# Research Papers — 2026-04 · bundle page 146 of 233 > Full-text markdown of papers #7251–7300 of 11612 published in 2026-04, newest first. AI-readable mirrors of the full 11612-paper 2026-04 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-04/page/146 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/145.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/147.md) ### VeriSim: A Configurable Framework for Evaluating Medical AI Under Realistic Patient Noise Authors: Sina Mansouri, Mohit Marvania, Vibhavari Ashok Shihorkar, Han Ngoc Tran, Kazhal Shafiei, Mehrdad Fazli, Yikuan Li, Ziwei Zhu Published: 2026-04-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10441v1 Medical large language models (LLMs) achieve impressive performance on standardized benchmarks, yet these evaluations fail to capture the complexity of real clinical encounters where patients exhibit memory gaps, limited health literacy, anxiety, and other communication barriers. We introduce VeriSim, a truth-preserving patient simulation framework that injects controllable, clinically evidence-grounded noise into patient responses while maintaining strict adherence to medical ground truth through a hybrid UMLS-LLM verification mechanism. Our framework operationalizes six noise dimensions derived from peer-reviewed medical communication literature, capturing authentic clinical phenomena such as patient recall limitations, health literacy barriers, and stigma-driven non-disclosure. Experiments across seven open-weight LLMs reveal that all models degrade significantly under realistic patient noise, with diagnostic accuracy dropping 15-25% and conversation length increasing 34-55%. Notably, smaller models (7B) show 40% greater degradation than larger models (70B+), while medical fine-tuning on standard corpora provides limited robustness benefits against patient communication noise. Evaluation by board-certified clinicians demonstrates high-quality simulation with strong inter-annotator agreement (kappa > 0.80), while LLM-as-a-Judge serves as a validated auxiliary evaluator achieving comparable reliability for scalable assessment. Our results highlight a critical Sim-to-Real gap in current medical AI. We release VeriSim as an open-source noise-injection framework, establishing a rigorous testbed for evaluating clinical robustness. --- ### Removing Motion Artifact in MRI by Using a Perceptual Loss Driven Deep Learning Framework Authors: Ziheng Guo, Danqun Zheng, Shuai Li, Chengwei Chen, Boyang Pan, Xuezhou Li, Ziqin Yu, Langdi Zhong, Chenwei Shao, Yun Bian, Nan-Jie Gong Published: 2026-04-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10439v2 Purpose: Deep learning-based MRI artifact correction methods often demonstrate poor generalization to clinical data. This limitation largely stems from the inability of deep learning models in reliably distinguishing motion artifacts from true anatomical structures, due to insufficient awareness of artifact characteristics. To address this challenge, we proposed PERCEPT-Net, a deep learning framework that enhances structure preserving and suppresses artifact through dedicated perceptual supervision.Method: PERCEPT-Net is built on a residual U-Net backbone and incorporates three auxiliary components. The first multi-scale recovery module is designed to preserve both global anatomical context and fine structural details, while the second dual attention mechanisms further improve performance by prioritizing clinically relevant features. At the core of the framework is the third Motion Perceptual Loss (MPL), an artifact-aware perceptual supervision strategy that learns generalized representations of MRI motion artifacts, enabling the model to effectively suppress them while maintaining anatomical fidelity. The model is trained on a hybrid dataset comprising both real and simulated paired volumes, and its performance is validated on a prospective test set using a combination of quantitative metrics and qualitative assessments by experienced radiologists.Result: PERCEPT-Net outperformed state-of-the-art methods on clinical data. Ablation studies identified the Motion Perceptual Loss as the primary contributor to this performance, yielding significant improvements in structural consistency and tissue contrast, as reflected by higher SSIM and PSNR values. These findings were further corroborated by radiologist evaluations, which demonstrated significantly higher diagnostic confidence in the corrected volumes. --- ### Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance Authors: Chenyu Wang, Weicheng Dai, Han Liu, Wenchao Li, Kayhan Batmanghelich Published: 2026-04-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10437v1 Vision--language models (VLMs) for radiology report generation (RRG) can produce long-form chest CT reports from volumetric scans and show strong potential to improve radiology workflow efficiency and consistency. However, existing methods face two key limitations: (i) training supervision is often coarse, aligning a whole CT volume with a full free-text report without explicit alignment for fine-grained attributes or pathology locations; and (ii) evaluation is typically holistic (lexical overlap, entity matching, or LLM-as-a-judge scores) and not diagnostic for spatial grounding. We propose \emph{Discriminative Cue-Prompting with Prompt Dropout (DCP-PD)}, a plug-and-play framework that distills fine-grained cues from free-text reports and uses them to guide report generation while mitigating shortcut reliance via prompt dropout. DCP-PD achieves state-of-the-art performance on CT-RATE, improving macro F1 from $=0.501$ to $0.603$ (20% relative), and substantially boosts out-of-distribution performance on Rad-ChestCT from F1 $=0.266$ to $0.503$ (89% relative). Finally, we introduce a hierarchical, location-aware question-set protocol (presence $\rightarrow$ laterality $\rightarrow$ lobe) to directly assess pathology-location grounding, showing that fine-grained spatial localization remains challenging even for models that score highly on current benchmarks. --- ### SignReasoner: Compositional Reasoning for Complex Traffic Sign Understanding via Functional Structure Units Authors: Ruibin Wang, Zhenyu Lin, Xinhai Zhao Published: 2026-04-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10436v1 Accurate semantic understanding of complex traffic signs-including those with intricate layouts, multi-lingual text, and composite symbols-is critical for autonomous driving safety. Current models, both specialized small ones and large Vision Language Models (VLMs), suffer from a significant bottleneck: a lack of compositional generalization, leading to failure when encountering novel sign configurations. To overcome this, we propose SignReasoner, a novel paradigm that transforms general VLMs into expert traffic sign reasoners. Our core innovation is Functional Structure Unit (FSU), which shifts from common instance-based modeling to flexible function-based decomposition. By breaking down complex signs into minimal, core functional blocks (e.g., Direction, Notice, Lane), our model learns the underlying structural grammar, enabling robust generalization to unseen compositions. We define this decomposition as the FSU-Reasoning task and introduce a two-stage VLM post-training pipeline to maximize performance: Iterative Caption-FSU Distillation that enhances the model's accuracy in both FSU-reasoning and caption generation; FSU-GRPO that uses Tree Edit Distance (TED) to compute FSU differences as the rewards in GRPO algorithm, boosting reasoning abilities. Experiments on the newly proposed FSU-Reasoning benchmark, TrafficSignEval, show that SignReasoner achieves new SOTA with remarkable data efficiency and no architectural modification, significantly improving the traffic sign understanding in various VLMs. --- ### Safety Guarantees in Zero-Shot Reinforcement Learning for Cascade Dynamical Systems Authors: Shima Rabiei, Sandipan Mishra, Santiago Paternain Published: 2026-04-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10429v1 This paper considers the problem of zero-shot safety guarantees for cascade dynamical systems. These are systems where a subset of the states (the inner states) affects the dynamics of the remaining states (the outer states) but not vice-versa. We define safety as remaining on a set deemed safe for all times with high probability. We propose to train a safe RL policy on a reduced-order model, which ignores the dynamics of the inner states, but it treats it as an action that influences the outer state. Thus, reducing the complexity of the training. When deployed in the full system the trained policy is combined with a low-level controller whose task is to track the reference provided by the RL policy. Our main theoretical contribution is a bound on the safe probability in the full-order system. In particular, we establish the interplay between the probability of remaining safe after the zero-shot deployment and the quality of the tracking of the inner states. We validate our theoretical findings on a quadrotor navigation task, demonstrating that the preservation of the safety guarantees is tied to the bandwidth and tracking capabilities of the low-level controller. --- ### A Queueing-Theoretic Framework for Dynamic Attack Surfaces: Data-Integrated Risk Analysis and Adaptive Defense Authors: Jihyeon Yun, Abdullah Yasin Etcibasi, Ming Shi, C. Emre Koksal Published: 2026-04-12 Categories: cs.CR, cs.AI, cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2604.10427v2 We develop a queueing-theoretic framework to model the temporal evolution of cyber-attack surfaces, where the number of active vulnerabilities is represented as the backlog of a queue. Vulnerabilities arrive as they are discovered or created, and leave the system when they are patched or successfully exploited. Building on this model, we study how automation affects attack and defense dynamics by introducing an AI amplification factor that scales arrival, exploit, and patching rates. Our analysis shows that even symmetric automation can increase the rate of successful exploits. We validate the model using vulnerability data collected from an open source software supply chain and show that it closely matches real-world attack surface dynamics. Empirical results reveal heavy-tailed patching times, which we prove induce long-range dependence in vulnerability backlog and help explain persistent cyber risk. Utilizing our queueing abstraction for the attack surface, we develop a systematic approach for cyber risk mitigation. We formulate the dynamic defense problem as a constrained Markov decision process with resource-budget and switching-cost constraints, and develop a reinforcement learning (RL) algorithm that achieves provably near-optimal regret. Numerical experiments validate the approach and demonstrate that our adaptive RL-based defense policies significantly reduce successful exploits and mitigate heavy-tail queue events. Using trace-driven experiments on the ARVO dataset, we show that the proposed RL-based defense policy reduces the average number of active vulnerabilities in a software supply chain by over 90% compared to existing defense practices, without increasing the overall maintenance budget. Our results allow defenders to quantify cumulative exposure risk under long-range dependent attack dynamics and to design adaptive defense strategies with provable efficiency. --- ### CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning Authors: Cheng-Yen Li, Xuanjun Chen, Claire Lin, Wei-Yu Chen, Wenhua Nie, Hung-Yi Lee, Jyh-Shing Roger Jang Published: 2026-04-12 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.10426v1 Large Language Models (LLMs) struggle with knowledge-intensive tasks due to hallucinations and fragmented reasoning over dispersed information. While Retrieval-Augmented Generation (RAG) grounds generation in external sources, existing methods often treat evidence as isolated units, failing to reconstruct the logical chains that connect these dots. Inspired by Complementary Learning Systems (CLS), we propose CodaRAG, a framework that evolves retrieval from passive lookup into active associative discovery. CodaRAG operates via a three-stage pipeline: (1) Knowledge Consolidation to unify fragmented extractions into a stable memory substrate; (2) Associative Navigation to traverse the graph via multi-dimensional pathways-semantic, contextualized, and functional-explicitly recovering dispersed evidence chains; and (3) Interference Elimination to prune hyper-associative noise, ensuring a coherent, high-precision reasoning context. On GraphRAG-Bench, CodaRAG achieves absolute gains of 7-10% in retrieval recall and 3-11% in generation accuracy. These results demonstrate CodaRAG's superior ability to systematically robustify associative evidence retrieval for factual, reasoning, and creative tasks. --- ### DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain Authors: Song Jin, Juntian Zhang, Xun Zhang, Zeying Tian, Fei Jiang, Guojun Yin, Wei Lin, Yong Liu, Rui Yan Published: 2026-04-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10425v1 Recent advancements in Vision-Language Models (VLMs) have revolutionized general visual understanding. However, their application in the food domain remains constrained by benchmarks that rely on coarse-grained categories, single-view imagery, and inaccurate metadata. To bridge this gap, we introduce DiningBench, a hierarchical, multi-view benchmark designed to evaluate VLMs across three levels of cognitive complexity: Fine-Grained Classification, Nutrition Estimation, and Visual Question Answering. Unlike previous datasets, DiningBench comprises 3,021 distinct dishes with an average of 5.27 images per entry, incorporating fine-grained "hard" negatives from identical menus and rigorous, verification-based nutritional data. We conduct an extensive evaluation of 29 state-of-the-art open-source and proprietary models. Our experiments reveal that while current VLMs excel at general reasoning, they struggle significantly with fine-grained visual discrimination and precise nutritional reasoning. Furthermore, we systematically investigate the impact of multi-view inputs and Chain-of-Thought reasoning, identifying five primary failure modes. DiningBench serves as a challenging testbed to drive the next generation of food-centric VLM research. All codes are released in https://github.com/meituan/DiningBench. --- ### Membership Inference Attacks Expose Participation Privacy in ECG Foundation Encoders Authors: Ziyu Wang, Elahe Khatibi, Ankita Sharma, Krishnendu Chakrabarty, Sanaz Rahimi Moosavi, Farshad Firouzi, Amir Rahmani Published: 2026-04-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.10424v1 Foundation-style ECG encoders pretrained with self-supervised learning are increasingly reused across tasks, institutions, and deployment contexts, often through model-as-a-service interfaces that expose scalar scores or latent representations. While such reuse improves data efficiency and generalization, it raises a participation privacy concern: can an adversary infer whether a specific individual or cohort contributed ECG data to pretraining, even when raw waveforms and diagnostic labels are never disclosed? In connected-health settings, training participation itself may reveal institutional affiliation, study enrollment, or sensitive health context. We present an implementation-grounded audit of membership inference attacks (MIAs) against modern self-supervised ECG foundation encoders, covering contrastive objectives (SimCLR, TS2Vec) and masked reconstruction objectives (CNN- and Transformer-based MAE). We evaluate three realistic attacker interfaces: (i) score-only black-box access to scalar outputs, (ii) adaptive learned attackers that aggregate subject-level statistics across repeated queries, and (iii) embedding-access attackers that probe latent representation geometry. Using a subject-centric protocol with window-to-subject aggregation and calibration at fixed false-positive rates under a cross-dataset auditing setting, we observe heterogeneous and objective-dependent participation leakage: leakage is most pronounced in small or institution-specific cohorts and, for contrastive encoders, can saturate in embedding space, while larger and more diverse datasets substantially attenuate operational tail risk. Overall, our results show that restricting access to raw signals or labels is insufficient to guarantee participation privacy, underscoring the need for deployment-aware auditing of reusable biosignal foundation encoders in connected-health systems. --- ### Replicable Composition Authors: Kiarash Banihashem, MohammadHossein Bateni, Hossein Esfandiari, Samira Goudarzi, MohammadTaghi Hajiaghayi Published: 2026-04-12 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2604.10423v1 Replicability requires that algorithmic conclusions remain consistent when rerun on independently drawn data. A central structural question is composition: given $k$ problems each admitting a $ρ$-replicable algorithm with sample complexity $n$, how many samples are needed to solve all jointly while preserving replicability? The naive analysis yields $\widetilde{O}(nk^2)$ samples, and Bun et al. (STOC'23) observed that reductions through differential privacy give an alternative $\widetilde{O}(n^2k)$ bound, leaving open whether the optimal $\widetilde{O}(nk)$ scaling is achievable. We resolve this open problem and, more generally, show that problems with sample complexities $n_1,\ldots,n_k$ can be jointly solved with $\widetilde{O}(\sum_i n_i)$ samples while preserving constant replicability. Our approach converts each replicable algorithm into a perfectly generalizing one, composes them via a privacy-style analysis, and maps back via correlated sampling. This yields the first advanced composition theorem for replicability. En route, we obtain new bounds for the composition of perfectly generalizing algorithms with heterogeneous parameters. As part of our results, we provide a boosting theorem for the success probability of replicable algorithms. For a broad class of problems, the failure probability appears as a separate additive term independent of $ρ$, immediately yielding improved sample complexity bounds for several problems. Finally, we prove an $Ω(nk^2)$ lower bound for adaptive composition, establishing a quadratic separation from the non-adaptive setting. The key technique, which we call the phantom run, yields structural results of independent interest. --- ### CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation Authors: Elahe Khatibi, Ziyu Wang, Ankita Sharma, Krishnendu Chakrabarty, Sanaz Rahimi Moosavi, Farshad Firouzi, Amir Rahmani Published: 2026-04-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.10420v1 Large language models (LLMs) enable waveform-to-text ECG interpretation and interactive clinical questioning, yet most ECG-LLM systems still rely on weak signal-text alignment and retrieval without explicit physiological or causal structure. This limits grounding, temporal reasoning, and counterfactual "what-if" analysis central to clinical decision-making. We propose CARE-ECG, a causally structured ECG-language reasoning framework that unifies representation learning, diagnosis, and explanation in a single pipeline. CARE-ECG encodes multi-lead ECGs into temporally organized latent biomarkers, performs causal graph inference for probabilistic diagnosis, and supports counterfactual assessment via structural causal models. To improve faithfulness, CARE-ECG grounds language outputs through causal retrieval-augmented generation and a modular agentic pipeline that integrates history, diagnosis, and response with verification. Across multiple ECG benchmarks and expert QA settings, CARE-ECG improves diagnostic accuracy and explanation faithfulness while reducing hallucinations (e.g., 0.84 accuracy on Expert-ECG-QA and 0.76 on SCP-mapped PTB-XL under GPT-4). Overall, CARE-ECG provides traceable reasoning by exposing key latent drivers, causal evidence paths, and how alternative physiological states would change outcomes. --- ### Turing or Cantor: That is the Question Authors: Eugene Eberbach Published: 2026-04-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.10418v2 Alan Turing is considered as a founder of current computer science together with Kurt Godel, Alonzo Church and John von Neumann. In this paper multiple new research results are presented. It is demonstrated that there would not be Alan Turing's achievements without earlier seminal contributions by Georg Cantor in the set theory and foundations of mathematics. It is proposed to introduce the measure of undecidability of problems unsolvable by Turing machines based on probability distribution of its input data, i.e., to provide the degree of unsolvabilty based on the number of undecidable instances of input data versus decidable ones. It is proposed as well to extend the Turing's work on infinite logics and Oracle machines to a whole class of super-Turing models of computation. Next, the three new complexity classes for TM undecidable problems have been defined: U-complete (Universal complete), D-complete (Diagonalization complete) and H-complete (Hypercomputation complete) classes. The above has never been defined explicitly before by other scientists, and has been inspired by Cook/Levin NP-complete class for intractable problems. Finally, an equivalent to famous P is not equal to NP unanswered question for NP-complete class, has been answered negatively for U-complete class of complexity for undecidable problems. --- ### LASQ: A Low-resource Aspect-based Sentiment Quadruple Extraction Dataset Authors: Aizihaierjiang Yusufu, Jiang Liu, Kamran Aziz, Abidan Ainiwaer, Bobo Li, Fei Li, Donghong Ji, Aizierguli Yusufu Published: 2026-04-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.10417v1 In recent years, aspect-based sentiment analysis (ABSA) has made rapid progress and shown strong practical value. However, existing research and benchmarks are largely concentrated on high-resource languages, leaving fine-grained sentiment extraction in low-resource languages under-explored. To address this gap, we constructed the first Low-resource languages Aspect-based Sentiment Quadruple dataset, named LASQ, which includes two low-resource languages: Uzbek and Uyghur. Secondly, it includes a fine-grained target-aspect-opinion-sentiment quadruple extraction task. To facilitate future research, we designed a grid-tagging model that integrates syntactic knowledge. This model incorporates part-of-speech (POS) and dependency knowledge into the model through our designed Syntax Knowledge Embedding Module (SKEM), thereby alleviating the lexical sparsity problem caused by agglutinative languages. Experiments on LASQ demonstrate consistent gains over competitive baselines, validating both the dataset's utility and the effectiveness of the proposed modeling approach. --- ### Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackers Authors: Tzu-Yuan Lin, Ho Jae Lee, Kevin Doherty, Yonghyeon Lee, Sangbae Kim Published: 2026-04-12 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.10415v2 We present Point2Pose, a model-free method for causal 6D pose tracking of multiple rigid objects from monocular RGB-D video. Initialized only from sparse image points on the objects, our approach tracks multiple unseen objects without requiring object CAD models or category priors. Point2Pose leverages a 2D point tracker to obtain long-range correspondences, enabling instant recovery after complete occlusion. Simultaneously, the system incrementally reconstructs an online Truncated Signed Distance Function (TSDF) representation of the tracked targets. Alongside the method, we introduce a new multi-object tracking dataset comprising both simulation and real-world sequences, with motion-capture ground truth for evaluation. Experiments show that Point2Pose trades some single-object pose accuracy for broader model-free tracking capabilities, including multi-object tracking and recovery from complete occlusion. Project page: https://point2pose.github.io/. --- ### Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackers Authors: Tzu-Yuan Lin, Ho Jae Lee, Kevin Doherty, Yonghyeon Lee, Sangbae Kim Published: 2026-04-12 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2604.10415v1 We present Point2Pose, a model-free method for causal 6D pose tracking of multiple rigid objects from monocular RGB-D video. Initialized only from sparse image points on the objects to be tracked, our approach tracks multiple unseen objects without requiring object CAD models or category priors. Point2Pose leverages a 2D point tracker to obtain long-range correspondences, enabling instant recovery after complete occlusion. Simultaneously, the system incrementally reconstructs an online Truncated Signed Distance Function (TSDF) representation of the tracked targets. Alongside the method, we introduce a new multi-object tracking dataset comprising both simulation and real-world sequences, with motion-capture ground truth for evaluation. Experiments show that Point2Pose achieves performance comparable to the state-of-the-art methods on a severe-occlusion benchmark, while additionally supporting multi-object tracking and recovery from complete occlusion, capabilities that are not supported by previous model-free tracking approaches. --- ### Neural Stochastic Processes for Satellite Precipitation Refinement Authors: Shunya Nagashima, Takumi Bannai, Shuitsu Koyama, Tomoya Mitsui, Shuntaro Suzuki Published: 2026-04-12 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.10414v1 Accurate precipitation estimation is critical for flood forecasting, water resource management, and disaster preparedness. Satellite products provide global hourly coverage but contain systematic biases; ground-based gauges are accurate at point locations but too sparse for direct gridded correction. Existing methods fuse these sources by interpolating gauge observations onto the satellite grid, but treat each time step independently and therefore discard temporal structure in precipitation fields. We propose Neural Stochastic Process (NSP), a model that pairs a Neural Process encoder conditioning on arbitrary sets of gauge observations with a latent Neural SDE on a 2D spatial representation. NSP is trained under a single variational objective with simulation-free cost. We also introduce QPEBench, a benchmark of 43{,}756 hourly samples over the Contiguous United States (2021--2025) with four aligned data sources and six evaluation metrics. On QPEBench, NSP outperforms 13 baselines across all six metrics and surpasses JAXA's operational gauge-calibrated product. An additional experiment on Kyushu, Japan confirms generalization to a different region with independent data sources. --- ### Orthogonal machine learning for conditional odds and risk ratios Authors: Jiacheng Ge, Iván Díaz Published: 2026-04-12 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2604.10412v1 Conditional effects are commonly used measures for understanding how treatment effects vary across different groups, and are often used to target treatments/interventions to groups who benefit most. In this work we review existing methods and propose novel ones, focusing on the odds ratio (OR) and the risk ratio (RR). While estimation of the conditional average treatment effect (ATE) has been widely studied, estimators for the OR and RR lag behind, and cutting edge estimators such as those based on doubly robust transformations or orthogonal risk functions have not been generalized to these parameters. We propose such a generalization here, focusing on the DR-learner and the R-learner. We derive orthogonal risk functions for the OR and RR and show that the associated pseudo-outcomes satisfy second-order conditional-mean remainder properties analogous to the ATE case. We also evaluate estimators for the conditional ATE, OR, and RR in a comprehensive nonparametric Monte Carlo simulation study to compare them with common alternatives under hundreds of different data-generating distributions. Our numerical studies provide empirical guidance for choosing an estimator. For instance, they show that while parametric models are useful in very simple settings, the proposed nonparametric estimators significantly reduce bias and mean squared error in the more complex settings expected in the real world. We illustrate the methods in the analysis of physical activity and sleep trouble in U.S. adults using data from the National Health and Nutrition Examination Survey (NHANES). The results demonstrate that our estimators uncover substantial treatment effect heterogeneity that is obscured by traditional regression approaches and lead to improved treatment decision rules, highlighting the importance of data-adaptive methods for advancing precision health research. --- ### CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation Authors: Shantam Srivastava, Mahesh Bhosale, David Doermann, Mingchen Gao Published: 2026-04-12 Categories: cs.AI arXiv: https://arxiv.org/abs/2604.10410v2 Interpreting chest X-rays is inherently challenging due to the overlap between anatomical structures and the subtle presentation of many clinically significant pathologies, making accurate diagnosis time-consuming even for experienced radiologists. Recent radiology-focused foundation models, such as LLaVA-Rad and Maira-2, have positioned multi-modal large language models (MLLMs) at the forefront of automated radiology report generation (RRG). However, despite these advances, current foundation models generate reports in a single forward pass. This decoding strategy diminishes attention to visual tokens and increases reliance on language priors as generation proceeds, which in turn introduces spurious pathology co-occurrences in the generated reports. To mitigate these limitations, we propose Category-Wise Contrastive Decoding (CWCD), a novel and modular framework designed to enhance structured radiology report generation (SRRG). Our approach introduces category-specific parameterization and generates category-wise reports by contrasting normal X-rays with masked X-rays using category-specific visual prompts. Experimental results demonstrate that CWCD consistently outperforms baseline methods across both clinical efficacy and natural language generation metrics. An ablation study further elucidates the contribution of each architectural component to overall performance. --- ### IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly Authors: Di Wen, Zeyun Zhong, David Schneider, Manuel Zaremski, Linus Kunzmann, Yitian Shi, Ruiping Liu, Yufan Chen, Junwei Zheng, Jiahang Li, Jonas Hemmerich, Qiyi Tong et al. Published: 2026-04-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10409v1 We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial angle grinder with professional-grade tools. To our knowledge, IMPACT is the first real industrial assembly benchmark that jointly provides synchronized ego-exo RGB-D capture, decoupled bimanual annotation, compliance-aware state tracking, and explicit anomaly--recovery supervision within a single real industrial workflow. It comprises 112 trials from 13 participants totaling 39.5 hours, with multi-route execution governed by a partial-order prerequisite graph, a six-category anomaly taxonomy, and operator cognitive load measured via NASA-TLX. The annotation hierarchy links hand-specific atomic actions to coarse procedural steps, component assembly states, and per-hand compliance phases, with synchronized null spans across views to decouple perceptual limitations from algorithmic failure. Systematic baselines reveal fundamental limitations that remain invisible to single-task benchmarks, particularly under realistic deployment conditions that involve incomplete observations, flexible execution paths, and corrective behavior. The full dataset, annotations, and evaluation code are available at https://github.com/Kratos-Wen/IMPACT. --- ### Sense Less, Infer More: Agentic Multimodal Transformers for Edge Medical Intelligence Authors: Chengwei Zhou, Zhaoyan Jia, Haotian Yu, Xuming Chen, Brandon Lee, Christopher Pulliam, Steve Majerus, Massoud Pedram, Gourav Datta Published: 2026-04-12 Categories: cs.ET, cs.LG arXiv: https://arxiv.org/abs/2604.10404v1 Edge-based multimodal medical monitoring requires models that balance diagnostic accuracy with severe energy constraints. Continuous acquisition of ECG, PPG, EMG, and IMU streams rapidly drains wearable batteries, often limiting operation to under 10 hours, while existing systems overlook the high temporal redundancy present in physiological signals. We introduce Adaptive Multimodal Intelligence (AMI), an end-to-end framework that jointly learns when to sense and how to infer. AMI integrates three components: (1) a lightweight Agentic Modality Controller that uses differentiable Gumbel-Sigmoid gating to dynamically select active sensors based on model confidence and task relevance; (2) a Learned Sigma-Delta Sensing module that applies patch-wise Delta-Sigma operations with learnable thresholds to skip temporally redundant samples; and (3) a Foundation-backed Multimodal Prediction Model built on unimodal foundation encoders and a cross-modal transformer with temporal context, enabling robust fusion even under gated or missing inputs. These components are trained jointly via a multi-objective loss combining classification accuracy, sparsity regularization, cross-modal alignment, and predictive coding. AMI is hardware-aware, supporting dynamic computation graphs and masked operations, leading to real energy and latency savings. Across MHEALTH, HMC Sleep, and WESAD datasets, it reduces sensor usage by 48.8% while improving state-of-the-art accuracy by 1.9% on average. --- ### Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs Authors: Eric Easley, Sebastian Farquhar Published: 2026-04-12 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.10403v1 We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when given malign instructions, our method specifically trains the model to change how it interprets instructions. Our method, Latent Instruction Representation Alignment (LIRA), greatly improves generalization. We further boost generalization through an internally adversarial training algorithm. Our methods block over 99% of PEZ jailbreak attacks; remove a challenging insecure code backdoor; and achieve optimal forgetting on WMDP cyber with negligible loss of benign capabilities. --- ### NameBERT: Scaling Name-Based Nationality Classification with LLM-Augmented Open Academic Data Authors: Cong Ming, Ruixin Shi, Yifan Hu Published: 2026-04-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.10401v2 Inferring nationality from personal names is a critical capability for equity and bias monitoring, personalization, and a valuable tool in biomedical and sociological research. However, existing name-based nationality classifiers are typically trained on relatively small or source-specific labeled datasets, which can introduce coverage gaps and limit performance for underrepresented countries. While large language models (LLMs) demonstrate strong zero-shot performance for name-based nationality prediction, their computational cost and latency make them impractical for real-time, large-scale deployment. In this work, we created a large-scale name-nationality dataset from the Open Academic Graph (OAG) and introduce a framework that leverages LLMs as dataset enrichers rather than inference engines. We augment low-resource countries with LLM-generated names and evaluate on real and synthetic-tail test sets. We find that augmentation produces large gains when evaluation includes synthetic tail names and still offers a modest lift on tail-country metrics otherwise. Overall, NameBERT models achieve significantly higher accuracy than state-of-the-art baselines across both in- and out-of-domain tasks, while remaining efficient for large-scale inference compared to LLMs. --- ### Estimating heterogeneous treatment effects with survival outcomes via a deep survival learner Authors: Yuming Sun, Jian Kang, Yi Li Published: 2026-04-12 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2604.10398v1 Estimating heterogeneous treatment effects in survival settings is complicated by right censoring as well as the time-varying nature of the estimand. While the conditional average treatment effect (CATE) provides a natural target, most existing approaches focus on a single prespecified time point and do not account for the temporal trajectory, leading to instability in estimation. We propose a deep survival learner (DSL) for estimating heterogeneous treatment effects with right-censored outcomes. The method is based on a doubly robust pseudo-outcome whose conditional expectation identifies time-specific CATEs under standard assumptions. This construction remains unbiased if either the outcome model or the treatment assignment model is correctly specified, when properly accounting for censoring. To estimate CATEs over a clinically relevant time spectrum, DSL employs a multi-output deep neural network with shared representations, enabling joint estimation of treatment effect trajectories. From a theoretical perspective, we derive error bounds for both pointwise and joint estimation over time. We show that joint estimation can leverage temporal structure to control estimation error without incurring much additional approximation cost under smoothness conditions, leading to improved stability relative to separate estimation. Cross-fitting is incorporated to reduce overfitting and mitigate bias arising from flexible nuisance estimation. Simulation studies demonstrate favorable finite-sample performance, particularly under nuisance model misspecification. Applied to the Boston Lung Cancer Study, DSL reveals heterogeneity in the effects of perioperative chemotherapy across patient characteristics and over time. --- ### Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipation Authors: Yuanhao Luo, Di Wen, Kunyu Peng, Ruiping Liu, Junwei Zheng, Yufan Chen, Jiale Wei, Rainer Stiefelhage Published: 2026-04-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10397v1 Video-based human-object interaction (HOI) understanding requires both detecting ongoing interactions and anticipating their future evolution. However, existing methods usually treat anticipation as a downstream forecasting task built on externally constructed human-object pairs, limiting joint reasoning between detection and prediction. In addition, sparse keyframe annotations in current benchmarks can temporally misalign nominal future labels from actual future dynamics, reducing the reliability of anticipation evaluation. To address these issues, we introduce DETAnt-HOI, a temporally corrected benchmark derived from VidHOI and Action Genome for more faithful multi-horizon evaluation, and HOI-DA, a pair-centric framework that jointly performs subject-object localization, present HOI detection, and future anticipation by modeling future interactions as residual transitions from current pair states. Experiments show consistent improvements in both detection and anticipation, with larger gains at longer horizons. Our results highlight that anticipation is most effective when learned jointly with detection as a structural constraint on pair-level video representation learning. Benchmark and code will be publicly available. --- ### Intent-aligned Formal Specification Synthesis via Traceable Refinement Authors: Zhe Ye, Aidan Z. H. Yang, Huangyuan Su, Zhenyu Liao, Samuel Tenka, Zhizhen Qin, Udaya Ghai, Dawn Song, Soonho Kong Published: 2026-04-12 Categories: cs.LG, cs.AI, cs.LO, cs.PL, cs.SE arXiv: https://arxiv.org/abs/2604.10392v1 Large language models are increasingly used to generate code from natural language, but ensuring correctness remains challenging. Formal verification offers a principled way to obtain such guarantees by proving that a program satisfies a formal specification. However, specifications are frequently missing in real-world codebases, and writing high-quality specifications remains expensive and expertise-intensive. We present VeriSpecGen, a traceable refinement framework that synthesizes intent-aligned specifications in Lean through requirement-level attribution and localized repair. VeriSpecGen decomposes natural language into atomic requirements and generates requirement-targeted tests with explicit traceability maps to validate generated specifications. When validation fails, traceability maps attribute failures to specific requirements, enabling targeted clause-level repairs. VeriSpecGen achieve 86.6% on VERINA SpecGen task using Claude Opus 4.5, improving over baselines by up to 31.8 points across different model families and scales. Beyond inference-time gains, we generate 343K training examples from VeriSpecGen refinement trajectories and demonstrate that training on these trajectories substantially improves specification synthesis by 62-106% relative and transfers gains to general reasoning abilities. --- ### FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception Authors: Rahul Ahuja, Mudit Jain, Bala Murali Manoghar Sai Sudhakar, Venkatraman Narayanan, Pratik Likhar, Varun Ravi Kumar, Senthil Yogamani Published: 2026-04-12 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.10391v1 Vision foundation models (VFMs) and Bird's Eye View (BEV) representation have advanced visual perception substantially, yet their internal spatial representations assume the rectilinear geometry of pinhole cameras. Fisheye cameras, widely deployed on production autonomous vehicles for their surround-view coverage, exhibit severe radial distortion that renders these representations geometrically inconsistent. At the same time, the scarcity of large-scale fisheye annotations makes retraining foundation models from scratch impractical. We present \ours, a lightweight framework that adapts frozen VFMs to fisheye geometry through two components: a frozen DINOv2 backbone with Low-Rank Adaptation (LoRA) that transfers rich self-supervised features to fisheye without task-specific pretraining, and Fisheye Rotary Position Embedding (FishRoPE), which reparameterizes the attention mechanism in the spherical coordinates of the fisheye projection so that both self-attention and cross-attention operate on angular separation rather than pixel distance. FishRoPE is architecture-agnostic, introduces negligible computational overhead, and naturally reduces to the standard formulation under pinhole geometry. We evaluate \ours on WoodScape 2D detection (54.3 mAP) and SynWoodScapes BEV segmentation (65.1 mIoU), where it achieves state-of-the-art results on both benchmarks. --- ### BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection Authors: Saukun Thika You, Nguyen Anh Khoa Tran, Wesley K. Marizane, Hanshu Rao, Qiunan Zhang, Xiaolei Huang Published: 2026-04-12 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.10389v2 Terminology substitution errors in clinical notes, where one medical term is replaced by a linguistically valid but clinically different term, pose a persistent challenge for automated error detection in healthcare. We introduce BLUEmed, a multi-agent debate framework augmented with hybrid Retrieval-Augmented Generation (RAG) that combines evidence-grounded reasoning with multi-perspective verification for clinical error detection. BLUEmed decomposes each clinical note into focused sub-queries, retrieves source-partitioned evidence through dense, sparse, and online retrieval, and assigns two domain expert agents distinct knowledge bases to produce independent analyses; when the experts disagree, a structured counter-argumentation round and cross-source adjudication resolve the conflict, followed by a cascading safety layer that filters common false-positive patterns. We evaluate BLUEmed on a clinical terminology substitution detection benchmark under both zero-shot and few-shot prompting with multiple backbone models spanning proprietary and open-source families. Experimental results show that BLUEmed achieves the best accuracy (69.13%), ROC-AUC (74.45%), and PR-AUC (72.44%) under few-shot prompting, outperforming both single-agent RAG and debate-only baselines. Further analyses across six backbone models and two prompting strategies confirm that retrieval augmentation and structured debate are complementary, and that the framework benefits most from models with sufficient instruction-following and clinical language understanding. --- ### TrajOnco: a multi-agent framework for temporal reasoning over longitudinal EHR for multi-cancer early detection Authors: Sihang Zeng, Young Won Kim, Wilson Lau, Ehsan Alipour, Ruth Etzioni, Meliha Yetisgen, Anand Oka Published: 2026-04-12 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2604.10386v1 Accurate estimation of cancer risk from longitudinal electronic health records (EHRs) could support earlier detection and improved care, but modeling such complex patient trajectories remains challenging. We present TrajOnco, a training-free, multi-agent large language model (LLM) framework designed for scalable multi-cancer early detection. Using a chain-of-agents architecture with long-term memory, TrajOnco performs temporal reasoning over sequential clinical events to generate patient-level summaries, evidence-linked rationales, and predicted risk scores. We evaluated TrajOnco on de-identified Truveta EHR data across 15 cancer types using matched case-control cohorts, predicting risk of cancer diagnosis at 1 year. In zero-shot evaluation, TrajOnco achieved AUROCs of 0.64-0.80, performing comparably to supervised machine learning in a lung cancer benchmark while demonstrating better temporal reasoning than single-agent LLMs. The multi-agent design also enabled effective temporal reasoning with smaller-capacity models such as GPT-4.1-mini. The fidelity of TrajOnco's output was validated through human evaluation. Furthermore, TrajOnco's interpretable reasoning outputs can be aggregated to reveal population-level risk patterns that align with established clinical knowledge. These findings highlight the potential of multi-agent LLMs to execute interpretable temporal reasoning over longitudinal EHRs, advancing both scalable multi-cancer early detection and clinical insight generation. --- ### GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models Authors: Nicolae Cudlenco, Mihai Masala, Marius Leordeanu Published: 2026-04-12 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.10385v3 Game engines hold what video models struggle to learn: a complete, explicit world state behind every frame. We turn one into a data instrument. GEST-Engine, our production-grade open-source system, deterministically executes Graphs of Events in Space and Time (GESTs), whether procedurally generated or derived from text, into videos of synchronized multi-actor scenarios, recording ground truth as it renders: 3D entity and camera state, pairwise spatial relations, event-to-frame mappings, instance segmentation, and long descriptions, at zero marginal annotation cost. With it we release GTASA, a 938-video sample of what the system can generate at arbitrary scale, carrying, to our knowledge, the densest spatial-relation coverage of any video dataset: a complete entity-pair relation graph at every frame, ~84x denser than the state of the art, frame-for-frame. We validate GTASA both qualitatively, through human evaluation of physical validity and semantic alignment where frontier neural generators, given the same prompts, largely fail, and quantitatively, with GTASA pretraining improving VLM video captioning. Probing six frozen video encoders across 11 spatio-temporal tasks enabled by GTASA's exact 3D ground truth, a previously untestable inter-entity relational probe of frozen video features, reveals that who-is-near-whom barely rises above chance for all of them. We release the engine, the corpus, and the benchmark, making this gap a measurable, trainable target. --- ### Empathic and agentic artificial intelligence in nursing: perspectives on a human-centered framework for cancer care navigation in the United States Authors: Tyra Girdwood, Saba Kheirinejad, Parnian Kheirkhah Rahimabad, Brianna M. White, Robert L Davis, David L Schwartz, Arash Shaban-Nejad Published: 2026-04-11 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2606.00010v1 For patients experiencing cancer, nurse navigation can ease the burden of complex care by enhancing coordination of health services and patient outcomes. However, in under-resourced areas, trained nurse navigators may be limited or non-existent. In the United States, artificial intelligence (AI)-enabled digital health tools are increasingly available and may help address gaps in care coordination; however, most are not designed to specifically support nursing. This perspective piece discusses a human-centered AI framework that integrates empathic and agentic approaches grounded in the American Nurses Association's code of ethics to support nurses in the United States in cancer care navigation. The framework could augment, not replace, human empathy and agency while improving nurse workflow, patient-clinician relationships, and care coordination services in under-resourced areas. --- ### From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and Elastic Horizons Authors: Xiangyu Ma, Teng Xiao, Zuchao Li, Lefei Zhang Published: 2026-04-11 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2605.27387v2 Diffusion models promise efficient parallel text generation but rely on bidirectional attention, creating a structural mismatch with pre-trained Autoregressive (AR) models. This incompatibility precludes reusing robust AR priors, necessitating prohibitive pre-training from scratch. To bridge this gap, we propose FLUID, a framework that efficiently adapts AR backbones to the diffusion paradigm. By enforcing Strictly Causal Alignment, FLUID enables seamless initialization from standard GPT-style checkpoints, circumventing the need for massive pre-training. Furthermore, we introduce Elastic Horizons, an entropy-driven mechanism that dynamically modulates denoising strides based on local information density rather than fixed schedules. Experiments demonstrate that FLUID achieves state-of-the-art performance while reducing training costs by orders of magnitude, effectively reconciling established AR foundations with efficient parallel generation. Our code is available at https://github.com/Oli-lab-nun/FLUID/tree/main. --- ### STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation Authors: Shuai Li, Chen Huang, Duanyu Feng, Wenqiang Lei, See-Kiong Ng Published: 2026-04-11 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2605.18765v1 To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG) leverages lightweight retrievers to efficiently extract information from a given Knowledge Graph (KG). However, existing methods often overlook the inherent challenge of sparse semantic information in graphs. Specifically, our experiments reveal that these methods produce biased retrieval Semantic Shortcut Bias and Long-Tail Path Bias, leading to inadequate semantic modeling and limited GraphRAG effectiveness. To address these issues, we propose STAR, a semantic-tuned and tail-adaptive retriever for GraphRAG. STAR integrates two key learning paradigms: token-level interaction learning and path-weighted contrastive learning. The former employs a cross-attention architecture and a hard path mining mechanism to jointly model the query and path, thereby mitigating the Semantic Shortcut Bias. The latter introduces a tailored contrastive learning objective that utilizes tail-adaptive path weighting, designed to optimize the training process and ease the Long-Tail Path Bias. Extensive experiments demonstrate that STAR consistently outperforms baselines, achieving average retrieval performance gains of 1.8\% and LLM QA performance improvements of 2.2\% across all benchmark datasets. Our code is available at https://anonymous.4open.science/r/STAR-C583. --- ### Taxonomy and Consistency Analysis of Safety Benchmarks for AI Agents Authors: Miles Q. Li, Benjamin C. M. Fung, Boyang Li, Heba Ismail, Farkhund Iqbal Published: 2026-04-11 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2605.16282v1 The rapid deployment of LLM-based autonomous agents has introduced safety risks that extend far beyond traditional LLM concerns, prompting a proliferation of safety benchmarks since late 2023. However, these benchmarks have developed independently, with inconsistent threat models, incompatible metrics, and overlapping yet incomplete risk coverage. We present the first systematic analysis dedicated to agent safety benchmarks as evaluation instruments. We catalog 40 behavioral agent-safety benchmarks (2023-2026), plus 5 adjacent evaluator, defense, and dataset artifacts, propose a six-axis taxonomy of benchmark evaluation methodology, and apply it across the corpus to characterize how methodological choices shape safety conclusions. A coverage matrix reveals broad risk coverage but limited methodological convergence, while the taxonomy analysis shows a behavioral-benchmark core concentrated in sandboxed, constrained, and often safety-only evaluation. Across the landscape, we find that benchmark choice can yield contradictory safety conclusions, coverage counts often overstate evaluation depth, environment fidelity systematically shapes reported safety, the field disproportionately tests externally imposed rather than agent-internal risks, metric fragmentation limits comparison, and robustness remains effectively unbenchmarked. We ground these claims with a cross-benchmark consistency check, with 95% confidence intervals and Kendall's W concordance analysis, finding no evidence of ranking concordance across evaluation dimensions (W = 0.10, p = 0.94). We release structured metadata, full taxonomy codings, risk annotations, and all experimental artifacts, and propose minimum reporting standards for future benchmarks. --- ### MPNet: A Robust and Efficient Manifold Pooling Network for Multi-Rhythm EEG Signal Decoding Authors: Guoqing Cai, Kai Zeng, Shoulin Huang, Ting Ma Published: 2026-04-11 Categories: eess.SP, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2605.05212v1 Deep Riemannian networks provide a powerful framework for Electroencephalography (EEG) decoding, but their practical applications are severely constrained. Accurately decoding EEG signals requires modeling complex temporal dynamics across multiple rhythms, which results in high-dimensional Riemannian inputs and significant computational costs. To address this, we propose the Manifold Pooling Network (MPNet). MPNet uses a rhythm-adaptive convolutional frontend to extract comprehensive time-frequency representations and generate multi-view Riemannian nodes. A novel manifold node pooling layer is then proposed to aggregate these nodes into a single fusion node with a fixed size, enabling the following deep Riemannian network to process it with greatly reduced costs. Experiments on two public EEG datasets show that MPNet achieves state-of-the-art accuracy, runs up to 10 times faster than the comparable Riemannian model, and maintains robust performance under limited-data conditions. These findings highlight MPNet's practicality and efficiency for real-world EEG applications. --- ### SemiConLens: Visual Analytics for 2D Semiconductor Discovery Authors: Kavinda Athapaththu, Shiwei Chen, Yuan Fang, Sanchali Mitra, Yee Sin Ang, Yong Wang Published: 2026-04-11 Categories: cs.HC, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2605.04067v1 The past few years have witnessed vibrant efforts in discovering new two-dimensional (2D) semiconductor materials from both academia and the industry, due to their promising potential in resolving the severe performance deterioration of traditional semiconductors resulting from condensed silicon thickness. However, existing methods (e.g., Density Functional Theory (DFT) or machine-learning-based approaches) suffer from various challenges such as small datasets, and reliability and trustworthiness issues. To bridge this gap, we propose SemiConLens, a visual analytics approach to combine human expertise with the power of ML to enable effective and reliable 2D semiconductor discovery. Specifically, we first develop a new Correlation Aware Multivariate Imputation (CAMI) method and use ML models like autoencoder, which can better learn from limited data and reveal uncertainty, to address the challenge of sparse data in semiconductivity prediction. Built upon this, our visualization module, consisting of three visualization views with linked interactions, allows material researchers to interactively filter, discover and compare 2D semiconductor candidates. A novel circular glyph design and a new cluster-aware layout optimization approach are proposed to effectively display all the user-configurable key attributes and possible prediction uncertainties of each semiconductor candidate, ensuring a reliable and trustable 2D semiconductor discovery. We assess SemiConLens through quantitative evaluations, expert interviews, and use cases. The results demonstrate SemiConLens's capability to help material researchers conduct effective discovery of desirable 2D semiconductors. --- ### Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning Authors: Yiming Huang, Zhenbo Shi, Shuzheng Gao, Cuiyun Gao, Peiyi Han, Chuanyi Liu Published: 2026-04-11 Categories: cs.CL, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2605.04066v2 Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically rely on static policy optimization schemes that misalign with the model's evolving reasoning capabilities. To address this issue, we propose Adaptive Power-Mean Policy Optimization (APMPO), which comprises two main innovations: Power-Mean Policy Optimization (PMPO) and Feedback-Adaptive Clipping (FAC). Specifically, PMPO introduces a generalized power-mean objective. This enables the model to adaptively transition from the signal-amplifying behavior of the arithmetic mean to the consistency-enforcing behavior of the geometric mean. FAC adaptively adjusts clipping bounds based on real-time reward statistics to overcome the limitations of static mechanisms. Capitalizing on these innovations, APMPO improves learning dynamics and reasoning performance. Extensive experiments on nine datasets across three reasoning tasks showcase the superiority of APMPO over state-of-the-art RLVR-based baselines. For instance, APMPO boosts the average Pass@1 score on mathematical reasoning benchmarks by 3.0 points compared to GRPO when using Qwen2.5-3B-Instruct. --- ### Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs Authors: Yiming Huang, Zhenbo Shi, Xin-Cheng Wen, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu Published: 2026-04-11 Categories: cs.CL, cs.ET, cs.LG arXiv: https://arxiv.org/abs/2605.04065v2 Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, existing unsupervised RL-based methods often lack the capacity to adapt to the model's evolving reasoning capabilities during training. Therefore, these methods can misdirect policy optimization in the absence of ground-truth supervision. To address this issue, we introduce FREIA, a novel RL-based algorithm built on two key innovations: (1) Free Energy-Driven Reward (FER) adapts rewards to balance consensus and exploration based on the Free Energy Principle. (2) Adaptive Advantage Shaping (AAS) adaptively adjusts learning signals based on the statistical characteristics of sampled rewards. Empirical evaluations on nine datasets across three reasoning tasks showcase that FREIA outperforms other unsupervised RL-based baselines. Notably, in mathematical reasoning tasks, FREIA surpasses other methods by an average of 0.5 to 3.5 points in Pass@1 using the DeepSeek-R1-Distill-Qwen-1.5B model. --- ### ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable Citations Authors: Navapat Nananukul, Mayank Kejriwal Published: 2026-04-11 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2605.00846v1 Clinical diagnosis requires answers that are accurate, verifiable, and explicitly grounded in official guidelines. While large language models excel at natural language processing, their tendency to hallucinate undermines their utility in high-stakes medical contexts where precision is essential. Existing retrieval-augmented generation (RAG) systems treat all evidence equally, producing noisy context and generic answers misaligned with clinical practice. We present ClinicBot, an AI system that translates guideline recommendations into trustworthy clinical support through three key advances: (1) structured extraction of clinical guidelines into semantic units (recommendations, tables, definitions, narrative) with explicit provenance, (2) evidence prioritization that ranks content by clinical significance and guideline structure rather than textual similarity, and (3) a web-based interface that presents concise, actionable answers with verifiable evidence. We will demonstrate ClinicBot using diabetes questions from real patients and an additional diabetes risk assessment tool that is faithful to the American Diabetes Association (ADA) Standards of Care in Diabetes (2025). The demonstration will illustrate how semantic knowledge extraction and hierarchical evidence ranking can reliably operate in a multi-agent setting to process complex clinical guidelines at scale. --- ### AITP: Traffic Accident Responsibility Allocation via Multimodal Large Language Models Authors: Zijin Zhou, Songan Zhang Published: 2026-04-11 Categories: cs.CL, cs.CV, cs.LG, eess.IV arXiv: https://arxiv.org/abs/2604.20878v1 Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Traffic Accident Detection (TAD) and Traffic Accident Understanding (TAU). However, existing studies mainly focus on describing and interpreting accident videos, leaving room for deeper causal reasoning and integration of legal knowledge. Traffic Accident Responsibility Allocation (TARA) is a more challenging task that requires multi-step reasoning grounded in traffic regulations. To address this, we introduce AITP (Artificial Intelligence Traffic Police), a multimodal large language model for responsibility reasoning and allocation. AITP enhances reasoning via a Multimodal Chain-of-Thought (MCoT) mechanism and integrates legal knowledge through Retrieval-Augmented Generation (RAG). We further present DecaTARA, a decathlon-style benchmark unifying ten interrelated traffic accident reasoning tasks with 67,941 annotated videos and 195,821 question-answer pairs. Extensive experiments show that AITP achieves state-of-the-art performance across responsibility allocation, TAD, and TAU tasks, establishing a new paradigm for reasoning-driven multimodal traffic analysis. --- ### The AI Telco Engineer: Toward Autonomous Discovery of Wireless Communications Algorithms Authors: Fayçal Aït Aoudia, Jakob Hoydis, Sebastian Cammerer, Lorenzo Maggi, Gian Marti, Alexander Keller Published: 2026-04-11 Categories: cs.AI, cs.IT, cs.MA arXiv: https://arxiv.org/abs/2604.19803v1 Agentic AI is rapidly transforming the way research is conducted, from prototyping ideas to reproducing results found in the literature. In this paper, we explore the ability of agentic AI to autonomously design wireless communication algorithms. To that end, we implement a dedicated framework that leverages large language models (LLMs) to iteratively generate, evaluate, and refine candidate algorithms. We evaluate the framework on three tasks spanning the physical (PHY) and medium access control (MAC) layers: statistics-agnostic channel estimation, channel estimation with known covariance, and link adaptation. Our results show that, in a matter of hours, the framework produces algorithms that are competitive with and, in some cases, outperforming conventional baselines. Moreover, unlike neural network-based approaches, the generated algorithms are fully explainable and extensible. This work represents a first step toward the autonomous discovery of novel wireless communication algorithms, and we look forward to the progress our community makes in this direction. --- ### Spike-driven Large Language Model Authors: Han Xu, Xuerui Qiu, Baiyu Chen, Xinhao Luo, Xingrun Xing, Jiahong Zhang, Bo Lei, Tiejun Huang, Bo Xu, Guoqi Li Published: 2026-04-11 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2604.16475v1 Current Large Language Models (LLMs) are primarily based on large-scale dense matrix multiplications. Inspired by the brain's information processing mechanism, we explore the fundamental question: how to effectively integrate the brain's spiking-driven characteristics into LLM inference. Spiking Neural Networks (SNNs) possess spike-driven characteristics, and some works have attempted to combine SNNs with Transformers. However, achieving spike-driven LLMs with billions of parameters, relying solely on sparse additions, remains a challenge in the SNN field. To address the issues of limited representational capacity and sparsity in existing spike encoding schemes at the LLM level, we propose SDLLM, a spike-driven large language model that eliminates dense matrix multiplications through sparse addition operations. Specifically, we use the plug-and-play gamma-SQP two-step spike encoding method to ensure that the quantization process aligns with the model's semantic space, mitigating representation degradation caused by binary spikes. Furthermore, we introduce bidirectional encoding under symmetric quantization and membrane potential clipping mechanisms, leading to spike trains with no or low firing counts dominating, significantly reducing the model's spike firing rate, while halving the number of time steps. Experimental results show that SDLLM not only significantly reduces inference costs but also achieves state-of-the-art task performance under the spike-based paradigm. For example, compared to previous spike-based LLMs, SDLLM reduces energy consumption by 7x and improves accuracy by 4.2%. Our model provides inspiration for the architecture design of the next generation of event-driven neuromorphic chips. --- ### Full Feature Spiking Neural Network Simulation on Micro-Controllers for Neuromorphic Applications at the Edge Authors: L. Niedermeier, J. L. Krichmar Published: 2026-04-11 Categories: cs.AR, cs.AI, cs.NE arXiv: https://arxiv.org/abs/2604.16474v1 Microcontroller units (MCU), which have an order of magnitude lower Size, Weight and Power (SWaP) than standard computers, makes them suitable for applications at the edge. Neuromorphic computing, which can realize low SWaP, relies on Spiking Neural Networks (SNNs). Until now, software based simulations of SNNs required GPU-based workstations, application classified core processors such as the ARM Cortex-A53, or specialized hardware like Intel's Loihi. In the present work, we demonstrate that the SNN simulator CARLsim can run its full feature set on a MCU RP2350 with 8 MB memory. We accomplished this by utilizing IEEE 16-bit float point numbers, which reduced memory requirements without loss of function. We were able to run the Synfire4 benchmark which comprises 1200 neurons. The accuracy was 97.5% compared to the standard single precision numbers. Furthermore, we show that CARLsim runs a Synfire4 benchmark scaled-down to 186 neurons on a MCU in real-time at only 20 mW. Compared to the smallest application class ARM processor used by Raspberry in their Pi Zero 2 W, our MCU implementation is five times more energy efficient for the SNN itself, and an order of magnitude better when compared to the complete SoC (MCU/CPU + Board). --- ### Taming Asynchronous CPU-GPU Coupling for Frequency-aware Latency Estimation on Mobile Edge Authors: Jiesong Chen, Jun You, Zhidan Liu, Zhenjiang Li Published: 2026-04-11 Categories: cs.AR, cs.AI, cs.DC arXiv: https://arxiv.org/abs/2604.15357v1 Precise estimation of model inference latency is crucial for time-critical mobile edge applications, enabling devices to calculate latency margins against deadlines and trade them for enhanced model performance or resource savings. However, the ubiquity of Dynamic Voltage and Frequency Scaling (DVFS) renders traditional static profiling invalid in real-world deployments, as inference latency fluctuates with varying processor (CPU and GPU) frequencies. While extensive profiling across frequency combinations is theoretically possible, it is prohibitively expensive, particularly for emerging Small Language Models (SLMs), where variable context lengths explode the profiling up to days. We observe that simple analytic scaling fails to predict these fluctuations due to the complex asynchronous coupling between CPU (kernel launching) and GPU (execution). In this paper, we introduce FLAME to accurately estimate inference latency across frequency combinations. It features a novel layer-wise modeling that quantifies the overlapping parallelism and then aggregates dynamic pipeline bubbles caused by asynchronous processor interactions when extending to the full model. This bottom-up approach ensures generalizability across diverse models from DNNs to SLMs, and its precise modeling allows for profiling a sparse subset of samples, cutting DNN profiling from hours to minutes and SLM profiling from days to mere minutes, while maintaining small estimation errors across frequencies. We further showcase FLAME's utility in a deadline-aware DVFS, outperforming the state-of-the-art approach in both power efficiency and latency guarantees. --- ### Applying an Agentic Coding Tool for Improving Published Algorithm Implementations Authors: Worasait Suwannik Published: 2026-04-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.13109v1 We present a two-stage pipeline for AI-assisted improvement of published algorithm implementations. In the first stage, a large language model with research capabilities identifies recently published algorithms satisfying explicit experimental criteria. In the second stage, Claude Code is given a prompt to reproduce the reported baseline and then iterate an improvement process. We apply this pipeline to published algorithm implementations spanning multiple research domains. Claude Code reported that all eleven experiments yielded improvements. Each improvement could be achieved within a single working day. We analyse the human contributions that remain indispensable, including selecting the target, verifying experimental validity, assessing novelty and impact, providing computational resources, and writing with appropriate AI-use disclosure. Finally, we discuss implications for peer review and academic publishing. --- ### Formal Architecture Descriptors as Navigation Primitives for AI Coding Agents Authors: Ruoqi Jin Published: 2026-04-11 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.13108v1 AI coding agents spend a substantial fraction of their tool calls on undirected codebase exploration. We investigate whether providing agents with formal architecture descriptors can reduce this navigational overhead. We present three complementary studies. First, a controlled experiment (24 code localization tasks x 4 conditions, Claude Sonnet 4.6, temperature=0) demonstrates that architecture context reduces navigation steps by 33-44% (Wilcoxon p=0.009, Cohen's d=0.92), with no significant format difference detected across S-expression, JSON, YAML, and Markdown. Second, an artifact-vs-process experiment (15 tasks x 3 conditions) demonstrates that an automatically generated descriptor achieves 100% accuracy versus 80% blind (p=0.002, d=1.04), proving direct navigational value independent of developer self-clarification. Third, an observational field study across 7,012 Claude Code sessions shows 52% reduction in agent behavioral variance. A writer-side experiment (96 generation runs, 96 error injections) reveals critical failure mode differences: JSON fails atomically, YAML silently corrupts 50% of errors, S-expressions detect all structural completeness errors. We propose intent.lisp, an S-expression architecture descriptor, and open-source the Forge toolkit. --- ### Uncertainty Quantification in CNN Through the Bootstrap of Convex Neural Networks Authors: Hongfei Du, Emre Barut, Fang Jin Published: 2026-04-11 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.11833v1 Despite the popularity of Convolutional Neural Networks (CNN), the problem of uncertainty quantification (UQ) of CNN has been largely overlooked. Lack of efficient UQ tools severely limits the application of CNN in certain areas, such as medicine, where prediction uncertainty is critically important. Among the few existing UQ approaches that have been proposed for deep learning, none of them has theoretical consistency that can guarantee the uncertainty quality. To address this issue, we propose a novel bootstrap based framework for the estimation of prediction uncertainty. The inference procedure we use relies on convexified neural networks to establish the theoretical consistency of bootstrap. Our approach has a significantly less computational load than its competitors, as it relies on warm-starts at each bootstrap that avoids refitting the model from scratch. We further explore a novel transfer learning method so our framework can work on arbitrary neural networks. We experimentally demonstrate our approach has a much better performance compared to other baseline CNNs and state-of-the-art methods on various image datasets. --- ### The Non-Optimality of Scientific Knowledge: Path Dependence, Lock-In, and The Local Minimum Trap Authors: Mohamed Mabrok Published: 2026-04-11 Categories: cs.AI, cs.CY, math.OC arXiv: https://arxiv.org/abs/2604.11828v2 Science is widely regarded as humanity's most reliable method for uncovering truths about the natural world. Yet the \emph{trajectory} of scientific discovery is rarely examined as an optimization problem in its own right. This paper argues that the body of scientific knowledge, at any given historical moment, represents a \emph{local optimum} rather than a global one--that the frameworks, formalisms, and paradigms through which we understand nature are substantially shaped by historical contingency, cognitive path dependence, and institutional lock-in. Drawing an analogy to gradient descent in machine learning, we propose that science follows the steepest local gradient of tractability, empirical accessibility, and institutional reward, and in doing so may bypass fundamentally superior descriptions of nature. We develop this thesis through detailed case studies spanning mathematics, physics, chemistry, biology, neuroscience, and statistical methodology. We identify three interlocking mechanisms of lock-in--cognitive, formal, and institutional--and argue that recognizing these mechanisms is a prerequisite for designing meta-scientific strategies capable of escaping local optima. We conclude by proposing concrete interventions and discussing the epistemological implications of our thesis for the philosophy of science. --- ### Inverse Design of Inorganic Compounds with Generative AI Authors: Hannes Kneiding, Lucía Morán-González, Nishamol Kuriakose, Ainara Nova, David Balcells Published: 2026-04-11 Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2604.11827v3 Machine learning is revolutionizing chemistry. Beyond the value of predictive models accelerating virtual screening, generative AI aims at enabling inverse design, reversing the compound-to-property prediction paradigm into property-to-compound generation. Chemists now have access to a rich AI toolbox for organic chemistry, including drug discovery. However, the application of these methods to inorganic compounds remains limited by the challenges posed by their intrinsic nature. This Review analyzes how these challenges have been addressed, considering widely diverse systems ranging from molecules to crystals, including transition metal complexes and microporous materials. The analysis focuses on how generative AI methods have evolved towards data-representation-model pipelines that address the full complexity of inorganic compounds, including their chemical composition, geometry, symmetry, and electronic structure. Future directions, like benchmark standardization and the development of synthesizability metrics, are also discussed. --- ### Inverse Design of Inorganic Compounds with Generative AI Authors: Hannes Kneiding, Lucía Morán-González, Nishamol Kuriakose, Ainara Nova, David Balcells Published: 2026-04-11 Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2604.11827v1 Machine learning is revolutionizing chemistry. Beyond the value of predictive models accelerating virtual screening, generative AI aims at enabling inverse design, reversing the compound-to-property prediction paradigm into property-to-compound generation. Chemists now have access to a rich AI toolbox for organic chemistry, including drug discovery. However, the application of these methods to inorganic compounds remains limited by the challenges posed by their intrinsic nature. This Review analyzes how these challenges have been addressed, considering widely diverse systems ranging from molecules to crystals, including transition metal complexes and microporous materials. The analysis focuses on how generative AI methods have evolved towards data-representation-model pipelines that address the full complexity of inorganic compounds, including their chemical composition, geometry, symmetry, and electronic structure. Future directions, like benchmark standardization and the development of synthesizability metrics, are also discussed. --- ### Refined Differentially Private Linear Regression via Extension of a Free Lunch Result Authors: Sasmita Harini S, Anshoo Tandon Published: 2026-04-11 Categories: cs.IT, cs.LG arXiv: https://arxiv.org/abs/2604.11820v1 As data-privacy regulations tighten and statistical models are increasingly deployed on sensitive human-sourced data, privacy-preserving linear regression has become a critical necessity. For the add-remove DP model, Kulesza et al. (2024) and Fitzsimons et al. (2024) have independently shown that the size of the dataset -- an important statistic for linear regression -- can be privately estimated for "free", via a simplex transformation of bounded variables and private sum queries on the transformed variables. In this work, we extend this free lunch result via carefully crafted multidimensional simplex transformations to variables and functions that are bounded in the interval (0,1). We show that these transformations can be applied to refine the estimates of sufficient statistics needed for private simple linear regression based on ordinary least squares. We provide both analytical and numerical results to demonstrate the superiority of our approach. Our proposed transformations have general applicability and can be readily adapted for differentially private polynomial regression. ---