpath, David Birnie, Sreeraman Rajan
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24985v3

Segmenting the left atrial (LA) wall from late gadolinium enhancement magnetic resonance imaging (LGE-MRI) is challenging because of its thin geometry, low contrast, and limited expert annotations. We propose a model-agnostic meta-learning (MAML) framework with a 3D residual U-Net backbone for K-shot (K = 5, 10, 20) LA wall segmentation. The framework is meta-trained on LA wall tasks together with auxiliary LA and right atrial (RA) cavity tasks and uses a boundary-aware composite loss to improve thin-structure delineation. We evaluated MAML on a held-out clean test set and assessed its robustness under an unseen synthetic domain shift and on a local cohort. On the held-out clean test set, MAML outperformed the K-shot fine-tuning baseline at 5-shot, achieving Dice coefficient (DSC) = 0.54 versus 0.48 and Hausdorff distance (HD95) = 4.60 versus 6.40 mm. At 20-shot, MAML approached the fully supervised model trained from scratch, with DSC = 0.59 versus 0.61. Under unseen shifts, performance decreased relative to clean testing but improved consistently as K increased. At 5-shot, MAML achieved DSC = 0.52 and HD95 = 5.02 mm under the unseen synthetic shift, and DSC = 0.50 and HD95 = 5.43 mm on the local cohort. These results suggest that meta-learning can improve thin-wall delineation in low-shot adaptation and may reduce the annotation burden for atrial remodeling assessment.

---

### MoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models

Authors: Dohwan Ko, Jinyoung Park, Seoung Choi, Sanghyeok Lee, Seohyun Lee, Hyunwoo J. Kim
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24984v2

Mixture-of-Experts (MoE) has emerged as an effective approach to reduce the computational overhead of Transformer architectures by sparsely activating a subset of parameters for each token while preserving high model capacity. This paradigm has recently been extended to Vision-Language Models (VLMs), enabling scalable multi-modal understanding with reduced computational cost. However, the widely adopted deterministic top-K routing mechanism may overlook more optimal expert combinations and lead to expert overfitting. To address this limitation and improve the diversity of expert selection, we propose MoE-GRPO, a reinforcement learning (RL)-based framework for optimizing expert routing in MoE-based VLMs. Specifically, we formulate expert selection as a sequential decision-making problem and optimize it using Group Relative Policy Optimization (GRPO), allowing the model to learn adaptive expert routing policies through exploration and reward-based feedback. Furthermore, we introduce a modality-aware router guidance that enhances training stability and efficiency by discouraging the router from exploring experts that are infrequently activated for a given modality. Extensive experiments on multi-modal image and video benchmarks show that MoE-GRPO consistently outperforms standard top-K routing and its variants by promoting more diverse expert selection, thereby mitigating expert overfitting and enabling a task-level expert specialization.

---

### Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection

Authors: Xiaowei Zhu, Yubing Ren, Fang Fang, Shi Wang, Yanan Cao, Li Guo
Published: 2026-03-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.24981v1

The rapid advancement of large language models has increasingly blurred the boundary between human-written and AI-generated text, raising societal risks such as misinformation dissemination, authorship ambiguity, and threats to intellectual property rights. These concerns highlight the urgent need for effective and reliable detection methods. While existing training-free approaches often achieve strong performance by aggregating token-level signals into a global score, they typically assume uniform token contributions, making them less robust under short sequences or localized token modifications. To address these limitations, we propose Exons-Detect, a training-free method for AI-generated text detection based on an exon-aware token reweighting perspective. Exons-Detect identifies and amplifies informative exonic tokens by measuring hidden-state discrepancy under a dual-model setting, and computes an interpretable translation score from the resulting importance-weighted token sequence. Empirical evaluations demonstrate that Exons-Detect achieves state-of-the-art detection performance and exhibits strong robustness to adversarial attacks and varying input lengths. In particular, it attains a 2.2\% relative improvement in average AUROC over the strongest prior baseline on DetectRL.

---

### LLM-Driven Reasoning for Constraint-Aware Feature Selection in Industrial Systems

Authors: Yuhang Zhou, Zhuokai Zhao, Ke Li, Spilios Evmorfos, Gökalp Demirci, Mingyi Wang, Qiao Liu, Qifei Wang, Serena Li, Weiwei Li, Tingting Wang, Mingze Gao et al.
Published: 2026-03-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.24979v1

Feature selection is a crucial step in large-scale industrial machine learning systems, directly affecting model accuracy, efficiency, and maintainability. Traditional feature selection methods rely on labeled data and statistical heuristics, making them difficult to apply in production environments where labeled data are limited and multiple operational constraints must be satisfied. To address this, we propose Model Feature Agent (MoFA), a model-driven framework that performs sequential, reasoning-based feature selection using both semantic and quantitative feature information. MoFA incorporates feature definitions, importance scores, correlations, and metadata (e.g., feature groups or types) into structured prompts and selects features through interpretable, constraint-aware reasoning. We evaluate MoFA in three real-world industrial applications: (1) True Interest and Time-Worthiness Prediction, where it improves accuracy while reducing feature group complexity, (2) Value Model Enhancement, where it discovers high-order interaction terms that yield substantial engagement gains in online experiments, and (3) Notification Behavior Prediction, where it selects compact, high-value feature subsets that improve both model accuracy and inference efficiency. Together, these results demonstrate the practicality and effectiveness of LLM-based reasoning for feature selection in real production systems.

---

### The Value of Information in Resource-Constrained Pricing

Authors: Ruicheng Ao, Jiashuo Jiang, David Simchi-Levi
Published: 2026-03-26
Categories: math.OC, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.24974v1

Firms that price perishable resources -- airline seats, hotel rooms, seasonal inventory -- now routinely use demand predictions, but these predictions vary widely in quality. Under hard capacity constraints, acting on an inaccurate prediction can irreversibly deplete inventory needed for future periods. We study how prediction uncertainty propagates into dynamic pricing decisions with linear demand, stochastic noise, and finite capacity. A certified demand forecast with known error bound~$ε^0$ specifies where the system should operate: it shifts regret from $O(\sqrt{T})$ to $O(\log T)$ when $ε^0 \lesssim T^{-1/4}$, and we prove this threshold is tight. A misspecified surrogate model -- biased but correlated with true demand -- cannot set prices directly but reduces learning variance by a factor of $(1-ρ^2)$ through control variates. The two mechanisms compose: the forecast determines the regret regime; the surrogate tightens estimation within it. All algorithms rest on a boundary attraction mechanism that stabilizes pricing near degenerate capacity boundaries without requiring non-degeneracy assumptions. Experiments confirm the phase transition threshold, the variance reduction from surrogates, and robustness across problem instances.

---

### PASDiff: Physics-Aware Semantic Guidance for Joint Real-World Low-Light Face Enhancement and Restoration

Authors: Yilin Ni, Wenjie Li, Zhengxue Wang, Juncheng Li, Guangwei Gao, Jian Yang
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24969v2

Face images captured in real-world low light suffer multiple degradations-low illumination, blur, noise, and low visibility, etc. Existing cascaded solutions often suffer from severe error accumulation, while generic joint models lack explicit facial priors and struggle to resolve clear face structures. In this paper, we propose PASDiff, a Physics-Aware Semantic Diffusion with a training-free manner. To achieve a plausible illumination and color distribution, we leverage inverse intensity weighting and Retinex theory to introduce photometric constraints, thereby reliably recovering visibility and natural chromaticity. To faithfully reconstruct facial details, our Style-Agnostic Structural Injection (SASI) extracts structures from an off-the-shelf facial prior while filtering out its intrinsic photometric biases, seamlessly harmonizing identity features with physical constraints. Furthermore, we construct WildDark-Face, a real-world benchmark of 700 low-light facial images with complex degradations. Extensive experiments demonstrate that PASDiff significantly outperforms existing methods, achieving a superior balance among natural illumination, color recovery, and identity consistency. Code and dataset will be available at https://github.com/IVIPLab/PASDiff.

---

### Subject-Specific Low-Field MRI Synthesis via a Neural Operator

Authors: Ziqi Gao, Nicha Dvornek, Xiaoran Zhang, Gigi Galiana, Hemant Tagare, Todd Constable
Published: 2026-03-26
Categories: eess.IV, cs.AI
arXiv: https://arxiv.org/abs/2603.24968v1

Low-field (LF) magnetic resonance imaging (MRI) improves accessibility and reduces costs but generally has lower signal-to-noise ratios and degraded contrast compared to high field (HF) MRI, limiting its clinical utility. Simulating LF MRI from HF MRI enables virtual evaluation of novel imaging devices and development of LF algorithms. Existing low field simulators rely on noise injection and smoothing, which fail to capture the contrast degradation seen in LF acquisitions. To this end, we introduce an end-to-end LF-MRI synthesis framework that learns HF to LF image degradation directly from a small number of paired HF-LF MRIs. Specifically, we introduce a novel HF to LF coordinate-image decoupled neural operator (H2LO) to model the underlying degradation process, and tailor it to capture high-frequency noise textures and image structure. Experimental results in T1w and T2w MRI demonstrate that H2LO produces more faithful simulated low-field images than existing parameterized noise synthesis models and popular image-to-image translation models. Furthermore, it improves performance in downstream image enhancement tasks, showcasing its potential to enhance LF MRI diagnostic capabilities.

---

### The Anatomy of Uncertainty in LLMs

Authors: Aditya Taparia, Ransalu Senanayake, Kowshik Thopalli, Vivek Narayanaswamy
Published: 2026-03-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2603.24967v2

Understanding why a large language model (LLM) is uncertain about the response is important for their reliable deployment. Current approaches, which either provide a single uncertainty score or rely on the classical aleatoric-epistemic dichotomy, fail to offer actionable insights for improving the generative model. Recent studies have also shown that such methods are not enough for understanding uncertainty in LLMs. In this work, we advocate for an uncertainty decomposition framework that dissects LLM uncertainty into three distinct semantic components: (i) input ambiguity, arising from ambiguous prompts; (ii) knowledge gaps, caused by insufficient parametric evidence; and (iii) decoding randomness, stemming from stochastic sampling. Through a series of experiments we demonstrate that the dominance of these components can shift across model size and task. Our framework provides a better understanding to audit LLM reliability and detect hallucinations, paving the way for targeted interventions and more trustworthy systems.

---

### Self-Corrected Image Generation with Explainable Latent Rewards

Authors: Yinyi Luo, Hrishikesh Gokhale, Marios Savvides, Jindong Wang, Shengfeng He
Published: 2026-03-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.24965v1

Despite significant progress in text-to-image generation, aligning outputs with complex prompts remains challenging, particularly for fine-grained semantics and spatial relations. This difficulty stems from the feed-forward nature of generation, which requires anticipating alignment without fully understanding the output. In contrast, evaluating generated images is more tractable. Motivated by this asymmetry, we propose xLARD, a self-correcting framework that uses multimodal large language models to guide generation through Explainable LAtent RewarDs. xLARD introduces a lightweight corrector that refines latent representations based on structured feedback from model-generated references. A key component is a differentiable mapping from latent edits to interpretable reward signals, enabling continuous latent-level guidance from non-differentiable image-level evaluations. This mechanism allows the model to understand, assess, and correct itself during generation. Experiments across diverse generation and editing tasks show that xLARD improves semantic alignment and visual fidelity while maintaining generative priors. Code is available at https://yinyiluo.github.io/xLARD/.

---

### Design Once, Deploy at Scale: Template-Driven ML Development for Large Model Ecosystems

Authors: Jiang Liu, John Martabano Landy, Yao Xuan, Swamy Muddu, Nhat Le, Munaf Sahaf, Luc Kien Hang, Rupinder Khandpour, Kevin De Angeli, Chang Yang, Shouyuan Chen, Shiblee Sadik et al.
Published: 2026-03-26
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.24963v3

Modern computational advertising platforms typically rely on recommendation systems to predict user responses, such as click-through rates, conversion rates, and other optimization events. To support a wide variety of product surfaces and advertiser goals, these platforms frequently maintain an extensive ecosystem of machine learning (ML) models. However, operating at this scale creates significant development and efficiency challenges. Substantial engineering effort is required to regularly refresh ML models and propagate new techniques, which results in long latencies when deploying ML innovations across the ecosystem. We present a large-scale empirical study comparing model performance, efficiency, and ML technique propagation between a standardized model-building approach and independent per-model optimization in recommendation systems. To facilitate this standardization, we propose the Standard Model Template (SMT) -- a framework that generates high-performance models adaptable to diverse data distributions and optimization events. By utilizing standardized, composable ML model components, SMT reduces technique propagation complexity from $O(n \cdot 2^k)$ to $O(n + k)$ where $n$ is the number of models and $k$ the number of techniques. Evaluating an extensive suite of models over four global development cycles within Meta's production ads ranking ecosystem, our results demonstrate: (1) a 0.63% average improvement in cross-entropy at neutral serving capacity, (2) a 92% reduction in per-model iteration engineering time, and (3) a $6.3\times$ increase in technique-model pair adoption throughput. These findings challenge the conventional wisdom that diverse optimization goals inherently require diversified ML model design.

---

### Can MLLMs Read Students' Minds? Unpacking Multimodal Error Analysis in Handwritten Math

Authors: Dingjie Song, Tianlong Xu, Yi-Fan Zhang, Hang Li, Zhiling Yan, Xing Fan, Haoyang Li, Lichao Sun, Qingsong Wen
Published: 2026-03-26
Categories: cs.AI, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2603.24961v1

Assessing student handwritten scratchwork is crucial for personalized educational feedback but presents unique challenges due to diverse handwriting, complex layouts, and varied problem-solving approaches. Existing educational NLP primarily focuses on textual responses and neglects the complexity and multimodality inherent in authentic handwritten scratchwork. Current multimodal large language models (MLLMs) excel at visual reasoning but typically adopt an "examinee perspective", prioritizing generating correct answers rather than diagnosing student errors. To bridge these gaps, we introduce ScratchMath, a novel benchmark specifically designed for explaining and classifying errors in authentic handwritten mathematics scratchwork. Our dataset comprises 1,720 mathematics samples from Chinese primary and middle school students, supporting two key tasks: Error Cause Explanation (ECE) and Error Cause Classification (ECC), with seven defined error types. The dataset is meticulously annotated through rigorous human-machine collaborative approaches involving multiple stages of expert labeling, review, and verification. We systematically evaluate 16 leading MLLMs on ScratchMath, revealing significant performance gaps relative to human experts, especially in visual recognition and logical reasoning. Proprietary models notably outperform open-source models, with large reasoning models showing strong potential for error explanation. All evaluation data and frameworks are publicly available to facilitate further research.

---

### Toward domain-specific machine translation and quality estimation systems

Authors: Javad Pourmostafa Roshan Sharami
Published: 2026-03-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.24955v1

Machine Translation (MT) and Quality Estimation (QE) perform well in general domains but degrade under domain mismatch. This dissertation studies how to adapt MT and QE systems to specialized domains through a set of data-focused contributions. Chapter 2 presents a similarity-based data selection method for MT. Small, targeted in-domain subsets outperform much larger generic datasets and reach strong translation quality at lower computational cost. Chapter 3 introduces a staged QE training pipeline that combines domain adaptation with lightweight data augmentation. The method improves performance across domains, languages, and resource settings, including zero-shot and cross-lingual cases. Chapter 4 studies the role of subword tokenization and vocabulary in fine-tuning. Aligned tokenization-vocabulary setups lead to stable training and better translation quality, while mismatched configurations reduce performance. Chapter 5 proposes a QE-guided in-context learning method for large language models. QE models select examples that improve translation quality without parameter updates and outperform standard retrieval methods. The approach also supports a reference-free setup, reducing reliance on a single reference set. These results show that domain adaptation depends on data selection, representation, and efficient adaptation strategies. The dissertation provides methods for building MT and QE systems that perform reliably in domain-specific settings.

---

### Select, Hypothesize and Verify: Towards Verified Neuron Concept Interpretation

Authors: ZeBin Ji, Yang Hu, Xiuli Bi, Bo Liu, Bin Xiao
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24953v1

It is essential for understanding neural network decisions to interpret the functionality (also known as concepts) of neurons. Existing approaches describe neuron concepts by generating natural language descriptions, thereby advancing the understanding of the neural network's decision-making mechanism. However, these approaches assume that each neuron has well-defined functions and provides discriminative features for neural network decision-making. In fact, some neurons may be redundant or may offer misleading concepts. Thus, the descriptions for such neurons may cause misinterpretations of the factors driving the neural network's decisions. To address the issue, we introduce a verification of neuron functions, which checks whether the generated concept highly activates the corresponding neuron. Furthermore, we propose a Select-Hypothesize-Verify framework for interpreting neuron functionality. This framework consists of: 1) selecting activation samples that best capture a neuron's well-defined functional behavior through activation-distribution analysis; 2) forming hypotheses about concepts for the selected neurons; and 3) verifying whether the generated concepts accurately reflect the functionality of the neuron. Extensive experiments show that our method produces more accurate neuron concepts. Our generated concepts activate the corresponding neurons with a probability approximately 1.5 times that of the current state-of-the-art method.

---

### Shopping with a Platform AI Assistant: Who Adopts, When in the Journey, and What For

Authors: Se Yan, Han Zhong, Zemin, Zhong, Wenyu Zhou
Published: 2026-03-26
Categories: cs.AI, econ.GN
arXiv: https://arxiv.org/abs/2603.24947v1

This paper provides some of the first large-scale descriptive evidence on how consumers adopt and use platform-embedded shopping AI in e-commerce. Using data on 31 million users of Ctrip, China's largest online travel platform, we study "Wendao," an LLM-based AI assistant integrated into the platform. We document three empirical regularities. First, adoption is highest among older consumers, female users, and highly engaged existing users, reversing the younger, male-dominated profile commonly documented for general-purpose AI tools. Second, AI chat appears in the same broad phase of the purchase journey as traditional search and well before order placement; among journeys containing both chat and search, the most common pattern is interleaving, with users moving back and forth between the two modalities. Third, consumers disproportionately use the assistant for exploratory, hard-to-keyword tasks: attraction queries account for 42% of observed chat requests, and chat intent varies systematically with both the timing of chat relative to search and the category of products later purchased within the same journey. These findings suggest that embedded shopping AI functions less as a substitute for conventional search than as a complementary interface for exploratory product discovery in e-commerce.

---

### MobileDev-Bench: A Benchmark for Issue Resolution in Mobile Application Development

Authors: Moshood A. Fakorede, Krishna Upadhyay, A. B. Siddique, Umar Farooq
Published: 2026-03-26
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2603.24946v2

Large language models (LLMs) have shown strong performance on automated software engineering tasks, yet existing benchmarks focus primarily on library-style repositories, leaving mobile application development largely unexplored despite its framework-specific build systems, heterogeneous artifact types, and coordinated multi-file fix requirements. We introduce MobileDev-Bench, a benchmark comprising 407 real-world issue-resolution tasks collected from 19 production mobile applications spanning Android Native (Java/Kotlin), React Native (TypeScript), and Flutter (Dart). Each task pairs a verified developer-reported issue with executable test patches, enabling fully automated validation of model-generated fixes within mobile build environments. The benchmark exhibits substantially greater patch complexity than prior benchmarks: fixes modify 12.9 files and 334.6 lines on average, and 41% of instances require coordinated changes across multiple artifact types, such as source, build configuration, and resource files. Evaluation of four frontier LLMs (Claude Sonnet 4.5, Qwen3-Coder, GPT-5.2, and Gemini 2.5 Flash) yields end-to-end resolution rates of only 3.23% - 4.23% under automated retrieval and at most 5.69% under oracle retrieval, well below resolution rates reported on existing benchmarks. We release MobileDev-Bench with task instances, an evaluation harness, and containerized environments to support reproducible research on AI-assisted mobile application development.

---

### FinMCP-Bench: Benchmarking LLM Agents for Real-World Financial Tool Use under the Model Context Protocol

Authors: Jie Zhu, Yimin Tian, Boyang Li, Kehao Wu, Zhongzhi Liang, Junhui Li, Xianyin Zhang, Lifan Guo, Feng Chen, Yong Liu, Chi Zhang
Published: 2026-03-26
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.24943v1

This paper introduces \textbf{FinMCP-Bench}, a novel benchmark for evaluating large language models (LLMs) in solving real-world financial problems through tool invocation of financial model context protocols. FinMCP-Bench contains 613 samples spanning 10 main scenarios and 33 sub-scenarios, featuring both real and synthetic user queries to ensure diversity and authenticity. It incorporates 65 real financial MCPs and three types of samples, single tool, multi-tool, and multi-turn, allowing evaluation of models across different levels of task complexity. Using this benchmark, we systematically assess a range of mainstream LLMs and propose metrics that explicitly measure tool invocation accuracy and reasoning capabilities. FinMCP-Bench provides a standardized, practical, and challenging testbed for advancing research on financial LLM agents.

---

### BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation

Authors: Yasong Dai, Zeeshan Hayder, David Ahmedt-Aristizabal, Hongdong Li
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24942v1

Recent diffusion and flow matching models have demonstrated strong capabilities in image generation and editing by progressively removing noise through iterative sampling. While this enables flexible inversion for semantic-preserving edits, few-step sampling regimes suffer from poor forward process approximation, leading to degraded editing quality. Existing few-step inversion methods often rely on pretrained generators and auxiliary modules, limiting scalability and generalization across different architectures. To address these limitations, we propose BiFM (Bidirectional Flow Matching), a unified framework that jointly learns generation and inversion within a single model. BiFM directly estimates average velocity fields in both ``image $\to$ noise" and ``noise $\to$ image" directions, constrained by a shared instantaneous velocity field derived from either predefined schedules or pretrained multi-step diffusion models. Additionally, BiFM introduces a novel training strategy using continuous time-interval supervision, stabilized by a bidirectional consistency objective and a lightweight time-interval embedding. This bidirectional formulation also enables one-step inversion and can integrate seamlessly into popular diffusion and flow matching backbones. Across diverse image editing and generation tasks, BiFM consistently outperforms existing few-step approaches, achieving superior performance and editability.

---

### Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models

Authors: Peiju Liu, Jinming Liu, Xipeng Qiu, Xuanjing Huang
Published: 2026-03-26
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2603.24941v1

Vision-Language-Action (VLA) models excel in robotic manipulation but suffer from significant inference latency due to processing dense visual tokens. Existing token reduction methods predominantly rely on attention magnitude as a static selection. In this work, we challenge this assumption, revealing that high-attention tokens are task-dependent and can even degrade policy performance. To address this, we introduce \textbf{TIES} (\textbf{T}au-guided \textbf{I}nter-layer \textbf{E}fficient \textbf{S}election), a dynamic framework guided by inter-layer token ranking consistency. By adaptively balancing attention magnitude with ranking consistency, TIES ensures robust token selection without requiring additional training. On the CogACT + SIMPLER benchmark, TIES improves average success rates by 6\% while reducing token usage by 78\%, and demonstrate strong generalization across diverse decoders and benchmarks.

---

### Evaluating adaptive and generative AI-based feedback and recommendations in a knowledge-graph-integrated programming learning system

Authors: Lalita Na Nongkhai, Jingyun Wang, Adam Wynn, Takahiko Mendori
Published: 2026-03-26
Categories: cs.PL, cs.AI
arXiv: https://arxiv.org/abs/2603.24940v1

This paper introduces the design and development of a framework that integrates a large language model (LLM) with a retrieval-augmented generation (RAG) approach leveraging both a knowledge graph and user interaction history. The framework is incorporated into a previously developed adaptive learning support system to assess learners' code, generate formative feedback, and recommend exercises. Moerover, this study examines learner preferences across three instructional modes; adaptive, Generative AI (GenAI), and hybrid GenAI-adaptive. An experimental study was conducted to compare the learning performance and perception of the learners, and the effectiveness of these three modes using four key log features derived from 4956 code submissions across all experimental groups. The analysis results show that learners receiving feedback from GenAI modes had significantly more correct code and fewer code submissions missing essential programming logic than those receiving feedback from adaptive mode. In particular, the hybrid GenAI-adaptive mode achieved the highest number of correct submissions and the fewest incorrect or incomplete attempts, outperforming both the adaptive-only and GenAI-only modes. Questionnaire responses further indicated that GenAI-generated feedback was widely perceived as helpful, while all modes were rated positively for ease of use and usefulness. These results suggest that the hybrid GenAI-adaptive mode outperforms the other two modes across all measured log features.

---

### Infinite Gaze Generation for Videos with Autoregressive Diffusion

Authors: Jenna Kang, Colin Groth, Tong Wu, Finley Torrens, Patsorn Sangkloy, Gordon Wetzstein, Qi Sun
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24938v1

Predicting human gaze in video is fundamental to advancing scene understanding and multimodal interaction. While traditional saliency maps provide spatial probability distributions and scanpaths offer ordered fixations, both abstractions often collapse the fine-grained temporal dynamics of raw gaze. Furthermore, existing models are typically constrained to short-term windows ($\approx$ 3-5s), failing to capture the long-range behavioral dependencies inherent in real-world content. We present a generative framework for infinite-horizon raw gaze prediction in videos of arbitrary length. By leveraging an autoregressive diffusion model, we synthesize gaze trajectories characterized by continuous spatial coordinates and high-resolution timestamps. Our model is conditioned on a saliency-aware visual latent space. Quantitative and qualitative evaluations demonstrate that our approach significantly outperforms existing approaches in long-range spatio-temporal accuracy and trajectory realism.

---

### TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization

Authors: Xuepeng Jing, Wenhuan Lu, Hao Meng, Zhizhi Yu, Jianguo Wei
Published: 2026-03-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2603.24936v2

Human trajectory forecasting is important for intelligent multimedia systems operating in visually complex environments, such as autonomous driving and crowd surveillance. Although Conditional Flow Matching (CFM) has shown strong ability in modeling trajectory distributions from spatio-temporal observations, existing approaches still focus primarily on supervised fitting, which may leave social norms and scene constraints insufficiently reflected in generated trajectories. To address this issue, we propose TIGFlow-GRPO, a two-stage generative approach that aligns flow-based trajectory generation with behavioral rules. In the first stage, we build a CFM-based predictor with a Trajectory-Interaction-Graph (TIG) module to model fine-grained visual-spatial interactions and strengthen context encoding. This stage captures both agent-agent and agent-scene relations more effectively, providing more informative conditional features for subsequent alignment. In the second stage, we perform Flow-GRPO post-training, where deterministic flow rollout is reformulated as stochastic ODE-to-SDE sampling to enable trajectory exploration, and a composite reward combines view-aware social compliance with map-aware physical feasibility. By evaluating trajectories explored through SDE rollout, GRPO progressively steers multimodal predictions toward behaviorally plausible futures. Experiments on the ETH/UCY and SDD datasets show that TIGFlow-GRPOimproves forecasting accuracy and long-horizon stability while generatingtrajectories that are more socially compliant and physically feasible.These results suggest that the proposed approach provides an effective way to connectflow-based trajectory modeling with behavior-aware alignment in dynamic multimedia environments.

---

### CVA: Context-aware Video-text Alignment for Video Temporal Grounding

Authors: Sungho Moon, Seunghun Lee, Jiwan Seo, Sunghoon Im
Published: 2026-03-26
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2603.24934v1

We propose Context-aware Video-text Alignment (CVA), a novel framework to address a significant challenge in video temporal grounding: achieving temporally sensitive video-text alignment that remains robust to irrelevant background context. Our framework is built on three key components. First, we propose Query-aware Context Diversification (QCD), a new data augmentation strategy that ensures only semantically unrelated content is mixed in. It builds a video-text similarity-based pool of replacement clips to simulate diverse contexts while preventing the ``false negative" caused by query-agnostic mixing. Second, we introduce the Context-invariant Boundary Discrimination (CBD) loss, a contrastive loss that enforces semantic consistency at challenging temporal boundaries, making their representations robust to contextual shifts and hard negatives. Third, we introduce the Context-enhanced Transformer Encoder (CTE), a hierarchical architecture that combines windowed self-attention and bidirectional cross-attention with learnable queries to capture multi-scale temporal context. Through the synergy of these data-centric and architectural enhancements, CVA achieves state-of-the-art performance on major VTG benchmarks, including QVHighlights and Charades-STA. Notably, our method achieves a significant improvement of approximately 5 points in Recall@1 (R1) scores over state-of-the-art methods, highlighting its effectiveness in mitigating false negatives.

---

### Decoding Market Emotions in Cryptocurrency Tweets via Predictive Statement Classification with Machine Learning and Transformers

Authors: Moein Shahiki Tash, Zahra Ahani, Mohim Tash, Mostafa Keikhay Farzaneh, Ari Y. Barrera-Animas, Olga Kolesnikova
Published: 2026-03-26
Categories: cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2603.24933v1

The growing prominence of cryptocurrencies has triggered widespread public engagement and increased speculative activity, particularly on social media platforms. This study introduces a novel classification framework for identifying predictive statements in cryptocurrency-related tweets, focusing on five popular cryptocurrencies: Cardano, Matic, Binance, Ripple, and Fantom. The classification process is divided into two stages: Task 1 involves binary classification to distinguish between Predictive and Non-Predictive statements. Tweets identified as Predictive proceed to Task 2, where they are further categorized as Incremental, Decremental, or Neutral. To build a robust dataset, we combined manual and GPT-based annotation methods and utilized SenticNet to extract emotion features corresponding to each prediction category. To address class imbalance, GPT-generated paraphrasing was employed for data augmentation. We evaluated a wide range of machine learning, deep learning, and transformer-based models across both tasks. The results show that GPT-based balancing significantly enhanced model performance, with transformer models achieving the highest F1-score in Task 1, while traditional machine learning models performed best in Task 2. Furthermore, our emotion analysis revealed distinct emotional patterns associated with each prediction category across the different cryptocurrencies.

---

### LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics

Authors: Farhan Ahmed, Yuya Jeremy Ong, Chad DeLuca
Published: 2026-03-26
Categories: cs.AI, cs.CL, cs.IT
arXiv: https://arxiv.org/abs/2603.24929v2

Understanding and quantifying uncertainty in large language model (LLM) outputs is critical for reliable deployment. However, traditional evaluation approaches provide limited insight into model confidence at individual token positions during generation. To address this issue, we introduce LogitScope, a lightweight framework for analyzing LLM uncertainty through token-level information metrics computed from probability distributions. By measuring metrics such as entropy and varentropy at each generation step, LogitScope reveals patterns in model confidence, identifies potential hallucinations, and exposes decision points where models exhibit high uncertainty, all without requiring labeled data or semantic interpretation. We demonstrate LogitScope's utility across diverse applications including uncertainty quantification, model behavior analysis, and production monitoring. The framework is model-agnostic, computationally efficient through lazy evaluation, and compatible with any HuggingFace model, enabling both researchers and practitioners to inspect LLM behavior during inference.

---

### GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation

Authors: Ruizhong Miao, Yuying Wang, Rongguang Wang, Chenyang Li, Tao Sheng, Sujith Ravi, Dan Roth
Published: 2026-03-26
Categories: cs.LG, cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2603.24925v3

Semantic search in retrieval-augmented generation (RAG) systems is often insufficient for complex information needs, particularly when relevant evidence is scattered across multiple sources, because it may fail to retrieve the complete set of evidence. Existing approaches to addressing this problem either rely on iterative agentic retrieval, which can be computationally inefficient, or maintain additional structures such as knowledge graphs, which introduce storage and maintenance overhead. In this paper, we propose GraphER, a graph-based enrichment and reranking framework that (1) leverages the organizational structure of data to capture proximity relationships beyond semantic similarity, (2) constructs a graph at query time based on these proximities, and (3) applies graph-based ranking to surface the top candidate documents. Experiments across table retrieval, multi-hop retrieval, and long-document retrieval benchmarks demonstrate consistent improvements in terms of retrieval completeness. Additionally, GraphER requires no additional graph infrastructure and integrates seamlessly with standard vector stores. The framework is retriever-agnostic, supports multiple forms of proximity, and introduces minimal query-time latency.

---

### Estimating near-verbatim extraction risk in language models with decoding-constrained beam search

Authors: A. Feder Cooper, Mark A. Lemley, Christopher De Sa, Lea Duesterwald, Allison Casasola, Jamie Hayes, Katherine Lee, Daniel E. Ho, Percy Liang
Published: 2026-03-26
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2603.24917v3

Recent work shows that standard greedy-decoding extraction methods for quantifying memorization in LLMs miss how extraction risk varies across sequences. Probabilistic extraction -- computing the probability of generating a target suffix given a prefix under a decoding scheme -- addresses this, but is tractable only for verbatim memorization, missing near-verbatim instances that pose similar privacy and copyright risks. Quantifying near-verbatim extraction risk is expensive: the set of near-verbatim suffixes is combinatorially large, and reliable Monte Carlo (MC) estimation can require ~100,000 samples per sequence. To mitigate this cost, we introduce decoding-constrained beam search, which yields deterministic lower bounds on near-verbatim extraction risk at a cost comparable to ~20 MC samples per sequence. Across experiments, our approach surfaces information invisible to verbatim methods: many more extractable sequences, substantially larger per-sequence extraction mass, and patterns in how near-verbatim extraction risk manifests across model sizes and types of text.

---

### Once-for-All Channel Mixers (HYPERTINYPW): Generative Compression for TinyML

Authors: Yassien Shaalan
Published: 2026-03-26
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2603.24916v1

Deploying neural networks on microcontrollers is constrained by kilobytes of flash and SRAM, where 1x1 pointwise (PW) mixers often dominate memory even after INT8 quantization across vision, audio, and wearable sensing. We present HYPER-TINYPW, a compression-as-generation approach that replaces most stored PW weights with generated weights: a shared micro-MLP synthesizes PW kernels once at load time from tiny per-layer codes, caches them, and executes them with standard integer operators. This preserves commodity MCU runtimes and adds only a one-off synthesis cost; steady-state latency and energy match INT8 separable CNN baselines. Enforcing a shared latent basis across layers removes cross-layer redundancy, while keeping PW1 in INT8 stabilizes early, morphology-sensitive mixing. We contribute (i) TinyML-faithful packed-byte accounting covering generator, heads/factorization, codes, kept PW1, and backbone; (ii) a unified evaluation with validation-tuned t* and bootstrap confidence intervals; and (iii) a deployability analysis covering integer-only inference and boot versus lazy synthesis. On three ECG benchmarks (Apnea-ECG, PTB-XL, MIT-BIH), HYPER-TINYPW shifts the macro-F1 versus flash Pareto frontier: at about 225 kB it matches a roughly 1.4 MB CNN while being 6.31x smaller (84.15% fewer bytes), retaining at least 95% of large-model macro-F1. Under 32-64 kB budgets it sustains balanced detection where compact baselines degrade. The mechanism applies broadly to other 1D biosignals, on-device speech, and embedded sensing tasks where per-layer redundancy dominates, indicating a wider role for compression-as-generation in resource-constrained ML systems. Beyond ECG, HYPER-TINYPW transfers to TinyML audio: on Speech Commands it reaches 96.2% test accuracy (98.2% best validation), supporting broader applicability to embedded sensing workloads where repeated linear mixers dominate memory.

---

### Shaping the Future of Mathematics in the Age of AI

Authors: Johan Commelin, Mateja Jamnik, Rodrigo Ochigame, Lenny Taelman, Akshay Venkatesh
Published: 2026-03-26
Categories: math.HO, cs.AI
arXiv: https://arxiv.org/abs/2603.24914v2

Artificial intelligence is transforming mathematics at a speed and scale that demand active engagement from the mathematical community. We examine five areas where this transformation is particularly pressing: values, practice, teaching, technology, and ethics. We offer recommendations on safeguarding our intellectual autonomy, rethinking our practice, broadening curricula, building academically oriented infrastructure, and developing shared ethical principles - with the aim of ensuring that the future of mathematics is shaped by the community itself.

---

### ICTPolarReal: A Polarized Reflection and Material Dataset of Real World Objects

Authors: Jing Yang, Krithika Dharanikota, Emily Jia, Haiwei Chen, Yajie Zhao
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24912v1

Accurately modeling how real-world materials reflect light remains a core challenge in inverse rendering, largely due to the scarcity of real measured reflectance data. Existing approaches rely heavily on synthetic datasets with simplified illumination and limited material realism, preventing models from generalizing to real-world images. We introduce a large-scale polarized reflection and material dataset of real-world objects, captured with an 8-camera, 346-light Light Stage equipped with cross/parallel polarization. Our dataset spans 218 everyday objects across five acquisition dimensions-multiview, multi-illumination, polarization, reflectance separation, and material attributes-yielding over 1.2M high-resolution images with diffuse-specular separation and analytically derived diffuse albedo, specular albedo, and surface normals. Using this dataset, we train and evaluate state-of-the-art inverse and forward rendering models on intrinsic decomposition, relighting, and sparse-view 3D reconstruction, demonstrating significant improvements in material separation, illumination fidelity, and geometric consistency. We hope that our work can establish a new foundation for physically grounded material understanding and enable real-world generalization beyond synthetic training regimes. Project page: https://jingyangcarl.github.io/ICTPolarReal/

---

### Associative Memory using Attribute-Specific Neuron Groups-2: Learning and Sequential Associative Recall between Cue Neurons for different Cue Balls

Authors: Hiroshi Inazawa
Published: 2026-03-26
Categories: cs.NE
arXiv: https://arxiv.org/abs/2603.24910v1

This paper introduces a neural network model that learns multiple attributes as images and performs associated, sequential recall of the learned memories. Briefly, the model presented here is an associative memory model that extends previous models (1) by increasing the number of attributes. In the real world, memory recall generates a chain of associations consisting of complex and diverse data with meaningful relations. However, because this experimental system is designed to implement and verify the processing operations behind such operations, we believe it is not a problem if the associative memory (i.e., the chain of data) is composed of attributes that do not necessarily have clear relation with each other. Accordingly, the attribute-processing systems prepared in this study consist of five types: the C.CB-RN system for processing color attributes, the S.CB-RN system for shape attributes, and the V.CB-RN system for size attributes, as adopted in our previous paper (1), as well as the SV.CB-RN system for processing the names of the world's most beautiful scenery (spectacular view names) and the CN.CB-RN system for processing constellation names. As before, the data presented to each CB-RN system are represented as image patterns using QR codes (2). These five types of CB-RN systems will be combined and trained with QR code pattern images of the attribute elements of each system. After that, when a pattern image of an attribute element is presented to any of the CB-RN systems, a mechanism will be constructed in which a chain (associative) recall of pattern images of related attribute elements in the other trained systems will be generated.

---

### Integrated Multi-Drone Task Allocation, Sequencing, and Optimal Trajectory Generation in Obstacle-Rich 3D Environments

Authors: Yunes Alqudsi, Murat Makaraci
Published: 2026-03-26
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2603.24908v1

Coordinating teams of aerial robots in cluttered three-dimensional (3D) environments requires a principled integration of discrete mission planning-deciding which robot serves which goals and in what order -- with continuous-time trajectory synthesis that enforces collision avoidance and dynamic feasibility. This paper introduces IMD-TAPP (Integrated Multi-Drone Task Allocation and Path Planning), an end-to-end framework that jointly addresses multi-goal allocation, tour sequencing, and safe trajectory generation for quadrotor teams operating in obstacle-rich spaces. IMD--TAPP first discretizes the workspace into a 3D navigation graph and computes obstacle-aware robot-to-goal and goal-to-goal travel costs via graph-search-based pathfinding. These costs are then embedded within an Injected Particle Swarm Optimization (IPSO) scheme, guided by multiple linear assignment, to efficiently explore coupled assignment/ordering alternatives and to minimize mission makespan. Finally, the resulting waypoint tours are transformed into time-parameterized minimum-snap trajectories through a generation-and-optimization routine equipped with iterative validation of obstacle clearance and inter-robot separation, triggering re-planning when safety margins are violated. Extensive MATLAB simulations across cluttered 3D scenarios demonstrate that IMD--TAPP consistently produces dynamically feasible, collision-free trajectories while achieving competitive completion times. In a representative case study with two drones serving multiple goals, the proposed approach attains a minimum mission time of 136~s while maintaining the required safety constraints throughout execution.

---

### On the Foundations of Trustworthy Artificial Intelligence

Authors: TJ Dunham
Published: 2026-03-26
Categories: cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2603.24904v1

We prove that platform-deterministic inference is necessary and sufficient for trustworthy AI. We formalize this as the Determinism Thesis and introduce trust entropy to quantify the cost of non-determinism, proving that verification failure probability equals 1 - 2^{-H_T} exactly. We prove a Determinism-Verification Collapse: verification under determinism requires O(1) hash comparison; without it, the verifier faces an intractable membership problem. IEEE 754 floating-point arithmetic fundamentally violates the determinism requirement. We resolve this by constructing a pure integer inference engine that achieves bitwise identical output across ARM and x86. In 82 cross-architecture tests on models up to 6.7B parameters, we observe zero hash mismatches. Four geographically distributed nodes produce identical outputs, verified by 356 on-chain attestation transactions. Every major trust property of AI systems (fairness, robustness, privacy, safety, alignment) presupposes platform determinism. Our system, 99,000 lines of Rust deployed across three continents, establishes that AI trust is a question of arithmetic.

---

### Self-Supervised Learning for Knee Osteoarthritis: Diagnostic Limitations and Prognostic Value of Hospital Data

Authors: Haresh Rengaraj Rajamohan, Yuxuan Chen, Kyunghyun Cho, Cem M. Deniz
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24903v2

This study assesses whether self-supervised learning (SSL) improves knee osteoarthritis (OA) modeling for diagnosis and prognosis relative to ImageNet-pretrained initialization. We compared (i) image-only SSL pretrained on knee radiographs from the OAI, MOST, and NYU cohorts, and (ii) multimodal image-text SSL pretrained on hospital knee radiographs paired with radiologist impressions. For diagnostic Kellgren-Lawrence (KL) grade prediction, SSL yielded mixed results. While image-only SSL improved accuracy during linear probing (frozen encoder), it did not outperform ImageNet pretraining during full fine-tuning. Similarly, multimodal SSL failed to improve grading performance. A likely explanation is mismatch between the hospital pretraining corpus and the downstream diagnostic task: the hospital image-text dataset was restricted to knees from patients with clinically identified OA in routine care, rather than a cohort spanning the full spectrum from normal to severe disease needed for balanced KL grading. In addition, radiology impressions do not explicitly encode KL grade, limiting supervision for learning KL-specific decision boundaries. In contrast, this same multimodal initialization significantly improved prognostic modeling. It outperformed ImageNet baselines in predicting 4-year structural incidence and progression, including on external validation (MOST AUROC: 0.701 vs. 0.599 at 10\% labeled data). Overall, these results suggest that our hospital image-text data may be less effective for diagnostic grading when the pretraining cohort is limited to OA knees, but can provide a strong signal for prognostic modeling when the downstream task is better aligned with the pretraining data distribution.

---

### Sovereign AI at the Front Door of Care: A Physically Unidirectional Architecture for Secure Clinical Intelligence

Authors: Vasu Srinivasan, Dhriti Vasu
Published: 2026-03-26
Categories: cs.CR, cs.AI, cs.NI
arXiv: https://arxiv.org/abs/2603.24898v1

We present a Sovereign AI architecture for clinical triage in which all inference is performed on-device and inbound data is delivered via a physically unidirectional channel, implemented using receive-only broadcast infrastructure or certified hardware data diodes, with no return path to any external network. This design removes the network-mediated attack surface by construction, rather than attempting to secure it through software controls. The system performs conversational symptom intake, integrates device-captured vitals, and produces structured, triage-aligned clinical records at the point of care. We formalize the security properties of receiver-side unidirectionality and show that the architecture is transport-agnostic across broadcast and diode-enforced deployments. We further analyze threat models, enforcement mechanisms, and deployment configurations, demonstrating how physical one-way data flow enables high-assurance operation in both resource-constrained and high-risk environments. This work positions physically unidirectional channels as a foundational primitive for sovereign, on-device clinical intelligence at the front door of care.

---

### SurgPhase: Time efficient pituitary tumor surgery phase recognition via an interactive web platform

Authors: Yan Meng, Jack Cook, X. Y. Han, Kaan Duman, Shauna Otto, Dhiraj Pangal, Jonathan Chainey, Ruth Lau, Margaux Masson-Forsythe, Daniel A. Donoho, Danielle Levy, Gabriel Zada et al.
Published: 2026-03-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.24897v1

Accurate surgical phase recognition is essential for analyzing procedural workflows, supporting intraoperative decision-making, and enabling data-driven improvements in surgical education and performance evaluation. In this work, we present a comprehensive framework for phase recognition in pituitary tumor surgery (PTS) videos, combining self-supervised representation learning, robust temporal modeling, and scalable data annotation strategies. Our method achieves 90\% accuracy on a held-out test set, outperforming current state-of-the-art approaches and demonstrating strong generalization across variable surgical cases. A central contribution of this work is the integration of a collaborative online platform designed for surgeons to upload surgical videos, receive automated phase analysis, and contribute to a growing dataset. This platform not only facilitates large-scale data collection but also fosters knowledge sharing and continuous model improvement. To address the challenge of limited labeled data, we pretrain a ResNet-50 model using the self-supervised framework on 251 unlabeled PTS videos, enabling the extraction of high-quality feature representations. Fine-tuning is performed on a labeled dataset of 81 procedures using a modified training regime that incorporates focal loss, gradual layer unfreezing, and dynamic sampling to address class imbalance and procedural variability.

---

### LogSigma at SemEval-2026 Task 3: Uncertainty-Weighted Multitask Learning for Dimensional Aspect-Based Sentiment Analysis

Authors: Baraa Hikal, Jonas Becker, Bela Gipp
Published: 2026-03-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.24896v1

This paper describes LogSigma, our system for SemEval-2026 Task 3: Dimensional Aspect-Based Sentiment Analysis (DimABSA). Unlike traditional Aspect-Based Sentiment Analysis (ABSA), which predicts discrete sentiment labels, DimABSA requires predicting continuous Valence and Arousal (VA) scores on a 1-9 scale. A central challenge is that Valence and Arousal differ in prediction difficulty across languages and domains. We address this using learned homoscedastic uncertainty, where the model learns task-specific log-variance parameters to automatically balance each regression objective during training. Combined with language-specific encoders and multi-seed ensembling, LogSigma achieves 1st place on five datasets across both tracks. The learned variance weights vary substantially across languages due to differing Valence-Arousal difficulty profiles-from 0.66x for German to 2.18x for English-demonstrating that optimal task balancing is language-dependent and cannot be determined a priori.

---

### Surrogates, Spikes, and Sparsity: Performance Analysis and Characterization of SNN Hyperparameters on Hardware

Authors: Ilkin Aliyev, Jesus Lopez, Tosiron Adegbija
Published: 2026-03-26
Categories: cs.AR, cs.AI
arXiv: https://arxiv.org/abs/2603.24891v1

Spiking Neural Networks (SNNs) offer inherent advantages for low-power inference through sparse, event-driven computation. However, the theoretical energy benefits of SNNs are often decoupled from real hardware performance due to the opaque relationship between training-time choices and inference-time sparsity. While prior work has focused on weight pruning and compression, the role of training hyperparameters -- specifically surrogate gradient functions and neuron model configurations -- in shaping hardware-level activation sparsity remains underexplored. This paper presents a workload characterization study quantifying the sensitivity of hardware latency to SNN hyperparameters. We decouple the impact of surrogate gradient functions (e.g., Fast Sigmoid, Spike Rate Escape) and neuron models (LIF, Lapicque) on classification accuracy and inference efficiency across three event-based vision datasets: DVS128-Gesture, N-MNIST, and DVS-CIFAR10. Our analysis reveals that standard accuracy metrics are poor predictors of hardware efficiency. While Fast Sigmoid achieves the highest accuracy on DVS-CIFAR10, Spike Rate Escape reduces inference latency by up to 12.2% on DVS128-Gesture with minimal accuracy trade-offs. We also demonstrate that neuron model selection is as critical as parameter tuning; transitioning from LIF to Lapicque neurons yields up to 28% latency reduction. We validate on a custom cycle-accurate FPGA-based SNN instrumentation platform, showing that sparsity-aware hyperparameter selection can improve accuracy by 9.1% and latency by over 2x compared to baselines. These findings establish a methodology for predicting hardware behavior from training parameters. The RTL and reproducibility artifacts are at https://zenodo.org/records/18893738.

---

### A Deep Reinforcement Learning (DRL)-Based Transformer Method for Solving the Open Shop Scheduling Problem

Authors: Faezeh Ardali, Mwembezi A. Nyelele, Gerald M. Knapp
Published: 2026-03-25
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2606.13682v1

The open shop scheduling problem (OSSP) arises in many industrial and service settings but remains computationally challenging as the number of jobs and machines increases. While exact methods quickly become intractable, classical dispatching rules and metaheuristics may require substantial tuning to maintain solution quality at large scales. This study develops a Transformer-based scheduling policy for OSSP using an encoder-decoder architecture with multi-head attention. The model is trained on Taillard benchmark instances (4x4, 5x5, 7x7, and 10x10) using only the processing-time matrix as input and produces feasible schedules with makespans typically within 15-30% of best-known values. To evaluate scalability, the trained policy is applied without retraining to randomly generated instances from 40x40 to 100x100 and compared against classical dispatching heuristics, including SPT, LPT, MWKR, and EST. Across these large instances, the Transformer achieved average gaps of 12.89-15.12% relative to a standard lower bound. Compared with EST, the Transformer remained competitive, typically within a modest margin, while substantially outperforming SPT and LPT. These results indicate that a Transformer policy trained on small OSSP instances can generalize to substantially larger problems and provide a feature-light, learning-based alternative to classical dispatching rules.

---

### Position Paper: Post-Solve Robustness in Decision Engines: Feasible Regions and Smoothness Under Perturbations

Authors: Yi-Xiang Hu
Published: 2026-03-25
Categories: cs.AI
arXiv: https://arxiv.org/abs/2606.00002v1

Mixed-Integer Linear Programming (MILP) decision engines routinely output nominally optimal plans for high-stakes industrial systems. Yet deployment rarely matches solve-time assumptions: small perturbations in costs, demands, or resource availability can invalidate feasibility or trigger discontinuous shifts to qualitatively different solutions. We argue that this post-solve robustness gap is a missing layer in today's optimization pipelines and a missing evaluation dimension for learning-enabled decision systems. Rather than replacing robust optimization or stochastic programming, the proposed layer audits a solved incumbent and returns solver-backed evidence about how far that solution can be trusted. We formalize two central objects: (i) an $ε$-near-optimal feasible neighborhood in parameter space, capturing when an incumbent remains feasible and near-optimal under perturbations, and (ii) solution smoothness in decision space, capturing whether nearby alternatives with small combinatorial edits remain competitive. We then synthesize the most relevant partial answers from sensitivity and stability analysis, robust optimization, neighborhood search, adversarial testing, and learning-based enhancements, and articulate an agenda for a unified post-solve robustness layer. Concretely, we call for certified inner approximations around the incumbent, probabilistic robustness estimation with calibrated uncertainty, adversarial robustness margins, and learning-based prediction and explanation aligned with solver-backed verification. We conclude with a compact reporting template and evaluation protocol that would make robustness a first-class output of decision engines.

---

### Lightweight Multimodal LLM-Enabled Cost-Effective Defect Grading of Power Transmission Equipment

Authors: Tao Wang, Lipeng Zhu, Jiayong Li, Feng Gao, Siwen Liang
Published: 2026-03-25
Categories: cs.CL
arXiv: https://arxiv.org/abs/2605.28822v1

Defect grading of power transmission equipment (DGPTE) is crucial to the stability of electric energy transmission. Although existing machine learning methods exhibit strong capabilities in defect detection, they are plagued by difficulties in integrating expert experience and facing class imbalance in more refined defect grading field. To address this issue, this paper introduces a novel defect grading framework based on multimodal large language model (MLLM). Specifically, this approach maximizes the commercial MLLMs' potential of DGPTE through in-context learning and obtains the state-of-te-art (SOTA) model. By sending a secondary request to this model, a small number of chain of thought-based question-answer pairs (Q\&As) are generated, which effectively reduces the cost of manual annotation. In this way, these high-quality interpretable Q\&As are used to train Qwen3-VL-8B via Low-Rank Adaption-based supervised fine-tuning (SFT). Experimental results on three DGPTE tasks demonstrate that fine-tuning only the language model layer yields the SOTA performance. Furthermore, multi-task joint fine-tuning verifies the feasibility of handling multiple grading tasks within only a single lightweight MLLM.

---

### FaceParts: Segmentation and Editing of Gaussian Splatting

Authors: Tymoteusz Zapała, Julia Farganus, Dominik Galus, Mikołaj Czachorowski, Piotr Syga, Przemysław Spurek
Published: 2026-03-25
Categories: cs.GR, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2605.13853v1

Facial editing is an important task with applications in entertainment, virtual reality, and digital avatars. Most existing approaches rely on generative models in the 2D image domain, while in 3D the task is typically performed through labor-intensive manual editing. We propose FaceParts, a framework for unsupervised segmentation and editing of Gaussian Splatting avatars. Unlike existing 2D or mesh-assisted methods, our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision. The method integrates feature disentanglement, density-based clustering, and FLAME-anchored part transfer, enabling precise editing and cross-avatar part swapping. Experiments on the NeRSemble dataset with 11 subjects demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).

---

### Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning

Authors: Ido Sobol, Kihyuk Sohn, Yoav Blum, Egor Zakharov, Max Bluvstein, Andrea Vedaldi, Or Litany
Published: 2026-03-25
Categories: cs.GR, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2605.13852v1

We often aim to generate images that are both photorealistic and 3D-consistent, adhering to precise geometry, material, and viewpoint controls. Typically, this is achieved by fine-tuning an image generator, pre-trained on billions of real images, using renders of synthetic 3D assets, where annotations for control signals are available. While this approach can learn the desired controls, it often compromises the realism of the images due to domain gap between photographs and renders. We observe that this issue largely arises from the model learning an unintended association between the presence of control signals and the synthetic appearance of the images. To address this, we introduce Realiz3D, a lightweight framework for training diffusion models, that decouples controls and visual domain. The key idea is to explicitly learn visual domain, real or synthetic, separately from other control signals by introducing a co-variate that, fed into small residual adapters, shifts the domain. Then, the generator can be trained to gain controllability, without fitting to specific visual domain. In this way, the model can be guided to produce realistic images even when controls are applied. We enhance control transferability to the real domain by leveraging insights about roles of different layers and denoising steps in diffusion-based generators, informing new training and inference strategies that further mitigate the gap. We demonstrate the advantages of Realiz3D in tasks as text-to-multiview generation and texturing from 3D inputs, producing outputs that are 3D-consistent and photorealistic.

---

### WhatsApp Vaccine Discourse (WhaVax): An Expert-Annotated Dataset and Benchmark for Health Misinformation Detection

Authors: Jônatas H. dos Santos, Julio C. S. Reis, Philipe Melo, João F. H. Olivetti, Thales H. Silva, Matheus Gontijo Guimaraes, Glaucio de Souza, Marcos A. Gonçalves, Fabricio Benevenuto, Filipe B. B. Zanovello, Marco A. G. Rodrigues, Cristiano X. Lima
Published: 2026-03-25
Categories: cs.SI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2605.12510v1

We introduce WhaVax, a new expert-annotated dataset of vaccine-related WhatsApp messages collected from large Brazilian public groups spanning multiple pandemic years. The dataset was constructed through a rigorous, carefully designed pipeline that integrates keyword-based data collection, semantic deduplication to remove near-duplicate content, and a multi-stage annotation protocol conducted by medical specialists. This process produced a high-quality gold-standard corpus, characterized by substantial inter-annotator agreement and strong reliability for downstream analysis. Additionally, we provide a detailed characterization of WhatsApp misinformation, revealing distinctive linguistic, structural, lexical, temporal, and group-level patterns, as well as a meaningful layer of ambiguous cases that reflect the complexity of health discourse in private messaging. We also benchmark classical models, fine-tuned Small Language Models, and zero- or few-shot Large Language Models under realistic data-scarcity constraints, demonstrating that strong embeddings and LLM approaches perform competitively, while domain alignment and data availability remain critical factors. This study provides a rare, high-quality resource to support misinformation research and computational modeling in encrypted communication environments.

---

### Secure On-Premise Deployment of Open-Weights Large Language Models in Radiology: An Isolation-First Architecture with Prospective Pilot Evaluation

Authors: Sebastian Nowak, Jann-Frederick Laß, Narine Mesropyan, Babak Salam, Nico Piel, Mohammed Bahaaeldin, Wolfgang Block, Alois Martin Sprinkart, Julian Alexander Luetkens, Benjamin Wulff, Alexander Isaak
Published: 2026-03-25
Categories: cs.CY, cs.CL
arXiv: https://arxiv.org/abs/2604.22768v1

Purpose: To design, implement, evaluate, and report on the regulatory requirements of a self-hosted LLM infrastructure for radiology adhering to the principle of least privilege, emphasizing technical feasibility, network isolation, and clinical utility. Materials and Methods: The isolation-first, containerized LLM inference stack relies on strict network segmentation, host-enforced egress filtering, and active isolation monitoring preventing unauthorized external connectivity. An accompanying deployment package provides automated isolation and hardening tests. The system served the open-weights DeepSeek-R1 model via vLLM. In a one-week pilot phase, 22 residents and radiologists were free to use 10 predefined prompt-templates whenever they considered them useful in daily work. Afterward, they rated clinical utility and system stability on an 0-10 Likert scale and reported observed critical errors in model output. Results: The applied institutional governance pathway achieved approval from clinic management, compliance, data protection and information security officers for processing unanonymized PHI. The system was rated stable and user friendly during the pilot. Source text-anchored tasks, such as report corrections or simplifications, and radiology guideline recommendations received the highest utility ratings, whereas open-ended conclusion generation based on findings resulted in the highest frequency of critical errors, such as clinically relevant hallucinations or omissions. Conclusion: The proposed isolation-first on-premise architecture enabled overcoming regulatory borders, showed promising clinical utility in text-anchored tasks and is the current base to serve open-weights LLMs as an official service of a German University Hospital with over 10,000 employees. The deployment package were made publicly available (https://github.com/ukbonn/ukb-gpt).

---

### Inference Headroom Ratio: A Diagnostic and Control Framework for Inference Stability Under Constraint

Authors: Robert Reinertsen
Published: 2026-03-25
Categories: cs.AI, cs.SI
arXiv: https://arxiv.org/abs/2604.19760v1

We present a simulation-based evaluation of the Inference Headroom Ratio (IHR), a dimensionless diagnostic quantity for characterizing inference stability in constrained decision systems. IHR formalizes the relationship between a system's effective inferential capacity C and the combined uncertainty and constraint load U + K imposed by its operating environment, and is intended to capture proximity to an inference stability boundary rather than output-level performance. Across three controlled experiments, we show that IHR functions as: (1) a quantifiable risk indicator whose relationship to collapse probability follows a well-fitted logistic curve with estimated critical threshold IHR* approx. 1.19, (2) a sensitive indicator of proximity to the inference stability boundary under environmental noise, and (3) a viable control variable whose active regulation reduces system collapse rate from 79.4% to 58.7% and IHR variance by 70.4% across 300 Monte Carlo runs. These results position IHR as a prospective, system-level complement to standard performance, drift, and uncertainty metrics, enabling estimation of remaining inferential margin before overt failure in AI systems operating under distributional shift and constraint.

---

### Automated Detection of Dosing Errors in Clinical Trial Narratives: A Multi-Modal Feature Engineering Approach with LightGBM

Authors: Mohammad AL-Smadi
Published: 2026-03-25
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2604.19759v1

Clinical trials require strict adherence to medication protocols, yet dosing errors remain a persistent challenge affecting patient safety and trial integrity. We present an automated system for detecting dosing errors in unstructured clinical trial narratives using gradient boosting with comprehensive multi-modal feature engineering. Our approach combines 3,451 features spanning traditional NLP (TF-IDF, character n-grams), dense semantic embeddings (all-MiniLM-L6v2), domain-specific medical patterns, and transformer-based scores (BiomedBERT, DeBERTa-v3), used to train a LightGBM model. Features are extracted from nine complementary text fields (median 5,400 characters per sample) ensuring complete coverage across all 42,112 clinical trial narratives. On the CT-DEB benchmark dataset with severe class imbalance (4.9% positive rate), we achieve 0.8725 test ROC-AUC through 5-fold ensemble averaging (cross-validation: 0.8833 + 0.0091 AUC). Systematic ablation studies reveal that removing sentence embeddings causes the largest performance degradation (2.39%), demonstrating their critical role despite contributing only 37.07% of total feature importance. Feature efficiency analysis demonstrates that selecting the top 500-1000 features yields optimal performance (0.886-0.887 AUC), outperforming the full 3,451-feature set (0.879 AUC) through effective noise reduction. Our findings highlight the importance of feature selection as a regularization technique and demonstrate that sparse lexical features remain complementary to dense representations for specialized clinical text classification under severe class imbalance.

---

### ThermoQA: A Three-Tier Benchmark for Evaluating Thermodynamic Reasoning in Large Language Models

Authors: Kemal Düzkar
Published: 2026-03-25
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2604.19758v1

We present ThermoQA, a benchmark of 293 open-ended engineering thermodynamics problems in three tiers: property lookups (110 Q), component analysis (101 Q), and full cycle analysis (82 Q). Ground truth is computed programmatically from CoolProp 7.2.0, covering water, R-134a, and variable-cp air. Six frontier LLMs are evaluated across three independent runs each. The composite leaderboard is led by Claude Opus 4.6 (94.1%), GPT-5.4 (93.1%), and Gemini 3.1 Pro (92.5%). Cross-tier degradation ranges from 2.8 pp (Opus) to 32.5 pp (MiniMax), confirming that property memorization does not imply thermodynamic reasoning. Supercritical water, R-134a refrigerant, and combined-cycle gas turbine analysis serve as natural discriminators with 40-60 pp performance spreads. Multi-run sigma ranges from +/-0.1% to +/-2.5%, quantifying reasoning consistency as a distinct evaluation axis. Dataset and code are open-source at https://huggingface.co/datasets/olivenet/thermoqa

---