# Research Papers — 2026-04 · bundle page 102 of 233 > Full-text markdown of papers #5051–5100 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/102 [← Previous bundle](https://aipod.dev/papers/archive/2026-04/page/101.md) [Next bundle →](https://aipod.dev/papers/archive/2026-04/page/103.md) ### Frequency-Corrupt Based Graph Self-Supervised Learning Authors: Haojie Li, Mengjiao Zhang, Guanfeng Liu, Qiang Hu, Yan Wang, Junwei Du Published: 2026-04-17 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2604.15699v2 Graph self-supervised learning can reduce the need for labeled graph data and has been widely used in recommendation, social networks, and other web applications. However, existing methods often underuse high-frequency signals and may overfit to specific local patterns, which limits representation quality and generalization. We propose Frequency-Corrupt Based Graph Self-Supervised Learning (FC-GSSL), a method that builds corrupted graphs biased toward high-frequency information by corrupting nodes and edges according to their low-frequency contributions. These corrupted graphs are used as inputs to an autoencoder, while low-frequency and general features are reconstructed as supervision targets, forcing the model to fuse information from multiple frequency bands. We further design multiple sampling strategies and generate diverse corrupted graphs from the intersections and unions of the sampling results. By aligning node representations from these views, the model can discover useful frequency combinations, reduce reliance on specific high-frequency components, and improve robustness. Experiments on 14 datasets across node classification, graph prediction, and transfer learning show that FC-GSSL consistently improves performance and generalization. --- ### The Price of Paranoia: Robust Risk-Sensitive Cooperation in Non-Stationary Multi-Agent Reinforcement Learning Authors: Deep Kumar Ganguly, Chandradithya S Jonnalagadda, Pratham Chintamani, Adithya Ananth Published: 2026-04-17 Categories: cs.GT, cs.AI arXiv: https://arxiv.org/abs/2604.15695v1 Cooperative equilibria are fragile. When agents learn alongside each other rather than in a fixed environment, the process of learning destabilizes the cooperation they are trying to sustain: every gradient step an agent takes shifts the distribution of actions its partner will play, turning a cooperative partner into a source of stochastic noise precisely where the cooperation decision is most sensitive. We study how this co-learning noise propagates through the structure of coordination games, and find that the cooperative equilibrium, even when strongly Pareto-dominant, is exponentially unstable under standard risk-neutral learning, collapsing irreversibly once partner noise crosses the game's critical cooperation threshold. The natural response to apply distributional robustness to hedge against partner uncertainty makes things strictly worse: risk-averse return objectives penalize the high-variance cooperative action relative to defection, widening the instability region rather than shrinking it, a paradox that reveals a fundamental mismatch between the domains where robustness is applied and instability originates. We resolve this by showing that robustness should target the policy gradient update variance induced by partner uncertainty, not the return distribution. This distinction yields an algorithm whose gradient updates are modulated by an online measure of partner unpredictability, provably expanding the cooperation basin in symmetric coordination games. To unify stability, sample complexity, and welfare consequences of this approach, we introduce the Price of Paranoia as the structural dual of the Price of Anarchy. Together with a novel Cooperation Window, it precisely characterizes how much welfare learning algorithms can recover under partner noise, pinning down the optimal degree of robustness as a closed-form balance between equilibrium stability and sample efficiency. --- ### Neural Continuous-Time Markov Chain: Discrete Diffusion via Decoupled Jump Timing and Direction Authors: Jingyuan Li, Xiaoyi Jiang, Fukang Wen, Wei Liu, Renqian Luo, Yi Zhu, Zuoqiang Shi, Pipi Hu Published: 2026-04-17 Categories: cs.LG, math.PR arXiv: https://arxiv.org/abs/2604.15694v2 Discrete diffusion models based on continuous-time Markov chains (CTMCs) have shown strong performance on language and discrete data generation, yet existing approaches typically parameterize the reverse rate matrix monolithically -- through proxies such as concrete scores (SEDD) or clean-data predictions (MDLM, GIDD) -- rather than aligning the parameterization with the intrinsic CTMC decomposition into jump timing and jump direction. We propose \textbf{Neural CTMC}, which exploits the underlying Poisson structure of CTMC dynamics by separately parameterizing the reverse process through an \emph{exit rate} (when to jump) and a \emph{jump distribution} (where to jump) via two dedicated network heads. We show that the evidence lower bound (ELBO) reduces to a path-space KL divergence between the true and learned reverse processes that factorizes into a Poisson KL for timing and a categorical KL for direction, and admits a tractable, gradient-equivalent and consistent loss. Experimentally, scored by Gemma2-9B, our pure-uniform Neural CTMC achieves $16.36$ generative perplexity on TinyStories (vs.\ GIDD $37.60$ and MDLM $42.66$). On OpenWebText, it attains the best perplexity at the same training-token budget across 16--128 sampling steps among the methods we compare (e.g., at 128 steps: Neural CTMC $183.6$ vs.\ MDLM $210.5$ and GIDD $249.8$). To facilitate reproducibility, we release our pretrained weights at https://huggingface.co/Jiangxy1117/Neural-CTMC. --- ### Preference Estimation via Opponent Modeling in Multi-Agent Negotiation Authors: Yuta Konishi, Kento Yamamoto, Eisuke Sonomoto, Rikuho Takeda, Ryo Furukawa, Yusuke Muraki, Takafumi Shimizu, Kazuma Fukumura, Yuya Kanemoto, Takayuki Ito, Shiyao Ding Published: 2026-04-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.15687v1 Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical-only approaches fail to capture the qualitative information embedded in natural language interactions, resulting in unstable and incomplete preference estimation. Although Large Language Models (LLMs) enable rich semantic understanding of utterances, it remains challenging to quantitatively incorporate such information into a consistent opponent modeling. To tackle this issue, we propose a novel preference estimation method integrating natural language information into a structured Bayesian opponent modeling framework. Our approach leverages LLMs to extract qualitative cues from utterances and converts them into probabilistic formats for dynamic belief tracking. Experimental results on a multi-party benchmark demonstrate that our framework improves the full agreement rate and preference estimation accuracy by integrating probabilistic reasoning with natural language understanding. --- ### Self-Supervised Angular Deblurring in Photoacoustic Reconstruction via Noisier2Inverse Authors: Markus Haltmeier, Nadja Gruber, Gyeongha Hwang Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15681v1 Photoacoustic tomography (PAT) is an emerging imaging modality that combines the complementary strengths of optical contrast and ultrasonic resolution. A central task is image reconstruction, where measured acoustic signals are used to recover the initial pressure distribution. For ideal point-like or line-like detectors, several efficient and fast reconstruction algorithms exist, including Fourier methods, filtered backprojection, and time reversal. However, when applied to data acquired with finite-size detectors, these methods yield systematically blurred images. Although sharper images can be obtained by compensating for finite-detector effects, supervised learning approaches typically require ground-truth images that may not be available in practice. We propose a self-supervised reconstruction method based on Noisier2Inverse that addresses finite-size detector effects without requiring ground-truth data. Our approach operates directly on noisy measurements and learns to recover high-quality PAT images in a ground-truth-free manner. Its key components are: (i) PAT-specific modeling that recasts the problem as angular deblurring; (ii) a Noisier2Inverse formulation in the polar domain that leverages the known angular point-spread function; and (iii) a novel, statistically grounded early-stopping rule. In experiments, the proposed method consistently outperforms alternative approaches that do not use supervised data and achieves performance close to supervised benchmarks, while remaining practical for real acquisitions with finite-size detectors. --- ### Hierarchical Active Inference using Successor Representations Authors: Prashant Rangarajan, Rajesh P. N. Rao Published: 2026-04-17 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2604.15679v1 Active inference, a neurally-inspired model for inferring actions based on the free energy principle (FEP), has been proposed as a unifying framework for understanding perception, action, and learning in the brain. Active inference has previously been used to model ecologically important tasks such as navigation and planning, but scaling it to solve complex large-scale problems in real-world environments has remained a challenge. Inspired by the existence of multi-scale hierarchical representations in the brain, we propose a model for planning of actions based on hierarchical active inference. Our approach combines a hierarchical model of the environment with successor representations for efficient planning. We present results demonstrating (1) how lower-level successor representations can be used to learn higher-level abstract states, (2) how planning based on active inference at the lower-level can be used to bootstrap and learn higher-level abstract actions, and (3) how these learned higher-level abstract states and actions can facilitate efficient planning. We illustrate the performance of the approach on several planning and reinforcement learning (RL) problems including a variant of the well-known four rooms task, a key-based navigation task, a partially observable planning problem, the Mountain Car problem, and PointMaze, a family of navigation tasks with continuous state and action spaces. Our results represent, to our knowledge, the first application of learned hierarchical state and action abstractions to active inference in FEP-based theories of brain function. --- ### HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning Authors: Eunju Lee, MiHyeon Kim, JuneHyoung Kwon, Yoonji Lee, JiHyun Kim, Soojin Jang, YoungBin Kim Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15678v2 Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) methods assume homogeneous domains and balanced data distributions, limiting real-world applicability where data arises from heterogeneous disciplines with imbalanced sample availability and varying visual complexity. We identify Domain Gravity, a representational asymmetry where data imbalance across heterogeneous domains causes overrepresented or low-entropy domains to disproportionately influence the embedding space, leading to prototype drift and degraded performance on underrepresented or high-entropy domains. To address this, we introduce Cross-Discipline Variable Few-Shot Class-Incremental Learning (XD-VSCIL), a benchmark capturing real-world heterogeneity and imbalance where Domain Gravity naturally intensifies. We propose Hybrid Prototype Calibration (HyCal), a training-free method combining cosine similarity and Mahalanobis distance to capture complementary geometric properties-directional alignment and covariance-aware magnitude-yielding stable prototypes under imbalanced heterogeneous conditions. Operating on frozen CLIP embeddings, HyCal achieves consistent retention-adaptation improvements while maintaining efficiency. Experiments show HyCal effectively mitigates Domain Gravity and outperforms existing methods in imbalanced cross-domain incremental learning. --- ### HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning Authors: Eunju Lee, MiHyeon Kim, JuneHyoung Kwon, Yoonji Lee, JiHyun Kim, Soojin Jang, YoungBin Kim Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15678v1 Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) methods assume homogeneous domains and balanced data distributions, limiting real-world applicability where data arises from heterogeneous disciplines with imbalanced sample availability and varying visual complexity. We identify Domain Gravity, a representational asymmetry where data imbalance across heterogeneous domains causes overrepresented or low-entropy domains to disproportionately influence the embedding space, leading to prototype drift and degraded performance on underrepresented or high-entropy domains. To address this, we introduce Cross-Discipline Variable Few-Shot Class-Incremental Learning (XD-VSCIL), a benchmark capturing real-world heterogeneity and imbalance where Domain Gravity naturally intensifies. We propose Hybrid Prototype Calibration (HyCal), a training-free method combining cosine similarity and Mahalanobis distance to capture complementary geometric properties-directional alignment and covariance-aware magnitude-yielding stable prototypes under imbalanced heterogeneous conditions. Operating on frozen CLIP embeddings, HyCal achieves consistent retention-adaptation improvements while maintaining efficiency. Experiments show HyCal effectively mitigates Domain Gravity and outperforms existing methods in imbalanced cross-domain incremental learning. --- ### C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignment Authors: Pufan Zeng, Yilun Liu, Mingchen Dai, Mengyao Piao, Chunguang Zhao, Lingqi Miao, Shimin Tao, Weibin Meng, Minggui He, Chenxin Liu, Zhenzhen Qin, Li Zhang et al. Published: 2026-04-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.15675v1 Achieving cultural alignment in Large Language Models (LLMs) increasingly depends on synthetic data generation. For such synthesis, the most vital initial step is seed curation; however, current methods lack quantifiable standards for selecting these seeds. Existing approaches rely on unscalable manual curation or bias-prone LLM extraction, treating cultural specificity as an abstract concept rather than a measurable signal. In this paper, we address this "quantification gap" by proposing C-Mining, an unsupervised framework that transforms the discovery of cultural seeds from a subjective selection process into a computable data mining formulation. Our approach exploits a novel geometric insight, leveraging the cross-lingual misalignment of cultural concepts within pre-trained embedding spaces as a quantifiable discovery signal. By systematically identifying these regions characterized by pronounced linguistic exclusivity and geometric isolation, while actively filtering out noise, C-Mining automatically extracts high-fidelity Culture Points (CPs) from raw multilingual corpora without reliance on human or LLM supervision, reducing preparation costs by more than 150-fold. We further leverage the mined knowledge to steer the synthesis of diverse instruction-tuning datasets. Extensive experiments demonstrate that this seed-centric approach significantly enhances cultural understanding and reasoning capabilities, achieving a +6.03 point improvement on CulturalBench-Hard and surpassing state-of-the-art baselines, providing a scalable, quantifiable solution for high-quality cultural data synthesis. --- ### Faster LLM Inference via Sequential Monte Carlo Authors: Yahya Emara, Mauricio Barba da Costa, Chi-Chih Chang, Cameron Freer, Tim Vieira, Ryan Cotterell, Mohamed S. Abdelfattah Published: 2026-04-17 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2604.15672v1 Speculative decoding (SD) accelerates language model inference by drafting tokens from a cheap proposal model and verifying them against an expensive target model via rejection sampling. Because rejection truncates the draft block at the first error, throughput degrades when draft and target diverge. Rather than rejecting draft tokens outright, we propose to reweight them. To this end, we introduce sequential Monte Carlo speculative decoding (SMC-SD), which replaces token-level rejection with importance-weighted resampling over a population of draft particles. SMC-SD is a principled approximate inference scheme that trades exactness for additional speed, while preserving theoretical bounds on its per-step approximation error. Because LLM inference is memory bandwidth-bound, the arithmetic needed to draft particles and to score them in parallel comes nearly for free -- SMC-SD uses idle compute to turn verification into a vectorized, fixed-size operation with no rollback. Empirically, SMC-SD achieves 2.36x speed-up over speculative decoding and a 5.2x speed-up over autoregressive decoding, while remaining within 3% of the target model's accuracy on reasoning, instruction-following, and coding benchmarks. --- ### PixDLM: A Dual-Path Multimodal Language Model for UAV Reasoning Segmentation Authors: Shuyan Ke, Yifan Mei, Changli Wu, Yonghan Zheng, Jiayi Ji, Liujuan Cao, Rongrong Ji Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15670v2 Reasoning segmentation has recently expanded from ground-level scenes to remote-sensing imagery, yet UAV data poses distinct challenges, including oblique viewpoints, ultra-high resolutions, and extreme scale variations. To address these issues, we formally define the UAV Reasoning Segmentation task and organize its semantic requirements into three dimensions: Spatial, Attribute, and Scene-level reasoning. Based on this formulation, we construct DRSeg, a large-scale benchmark for UAV reasoning segmentation, containing 10k high-resolution aerial images paired with Chain-of-Thought QA supervision across all three reasoning types. As a benchmark companion, we introduce PixDLM, a simple yet effective pixel-level multimodal language model that serves as a unified baseline for this task. Experiments on DRSeg establish strong baseline results and highlight the unique challenges of UAV reasoning segmentation, providing a solid foundation for future research. --- ### NK-GAD: Neighbor Knowledge-Enhanced Unsupervised Graph Anomaly Detection Authors: Zehao Wang, Lanjun Wang Published: 2026-04-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.15668v1 Graph anomaly detection aims to identify irregular patterns in graph-structured data. Most unsupervised GNN-based methods rely on the homophily assumption that connected nodes share similar attributes. However, real-world graphs often exhibit attribute-level heterophily, where connected nodes have dissimilar attributes. Our analysis of attribute-level heterophily graphs reveals two phenomena indicating that current approaches are not practical for unsupervised graph anomaly detection: 1) attribute similarities between connected nodes show nearly identical distributions across different connected node pair types, and 2) anomalies cause consistent variation trends between the graph with and without anomalous edges in the low- and high-frequency components of the spectral energy distributions, while the mid-part exhibits more erratic variations. Based on these observations, we propose NK-GAD, a neighbor knowledge-enhanced unsupervised graph anomaly detection framework. NK-GAD integrates a joint encoder capturing both similar and dissimilar neighbor features, a neighbor reconstruction module modeling normal distributions, a center aggregation module refining node features, and dual decoders for reconstructing attributes and structures. Experiments on seven datasets show NK-GAD achieves an average 3.29\% AUC improvement. --- ### CPU Optimization of a Monocular 3D Biomechanics Pipeline for Low-Resource Deployment Authors: Yan Zhang, Xiong Zhao Published: 2026-04-17 Categories: cs.CV, cs.PF arXiv: https://arxiv.org/abs/2604.15665v1 Markerless 3D movement analysis from monocular video enables accessible biomechanical assessment in clinical and sports settings. However, most research-grade pipelines rely on GPU acceleration, limiting deployment on consumer-grade hardware and in low-resource environments. In this work, we optimize a monocular 3D biomechanics pipeline derived from the MonocularBiomechanics framework for efficient CPU-only execution. Through profiling-driven system optimization, including model initialization restructuring, elimination of disk I/O serialization, and improved CPU parallelization. Experiments on a consumer workstation (AMD Ryzen 7 9700X CPU) show a 2.47x increase in processing throughput and a 59.6\% reduction in total runtime, with initialization latency reduced by 4.6x. Despite these changes, biomechanical outputs remain highly consistent with the baseline implementation (mean joint-angle deviation 0.35$^\circ$, $r=0.998$). These results demonstrate that research-grade vision-based biomechanics pipelines can be deployed on commodity CPU hardware for scalable movement assessment. --- ### Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints Authors: Xinge Liu, Terry Jingchen Zhang, Bernhard Schölkopf, Zhijing Jin, Kristen Menou Published: 2026-04-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.15664v2 The rise of autonomous AI agents suggests that dynamic benchmark environments with built-in feedback on scientifically grounded tasks are needed to evaluate the capabilities of these agents in research work. We introduce Stargazer, a scalable environment for evaluating AI agents on dynamic, iterative physics-grounded model-fitting tasks using inference on radial-velocity (RV) time series data. Stargazer comprises 120 tasks across three difficulty tiers, including 20 real archival cases, covering diverse scenarios ranging from high-SNR single-planet systems to complex multi-planetary configurations requiring involved low-SNR analysis. Our evaluation of eight frontier agents reveals a gap between numerical optimization and adherence to physical constraints: although agents often achieve a good statistical fit, they frequently fail to recover correct physical system parameters, a limitation that persists even when agents are equipped with vanilla skills. Furthermore, increasing test-time compute yields only marginal gains, with excessive token usage often reflecting recursive failure loops rather than meaningful exploration. Stargazer presents an opportunity to train, evaluate, scaffold, and scale strategies on a model-fitting problem of practical research relevance today. Our methodology to design a simulation-driven environment for AI agents presumably generalizes to many other model-fitting problems across scientific domains. Source code and the project website are available at https://github.com/AIPS-UofT/Stargazer and https://aips-uoft.github.io/Stargazer/, respectively. --- ### CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval Authors: Jiahui Geng, Qing Li, Fengyu Cai, Fakhri Karray Published: 2026-04-17 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2604.15663v1 Code search, framed as information retrieval (IR), underpins modern software engineering and increasingly powers retrieval-augmented generation (RAG), improving code discovery, reuse, and the reliability of LLM-based coding. Yet existing code IR models remain largely text-centric and often overlook the visual and structural aspects inherent in programming artifacts such as web interfaces, data visualizations, SVGs, schematic diagrams, and UML. To bridge this gap, we introduce MMCoIR, the first comprehensive benchmark for evaluating multimodal code IR across five visual domains, eight programming languages, eleven libraries, and show the challenge of the task through extensive evaluation. Therefore, we then propose CodeMMR, a unified retrieval model that jointly embeds natural language, code, and images into a shared semantic space through instruction-based multimodal alignment. CodeMMR achieves strong generalization across modalities and languages, outperforming competitive baselines (e.g., UniIR, GME, VLM2Vec) by an average of 10 points on nDCG@10. Moreover, integrating CodeMMR into RAG enhances code generation fidelity and visual grounding on unseen code generation tasks, underscoring the potential of multimodal retrieval as a core enabler for next-generation intelligent programming systems. Datasets are available at HuggingFace. --- ### From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark Authors: Chen Zhao, Yunzhe Xu, Zhizhou Chen, Enxuan Gu, Kai Zhang, Xiaoming Liu, Jian Yang, Ying Tai Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15654v1 Ultra-high-definition (UHD) image restoration poses unique challenges due to the high spatial resolution, diverse content, and fine-grained structures present in UHD images. To address these issues, we introduce a progressive spectral decomposition for the restoration process, decomposing it into three stages: zero-frequency \textbf{enhancement}, low-frequency \textbf{restoration}, and high-frequency \textbf{refinement}. Based on this formulation, we propose a novel framework, \textbf{ERR}, which integrates three cooperative sub-networks: the zero-frequency enhancer (ZFE), the low-frequency restorer (LFR), and the high-frequency refiner (HFR). The ZFE incorporates global priors to learn holistic mappings, the LFR reconstructs the main content by focusing on coarse-scale information, and the HFR adopts our proposed frequency-windowed Kolmogorov-Arnold Network (FW-KAN) to recover fine textures and intricate details for high-fidelity restoration. To further advance research in UHD image restoration, we also construct a large-scale, high-quality benchmark dataset, \textbf{LSUHDIR}, comprising 82{,}126 UHD images with diverse scenes and rich content. Our proposed methods demonstrate superior performance across a range of UHD image restoration tasks, and extensive ablation studies confirm the contribution and necessity of each module. Project page: https://github.com/NJU-PCALab/ERR. --- ### Towards Realistic Open-Vocabulary Remote Sensing Segmentation: Benchmark and Baseline Authors: Bingyu Li, Tao Huo, Haocheng Dong, Da Zhang, Zhiyuan Zhao, Junyu Gao, Xuelong Li Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15652v2 Open-vocabulary remote sensing image segmentation (OVRSIS) remains underexplored due to fragmented datasets, limited training diversity, and the lack of evaluation benchmarks that reflect realistic geospatial application demands. Our previous \textit{OVRSISBenchV1} established an initial cross-dataset evaluation protocol, but its limited scope is insufficient for assessing realistic open-world generalization. To address this issue, we propose \textit{OVRSISBenchV2}, a large-scale and application-oriented benchmark for OVRSIS. We first construct \textbf{OVRSIS95K}, a balanced dataset of about 95K image--mask pairs covering 35 common semantic categories across diverse remote sensing scenes. Built upon OVRSIS95K and 10 downstream datasets, OVRSISBenchV2 contains 170K images and 128 categories, substantially expanding scene diversity, semantic coverage, and evaluation difficulty. Beyond standard open-vocabulary segmentation, it further includes downstream protocols for building extraction, road extraction, and flood detection, thereby better reflecting realistic geospatial application demands and complex deployment scenarios. We also propose \textbf{Pi-Seg}, a baseline for OVRSIS. Pi-Seg improves transferability through a \textbf{positive-incentive noise} mechanism, where learnable and semantically guided perturbations broaden the visual-text feature space during training. Extensive experiments on OVRSISBenchV1, OVRSISBenchV2, and downstream tasks show that Pi-Seg delivers strong and consistent results, particularly on the more challenging OVRSISBenchV2 benchmark. Our results highlight both the importance of realistic benchmark design and the effectiveness of perturbation-based transfer for OVRSIS. The code and datasets are available at \href{https://github.com/LiBingyu01/Pi-Seg}{LiBingyu01/Pi-Seg}. --- ### SPLIT: Self-supervised Partitioning for Learned Inversion in Nonlinear Tomography Authors: Markus Haltmeier, Lukas Neumann, Nadja Gruber, Gyeongha Hwang Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15651v1 Machine learning has achieved impressive performance in tomographic reconstruction, but supervised training requires paired measurements and ground-truth images that are often unavailable. This has motivated self-supervised approaches, which have primarily addressed denoising and, more recently, linear inverse problems. We address nonlinear inverse problems and introduce SPLIT (Self-supervised Partitioning for Learned Inversion in Nonlinear Tomography), a self-supervised machine-learning framework for reconstructing images from nonlinear, incomplete, and noisy projection data without any samples of ground-truth images. SPLIT enforces cross-partition consistency and measurement-domain fidelity while exploiting complementary information across multiple partitions. Our main theoretical result shows that, under mild conditions, the proposed self-supervised objective is equivalent to its supervised counterpart in expectation. We regularize training with an automatic stopping rule that halts optimization when a no-reference image-quality surrogate saturates. As a concrete application, we derive SPLIT variants for multispectral computed tomography. Experiments on sparse-view acquisitions demonstrate high reconstruction quality and robustness to noise, surpassing classical iterative reconstruction and recent self-supervised baselines. --- ### HyperGVL: Benchmarking and Improving Large Vision-Language Models in Hypergraph Understanding and Reasoning Authors: Yanbin Wei, Chun Kang, Siwei Li, Haoxuan Che, Yang Chen, Hua Liu, Jian Liu, Zhuang Liu, Can Ouyang, Fei Xing, Lei Sha, Rui Liu et al. Published: 2026-04-17 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2604.15648v1 Large Vision-Language Models (LVLMs) consistently require new arenas to guide their expanding boundaries, yet their capabilities with hypergraphs remain unexplored. In the real world, hypergraphs have significant practical applications in areas such as life sciences and social communities. Recent advancements in LVLMs have shown promise in understanding complex topologies, yet there remains a lack of a benchmark to delineate the capabilities of LVLMs with hypergraphs, leaving the boundaries of their abilities unclear. To fill this gap, in this paper, we introduce $\texttt{HyperGVL}$, the first benchmark to evaluate the proficiency of LVLMs in hypergraph understanding and reasoning. $\texttt{HyperGVL}$ provides a comprehensive assessment of 12 advanced LVLMs across 84,000 vision-language question-answering (QA) samples spanning 12 tasks, ranging from basic component counting to complex NP-hard problem reasoning. The involved hypergraphs contain multiscale synthetic structures and real-world citation and protein networks. Moreover, we examine the effects of 12 textual and visual hypergraph representations and introduce a generalizable router $\texttt{WiseHyGR}$ that improves LVLMs in hypergraph via learning adaptive representations. We believe that this work is a step forward in connecting hypergraphs with LVLMs. --- ### CIG: Measuring Conversational Information Gain in Deliberative Dialogues with Semantic Memory Dynamics Authors: Ming-Bin Chen, Jey Han Lau, Lea Frermann Published: 2026-04-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.15647v2 Measuring the quality of public deliberation requires evaluating not only civility or argument structure, but also the informational progress of a conversation. We introduce a framework for Conversational Information Gain (CIG) that evaluates each utterance in terms of how it advances collective understanding of the target topic. To operationalize CIG, we model an evolving semantic memory of the discussion: the system extracts atomic claims from utterances and incrementally consolidates them into a structured memory state. Using this memory, we score each utterance along three interpretable dimensions: Novelty, Relevance, and Implication Scope. We annotate 80 segments from two moderated deliberative settings (TV debates and community discussions) with these dimensions and show that memory-derived dynamics (e.g., the number of claim updates) correlate more strongly with human-perceived CIG than traditional heuristics such as utterance length or TF--IDF. We develop effective LLM-based CIG predictors paving the way for information-focused conversation quality analysis in dialogues and deliberative success. --- ### FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Use Authors: Suparno Roy Chowdhury, Tejas Anvekar, Manan Roy Choudhury, Muhammad Ali Khan, Kaneez Zahra Rubab Khakwani, Mohamad Bassam Sonbol, Irbaz Bin Riaz, Vivek Gupta Published: 2026-04-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.15646v1 Clinicians exploring oncology trial repositories often need ad-hoc, multi-constraint queries over biomarkers, endpoints, interventions, and time, yet writing SQL requires schema expertise. We demo FD-NL2SQL, a feedback-driven clinical NL2SQL assistant for SQLite-based oncology databases. Given a natural-language question, a schema-aware LLM decomposes it into predicate-level sub-questions, retrieves semantically similar expert-verified NL2SQL exemplars via sentence embeddings, and synthesizes executable SQL conditioned on the decomposition, retrieved exemplars, and schema, with post-processing validity checks. To improve with use, FD-NL2SQL incorporates two update signals: (i) clinician edits of generated SQL are approved and added to the exemplar bank; and (ii) lightweight logic-based SQL augmentation applies a single atomic mutation (e.g., operator or column change), retaining variants only if they return non-empty results. A second LLM generates the corresponding natural-language question and predicate decomposition for accepted variants, automatically expanding the exemplar bank without additional annotation. The demo interface exposes decomposition, retrieval, synthesis, and execution results to support interactive refinement and continuous improvement. --- ### Hybrid Quantum-Classical PINNs for Scientific Computing: A Multi-GPU Open-Source Framework Authors: Ziv Chen, Hemanth Chandravamsi, Shimon Pisnoy, Aaron Goldgewert, Gal Shaviner, Boris Shragner, Steven H. Frankel Published: 2026-04-17 Categories: cs.LG, physics.comp-ph, quant-ph arXiv: https://arxiv.org/abs/2604.15645v2 We present QPINNACLE, an open-source computational framework for physics-informed neural networks (PINNs) that integrates modern training strategies, multi-GPU acceleration, and hybrid quantum-classical architectures within a unified modular workflow. The framework enables systematic evaluation of PINN performance across benchmark problems including 1D hyperbolic conservation laws, incompressible flows, and electromagnetic wave propagation. It supports a range of architectural and training enhancements, including Fourier feature embeddings, random weight factorization, strict boundary condition enforcement, adaptive loss balancing, curriculum training, and second-order optimization strategies, with extensibility to additional methods. We provide a comprehensive benchmark study quantifying the impact of these methods on convergence, accuracy, and computational cost, and analyze distributed data parallel scaling in terms of runtime and memory efficiency. In addition, we extend the framework to hybrid quantum-classical PINNs and derive a formal estimate for circuit-evaluation complexity under parameter-shift differentiation. Results highlight the sensitivity of PINNs to architectural and training choices, confirm their high computational cost relative to classical solvers, and identify regimes where hybrid quantum models offer improved parameter efficiency. QPINNACLE provides a foundation for benchmarking physics-informed learning methods and guiding future developments through quantitative assessment of their trade-offs. --- ### PINNACLE: An Open-Source Computational Framework for Classical and Quantum PINNs Authors: Shimon Pisnoy, Hemanth Chandravamsi, Ziv Chen, Aaron Goldgewert, Gal Shaviner, Boris Shragner, Steven H. Frankel Published: 2026-04-17 Categories: cs.LG, physics.comp-ph, quant-ph arXiv: https://arxiv.org/abs/2604.15645v1 We present PINNACLE, an open-source computational framework for physics-informed neural networks (PINNs) that integrates modern training strategies, multi-GPU acceleration, and hybrid quantum-classical architectures within a unified modular workflow. The framework enables systematic evaluation of PINN performance across benchmark problems including 1D hyperbolic conservation laws, incompressible flows, and electromagnetic wave propagation. It supports a range of architectural and training enhancements, including Fourier feature embeddings, random weight factorization, strict boundary condition enforcement, adaptive loss balancing, curriculum training, and second-order optimization strategies, with extensibility to additional methods. We provide a comprehensive benchmark study quantifying the impact of these methods on convergence, accuracy, and computational cost, and analyze distributed data parallel scaling in terms of runtime and memory efficiency. In addition, we extend the framework to hybrid quantum-classical PINNs and derive a formal estimate for circuit-evaluation complexity under parameter-shift differentiation. Results highlight the sensitivity of PINNs to architectural and training choices, confirm their high computational cost relative to classical solvers, and identify regimes where hybrid quantum models offer improved parameter efficiency. PINNACLE provides a foundation for benchmarking physics-informed learning methods and guiding future developments through quantitative assessment of their trade-offs. --- ### HYPERHEURIST: A Simulated Annealing-Based Control Framework for LLM-Driven Code Generation in Optimized Hardware Design Authors: Shiva Ahir, Prajna Bhat, Alex Doboli Published: 2026-04-17 Categories: cs.AR, cs.AI arXiv: https://arxiv.org/abs/2604.15642v1 Large Language Models (LLMs) have shown promising progress for generating Register Transfer Level (RTL) hardware designs, largely because they can rapidly propose alternative architectural realizations. However, single-shot LLM generation struggles to consistently produce designs that are both functionally correct and power-efficient. This paper proposes HYPERHEURIST, a simulated annealing-based control framework that treats LLM-generated RTL as intermediate candidates rather than final designs. The suggested system not only focuses on functionality correctness but also on Power-Performance-Area (PPA) optimization. In the first phase, RTL candidates are filtered through compilation, structural checks, and simulation to identify functionally valid designs. PPA optimization is restricted to RTL designs that have already passed compilation and simulation. Evaluated across eight RTL benchmarks, this staged approach yields more stable and repeatable optimization behavior than single-pass LLM-generated RTL. --- ### Algebraic Invariants of Lightning Self-Attention Authors: Yulia Alexandr, Hao Duan, Guido Montúfar Published: 2026-04-17 Categories: math.AG, stat.ML arXiv: https://arxiv.org/abs/2604.15632v2 We study the polynomial coefficients of lightning self-attention as coordinates of an algebraic variety. In the single-token case, we characterize the coefficient variety as a rank-constrained Chow-type variety and derive algebraic equations from this description. For multiple tokens, linear relations reduce the nonlinear geometry to coefficients involving interactions between distinct tokens. We characterize the resulting variety by a common linear factor together with a low-rank condition on the remaining factors. This structure yields explicit families of determinantal, Veronese-type, and Sylvester resultant-based invariants. In the rank-one case, natural pencil and flattening equations define the variety set-theoretically. We complement these results with computations in small dimensions, where the theoretical constructions recover the generators of the defining ideals. Overall, the paper gives a structural description of the algebraic constraints imposed on polynomial coefficient arrays by lightning self-attention and provides explicit certificates of non-realizability. --- ### Algebraic Invariants of Lightning Self-Attention Authors: Yulia Alexandr, Hao Duan, Guido Montúfar Published: 2026-04-17 Categories: math.AG, stat.ML arXiv: https://arxiv.org/abs/2604.15632v1 We study the polynomial coefficients of lightning self-attention as coordinates of an algebraic variety. We identify linear and nonlinear families of algebraic invariants, including Chow-type, low-rank, Veronese-type, and Sylvester resultant-based constraints. --- ### Causal Bootstrapped Alignment for Unsupervised Video-Based Visible-Infrared Person Re-Identification Authors: Shuang Li, Jiaxu Leng, Changjiang Kuang, Mingpi Tan, Yu Yuan, Xinbo Gao Published: 2026-04-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2604.15631v1 VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images. However, existing approaches rely heavily on fully supervised learning with expensive cross-modality annotations, limiting scalability. To address this issue, we investigate Unsupervised Learning for VVI-ReID (USL-VVI-ReID), which learns identity-discriminative representations directly from unlabeled video tracklets. Directly extending image-based USL-VI-ReID methods to this setting with generic pretrained encoders leads to suboptimal performance. Such encoders suffer from weak identity discrimination and strong modality bias, resulting in severe intra-modality identity confusion and pronounced clustering granularity imbalance between visible and infrared modalities. These issues jointly degrade pseudo-label reliability and hinder effective cross-modality alignment. To address these challenges, we propose a Causal Bootstrapped Alignment (CBA) framework that explicitly exploits inherent video priors. First, we introduce Causal Intervention Warm-up (CIW), which performs sequence-level causal interventions by leveraging temporal identity consistency and cross-modality identity consistency to suppress modality- and motion-induced spurious correlations while preserving identity-relevant semantics, yielding cleaner representations for unsupervised clustering. Second, we propose Prototype-Guided Uncertainty Refinement (PGUR), which employs a coarse-to-fine alignment strategy to resolve cross-modality granularity mismatch, reorganizing under-clustered infrared representations under the guidance of reliable visible prototypes with uncertainty-aware supervision. Extensive experiments on the HITSZ-VCM and BUPTCampus benchmarks demonstrate that CBA significantly outperforms existing USL-VI-ReID methods when extended to the USL-VVI-ReID setting. --- ### SIMMER: Cross-Modal Food Image--Recipe Retrieval via MLLM-Based Embedding Authors: Keisuke Gomi, Keiji Yanai Published: 2026-04-17 Categories: cs.CV, cs.CL, cs.IR, cs.LG, cs.MM arXiv: https://arxiv.org/abs/2604.15628v1 Cross-modal retrieval between food images and recipe texts is an important task with applications in nutritional management, dietary logging, and cooking assistance. Existing methods predominantly rely on dual-encoder architectures with separate image and text encoders, requiring complex alignment strategies and task-specific network designs to bridge the semantic gap between modalities. In this work, we propose SIMMER (Single Integrated Multimodal Model for Embedding Recipes), which applies Multimodal Large Language Model (MLLM)-based embedding models, specifically VLM2Vec, to this task, replacing the conventional dual-encoder paradigm with a single unified encoder that processes both food images and recipe texts. We design prompt templates tailored to the structured nature of recipes, which consist of a title, ingredients, and cooking instructions, enabling effective embedding generation by the MLLM. We further introduce a component-aware data augmentation strategy that trains the model on both complete and partial recipes, improving robustness to incomplete inputs. Experiments on the Recipe1M dataset demonstrate that SIMMER achieves state-of-the-art performance across both the 1k and 10k evaluation settings, substantially outperforming all prior methods. In particular, our best model improves the 1k image-to-recipe R@1 from 81.8\% to 87.5\% and the 10k image-to-recipe R@1 from 56.5\% to 65.5\% compared to the previous best method. --- ### AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference Authors: Yiwei Zhao, Yi Zheng, Huapeng Su, Jieyu Lin, Stefano Ambrogio, Cijo Jose, Michael Ramamonjisoa, Patrick Labatut, Barbara De Salvo, Chiao Liu, Phillip B. Gibbons, Ziyun Li Published: 2026-04-17 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2604.15622v3 Always-on contextual AI runs language-aligned vision foundation models (VFMs) on edge devices, where the on-device model is the dominant continuous compute cost under strict latency and power limits. Due to an observed low-frequency shift in scene context and its relevant vocabulary, we present AdaDINO, an adaptive framework that makes on-device VFM inference efficient by matching execution to the current scene and task. We build on a known phenomenon, that the accuracy drop of shrinking model sizes depends on the task, and turn it into task-level adaptive execution. AdaDINO integrates neural architecture search (NAS) into a language-aligned VFM backbone distilled from DINOv2, training a single family of subnets for efficient execution during runtime. A multimodal large language model (LLM) on the cloud, invoked at low frequency, refines the candidate class set from scene context, while a learned selector activates the least-cost subnet predicted to retain a target fraction of accuracy. With the backbone and semantic pipeline held fixed, learned selection alone reduces average compute by $37\%$ over the best fixed subnet at equal segmentation accuracy. Across zero-shot classification and open-vocabulary segmentation, AdaDINO establishes a strong accuracy-efficiency frontier, improving over evaluated models of comparable sizes by up to $7.9\%$ in acc@1 on IN1K and $5.2\%$ mIoU on ADE20K, and reducing average FLOPs by up to $74.9\%$ at similar accuracy. --- ### Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking Authors: Jun Feng, Jiahui Tang, Zhicheng He, Hang Lv, Hongchao Gu, Hao Wang, Xuezhi Yang, Shuai Fang Published: 2026-04-17 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2604.15621v1 Adaptive Retrieval-Augmented Generation aims to mitigate the interference of extraneous noise by dynamically determining the necessity of retrieving supplementary passages. However, as Large Language Models evolve with increasing robustness to noise, the necessity of adaptive retrieval warrants re-evaluation. In this paper, we rethink this necessity and propose AdaRankLLM, a novel adaptive retrieval framework. To effectively verify the necessity of adaptive listwise reranking, we first develop an adaptive ranker employing a zero-shot prompt with a passage dropout mechanism, and compare its generation outcomes against static fixed-depth retrieval strategies. Furthermore, to endow smaller open-source LLMs with this precise listwise ranking and adaptive filtering capability, we introduce a two-stage progressive distillation paradigm enhanced by data sampling and augmentation techniques. Extensive experiments across three datasets and eight LLMs demonstrate that AdaRankLLM consistently achieves optimal performance in most scenarios with significantly reduced context overhead. Crucially, our analysis reveals a role shift in adaptive retrieval: it functions as a critical noise filter for weaker models to overcome their limitations, while serving as a cost-effective efficiency optimizer for stronger reasoning models. --- ### Majority Voting for Code Generation Authors: Tim Launer, Jonas Hübotter, Marco Bagatella, Ido Hakimi, Andreas Krause Published: 2026-04-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.15618v1 We investigate Functional Majority Voting (FMV), a method based on functional consensus for code generation with Large Language Models, which identifies a representative solution from multiple generations using their runtime execution signatures on test inputs. We find that FMV is an effective test-time inference strategy, substantially boosting performance on LiveCodeBench without a large compute overhead. Furthermore, we extend the utility of functional consensus and apply it as an aggregation strategy for label-free Test-Time Reinforcement Learning. We demonstrate that this increases pass@1 on holdout tasks, but find no evidence of self-improvement beyond the base model's performance ceiling. --- ### A Structure-Preserving Graph Neural Solver for Parametric Hyperbolic Conservation Laws Authors: Jiamin Jiang, Shanglin Lv, Jingrun Chen Published: 2026-04-17 Categories: physics.comp-ph, cs.LG, math.NA arXiv: https://arxiv.org/abs/2604.15617v1 Hyperbolic conservation laws govern a wide range of transport-driven dynamics featuring shocks, contact discontinuities, and complex wave interactions, posing distinct challenges for deep-learning-based surrogate modeling. While classical numerical methods provide robust and physically admissible solutions, their computational cost restricts applicability in many-query tasks such as parametric studies and design optimization. Conversely, existing neural surrogates offer rapid inference but often fail to respect intrinsic PDE structures, leading to non-physical artifacts, rollout instability, and poor generalization. We present an interpretable, structure-preserving graph neural solver that bridges classical numerical principles with graph neural networks (GNNs). The network is designed as a learned reconstruction-and-flux operator rather than a black-box state updater, thereby inherently preserving key properties such as local conservation and upwinding. Inspired by Arbitrary high-order DERivatives schemes, we further recast message-passing GNNs as high-order space-time predictors, enabling conservative and stable neural updates with large time steps. Evaluation is performed on challenging supersonic flow benchmarks spanning broad parametric variations in geometry, initial/boundary conditions, and flow regimes. The neural solver achieves superior long-horizon rollout stability and accuracy compared with strong surrogate baselines, outperforms low-order discretizations, and delivers orders-of-magnitude runtime speedups over high-resolution simulations. --- ### Flexible Empowerment at Reasoning with Extended Best-of-N Sampling Authors: Taisuke Kobayashi Published: 2026-04-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2604.15614v1 This paper proposes a novel method that incorporates empowerment when reasoning actions in reinforcement learning (RL), thereby achieving the flexibility of exploration-exploitation dilemma (EED). In previous methods, empowerment for promoting exploration has been provided as a bonus term to the task-specific reward function as an intrinsically-motivated RL. However, this approach introduces a delay until the policy that accounts for empowerment is learned, making it difficult to adjust the emphasis on exploration as needed. On the other hand, a trick devised for fine-tuning recent foundation models at reasoning, so-called best-of-N (BoN) sampling, allows for the implicit acquisition of modified policies without explicitly learning them. It is expected that applying this trick to exploration-promoting terms, such as empowerment, will enable more flexible adjustment of EED. Therefore, this paper investigates BoN sampling for empowerment. Furthermore, to adjust the degree of policy modification in a generalizable manner while maintaining computational cost, this paper proposes a novel BoN sampling method extended by Tsalis statistics. Through toy problems, the proposed method's cability to balance EED is verified. In addition, it is demonstrated that the proposed method improves RL performance to solve complex locomotion tasks. --- ### Green-ELM: Efficient Analytic Learning via High-Dimensional Random Projections Authors: Wladimir Silva Published: 2026-04-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.15613v4 We present Green-ELM, a non-iterative neural architecture that replaces gradient-based optimization of the output layer with a closed-form analytic solution over a fixed, high-dimensional random feature representation. By projecting input manifolds into a high-dimensional, random feature space ($d \gg 784$), our results show that complex class boundaries can be effectively untangled without the computational overhead of backpropagation. Utilizing the Moore-Penrose pseudoinverse, LU and Cholesky decomposition to solve for the output layer in a single analytic step, Green-ELM achieves a classification accuracy of 98.10\% on MNIST ($d=4000$) and 86.63\% on Fashion-MNIST. Furthermore, we experiment with a pre-trained ``frozen-backbone'' based on ResNet-18 to extract high-quality features and show that these one-shot solvers are effective beyond simple datasets. Notably, our baseline CPU configuration on MNIST ($d=2000$) achieves 97.15% accuracy in 1.5s, representing a 11.6$\times$ reduction in reported training time over an SGD baseline while maintaining comparable performance. We observe a near-logarithmic scaling behavior between dimensionality and accuracy, where the accuracy increases approximately logarithmically with hidden dimensionality over the tested range, suggesting that feature-space expansion contributes substantially to performance in these experiments. . This one-shot linear matrix solver approach offers a viable alternative for real-time Edge AI, where the traditional training phase is bypassed in favor of non-iterative manifold representation and readout. Finally, we propose an Empirical Scaling Hypothesis, a framework that models accuracy bounds as a function of high dimensionality and intrinsic dataset complexity. --- ### VoodooNet: Achieving Analytic Ground States via High-Dimensional Random Projections Authors: Wladimir Silva Published: 2026-04-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2604.15613v3 We present VoodooNet, a non-iterative neural architecture that replaces the stochastic gradient descent (SGD) paradigm with a closed-form analytic solution via Galactic Expansion. By projecting input manifolds into a high-dimensional, high-entropy "Galactic" space ($d \gg 784$), we demonstrate that complex features can be untangled without the thermodynamic cost of backpropagation. Utilizing the Moore-Penrose pseudoinverse to solve for the output layer in a single step, VoodooNet achieves a classification accuracy of \textbf{98.10\% on MNIST} and \textbf{86.63\% on Fashion-MNIST}. Notably, our results on Fashion-MNIST surpass a 10-epoch SGD baseline (84.41\%) while reducing the training time by orders of magnitude. We observe a near-logarithmic scaling law between dimensionality and accuracy, suggesting that performance is a function of "Galactic" volume rather than iterative refinement. This "Magic Hat" approach offers a new frontier for real-time Edge AI, where the traditional training phase is bypassed in favor of instantaneous manifold discovery. --- ### GaussianFlow SLAM: Monocular Gaussian Splatting SLAM Guided by GaussianFlow Authors: Dong-Uk Seo, Jinwoo Jeon, Eungchang Mason Lee, Hyun Myung Published: 2026-04-17 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2604.15612v1 Gaussian splatting has recently gained traction as a compelling map representation for SLAM systems, enabling dense and photo-realistic scene modeling. However, its application to monocular SLAM remains challenging due to the lack of reliable geometric cues from monocular input. Without geometric supervision, mapping or tracking could fall in local-minima, resulting in structural degeneracies and inaccuracies. To address this challenge, we propose GaussianFlow SLAM, a monocular 3DGS-SLAM that leverages optical flow as a geometry-aware cue to guide the optimization of both the scene structure and camera poses. By encouraging the projected motion of Gaussians, termed GaussianFlow, to align with the optical flow, our method introduces consistent structural cues to regularize both map reconstruction and pose estimation. Furthermore, we introduce normalized error-based densification and pruning modules to refine inactive and unstable Gaussians, thereby contributing to improved map quality and pose accuracy. Experiments conducted on public datasets demonstrate that our method achieves superior rendering quality and tracking accuracy compared with state-of-the-art algorithms. The source code is available at: https://github.com/url-kaist/gaussianflow-slam. --- ### CLIMB: Controllable Longitudinal Brain Image Generation using Mamba-based Latent Diffusion Model and Gaussian-aligned Autoencoder Authors: Duy-Phuong Dao, Muhammad Taqiyuddin, Jahae Kim, Sang-Heon Lee, Hye-Won Jung, Jaehoo Choi, Hyung-Jeong Yang Published: 2026-04-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2604.15611v1 Latent diffusion models have emerged as powerful generative models in medical imaging, enabling the synthesis of high quality brain magnetic resonance imaging scans. In particular, predicting the evolution of a patients brain can aid in early intervention, prognosis, and treatment planning. In this study, we introduce CLIMB, Controllable Longitudinal brain Image generation via state space based latent diffusion model, an advanced framework for modeling temporal changes in brain structure. CLIMB is designed to model the structural evolution of the brain structure over time, utilizing a baseline MRI scan and its acquisition age as foundational inputs. Additionally, multiple conditional variables, including projected age, gender, disease status, genetic information, and brain structure volumes, are incorporated to enhance the temporal modeling of anatomical changes. Unlike existing LDM methods that rely on self attention modules, which effectively capture contextual information from input images but are computationally expensive, our approach leverages state space, a state space model architecture that substantially reduces computational overhead while preserving high-quality image synthesis. Furthermore, we introduce a Gaussian-aligned autoencoder that extracts latent representations conforming to prior distributions without the sampling noise inherent in conventional variational autoencoders. We train and evaluate our proposed model on the Alzheimers Disease Neuroimaging Initiative dataset, consisting of 6,306 MRI scans from 1,390 participants. By comparing generated images with real MRI scans, CLIMB achieves a structural similarity index of 0.9433, demonstrating notable improvements over existing methods. --- ### Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models Authors: Yunbei Zhang, Shuaicheng Niu, Chengyi Cai, Feng Liu, Jihun Hamm Published: 2026-04-17 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2604.15609v1 Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limited adaptive capacity, while Zeroth-Order Optimization (ZOO) enables input-space adaptation but faces high query costs and optimization challenges in the unsupervised TTA setting. We introduce BETA (Black-box Efficient Test-time Adaptation), a framework that addresses these limitations by employing a lightweight, local white-box steering model to create a tractable gradient pathway. Through a prediction harmonization technique combined with consistency regularization and prompt learning-oriented filtering, BETA enables stable adaptation with no additional API calls and negligible latency beyond standard inference. On ImageNet-C, BETA achieves a +7.1% accuracy gain on ViT-B/16 and +3.4% on CLIP, surpassing strong white-box and gray-box methods including TENT and TPT. On a commercial API, BETA achieves comparable performance to ZOO at 250x lower cost while maintaining real-time inference speed, establishing it as a practical and efficient solution for real-world black-box TTA. --- ### Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies Authors: Myke C. Cohen, Mingqian Zheng, Neel Bhandari, Hsien-Te Kao, Xuhui Zhou, Daniel Nguyen, Laura Cassani, Maarten Sap, Svitlana Volkova Published: 2026-04-17 Categories: cs.CL, cs.AI, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2604.15607v1 AI design characteristics and human personality traits each impact the quality and outcomes of human-AI interactions. However, their relative and joint impacts are underexplored in imperfectly cooperative scenarios, where people and AI only have partially aligned goals and objectives. This study compares a purely simulated dataset comprising 2,000 simulations and a parallel human subjects experiment involving 290 human participants to investigate these effects across two scenario categories: (1) hiring negotiations between human job candidates and AI hiring agents; and (2) human-AI transactions wherein AI agents may conceal information to maximize internal goals. We examine user Extraversion and Agreeableness alongside AI design characteristics, including Adaptability, Expertise, and chain-of-thought Transparency. Our causal discovery analysis extends performance-focused evaluations by integrating scenario-based outcomes, communication analysis, and questionnaire measures. Results reveal divergences between purely simulated and human study datasets, and between scenario types. In simulation experiments, personality traits and AI attributes were comparatively influential. Yet, with actual human subjects, AI attributes -- particularly transparency -- were much more impactful. We discuss how these divergences vary across different interaction contexts, offering crucial insights for the future of human-centered AI agents. --- ### GroupDPO: Memory-Efficient Group-Wise Direct Preference Optimization Authors: Jixuan Leng, Si Si, Hsiang-Fu Yu, Vinod Raman, Inderjit S. Dhillon Published: 2026-04-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.15602v2 Preference optimization is widely used to align Large Language Models (LLMs) with preference feedback. However, most existing methods train on a single positive-negative pair per prompt, discarding additional supervision available in preference datasets that typically contain multiple candidate responses. Motivated by this limitation, recent work explores group-wise preference optimization, which jointly contrasts multiple responses for the same prompt, but its empirical behavior and scalability remain underexplored due to the memory overhead of group-coupled objectives. In this work, we present a unified empirical and systems study of group-wise preference optimization and develop a memory-efficient implementation for group-coupled objectives. By instantiating first-order linearization with objective-specific per-response coefficients, our implementation preserves first-order gradients while decoupling samples during backpropagation, substantially reducing peak memory usage and enabling scalable training with larger groups. Across offline and online settings, we show that leveraging multiple responses consistently outperforms single-pair training. Furthermore, incorporating a negative log-likelihood (NLL) term on positive responses is critical for both performance gains and training stability. --- ### GroupDPO: Memory efficient Group-wise Direct Preference Optimization Authors: Jixuan Leng, Si Si, Hsiang-Fu Yu, Vinod Raman, Inderjit S. Dhillon Published: 2026-04-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2604.15602v1 Preference optimization is widely used to align Large Language Models (LLMs) with preference feedback. However, most existing methods train on a single positive-negative pair per prompt, discarding additional supervision available in preference datasets that typically contain multiple candidate responses. Motivated by this limitation, recent work explores group-wise preference optimization, which jointly contrasts multiple responses for the same prompt, but its empirical behavior and scalability remain underexplored due to the memory overhead of group-coupled objectives. In this work, we introduce a memory-efficient group-wise preference optimization algorithm that preserves gradients while decoupling samples during backpropagation, substantially reducing peak memory usage, which enables scalable training with larger group sizes. Across both offline and online alignment settings, we show that leveraging multiple responses consistently outperforms single-pair training. Furthermore, incorporating a negative log-likelihood (NLL) term on positive responses is critical for both performance gains and training stability. --- ### LLMs Corrupt Your Documents When You Delegate Authors: Philippe Laban, Tobias Schnabel, Jennifer Neville Published: 2026-04-17 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2604.15597v1 Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation that the LLM will faithfully execute the task without introducing errors into documents. We introduce DELEGATE-52 to study the readiness of AI systems in delegated workflows. DELEGATE-52 simulates long delegated workflows that require in-depth document editing across 52 professional domains, such as coding, crystallography, and music notation. Our large-scale experiment with 19 LLMs reveals that current models degrade documents during delegation: even frontier models (Gemini 3.1 Pro, Claude 4.6 Opus, GPT 5.4) corrupt an average of 25% of document content by the end of long workflows, with other models failing more severely. Additional experiments reveal that agentic tool use does not improve performance on DELEGATE-52, and that degradation severity is exacerbated by document size, length of interaction, or presence of distractor files. Our analysis shows that current LLMs are unreliable delegates: they introduce sparse but severe errors that silently corrupt documents, compounding over long interaction. --- ### DataCenterGym: A Physics-Grounded Simulator for Multi-Objective Data Center Scheduling Authors: Nilavra Pathak, Samadrita Biswas, Nirmalya Roy Published: 2026-04-17 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2604.15594v1 Modern datacenters schedule heterogeneous workloads across geo-distributed sites with diverse compute capacities, electricity prices, and thermal conditions. Compute utilization, heat generation, cooling demand, and energy consumption are tightly coupled, yet most existing schedulers abstract these effects and treat them independently. We present \textit{DataCenterGym}, a physics-grounded simulation environment for job scheduling in geo-distributed data centers, designed as a reusable testbed for future research. The simulator integrates compute queueing, building thermal dynamics, localized HVAC behavior, and temperature-dependent service degradation within a Gymnasium-compatible interface. We also develop a Hierarchical Model Predictive Control (H-MPC) scheduling algorithm that performs distributed job placement while explicitly accounting for thermal and power dynamics. Through experiments on nominal operation and workload sensitivity, we demonstrate how H-MPC improves scheduling performance relative to baseline schedulers. --- ### DALM: A Domain-Algebraic Language Model via Three-Phase Structured Generation Authors: Chao Li Published: 2026-04-17 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.15593v1 Large language models compress heterogeneous knowledge into a single parameter space, allowing facts from different domains to interfere during generation. We propose DALM, a Domain-Algebraic Language Model that replaces unconstrained token generation with structured denoising over a domain lattice. DALM follows a three-phase generation path: it first resolves domain uncertainty, then relation uncertainty, and finally concept uncertainty, so each stage operates under explicit algebraic constraints. The framework requires only three ingredients: a lattice of domains with computable meet, join, and implication; a typing function over relations that controls inheritance across domains; and a fiber partition that localizes knowledge to domain-specific subsets. Given these ingredients, DALM yields a three-phase encoder-decoder architecture in which generation is confined to a domain fiber, cross-domain contamination is structurally prevented in closed-vocabulary mode and auditably bounded in open-vocabulary mode, and a single query can produce a domain-indexed multi-perspective answer space. We instantiate the framework with the CDC knowledge representation system and outline training and evaluation on validated domain-annotated crystal libraries. DALM reframes language generation as algebraically constrained structured denoising rather than unconstrained decoding over a flat token space. --- ### BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels Authors: Mengfei Lan, Lecheng Zheng, Halil Kilicoglu Published: 2026-04-17 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.15591v2 Effective biomedical information retrieval requires modeling domain semantics and hierarchical relationships among biomedical texts. Existing biomedical generative retrievers build on coarse binary relevance signals, limiting their ability to capture semantic overlap. We propose BioHiCL (Biomedical Retrieval with Hierarchical Multi-Label Contrastive Learning), which leverages hierarchical MeSH annotations to provide structured supervision for multi-label contrastive learning. Our models, BioHiCL-Base (0.1B) and BioHiCL-Large (0.3B), achieve promising performance on biomedical retrieval, sentence similarity, and question answering tasks, while remaining computationally efficient for deployment. --- ### Scaffolding Critical Engagement with GenAI: Transforming Ethnic Minority Preparatory Students' Collaborative Discourse in Prompt Engineering Tasks Authors: Deliang Wang, Cunling Bian Published: 2026-04-16 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.28630v1 Generative AI (GenAI) holds significant promise for advancing educational equity among ethnic minority students by broadening access to learning resources and mitigating linguistic barriers. However, these benefits are counterbalanced by the risk of cognitive laziness, whereby students may treat GenAI as an answer engine or shortcut rather than as a partner in thinking. This design-based research investigated how pedagogical scaffolding can shift students from passive consumption to critical co-creation with GenAI. The study involved 78 ethnic minority preparatory students in China participating in a three-week GenAI course that integrated a human-in-the-loop workflow and teacher modeling with contrasting cases to disrupt uncritical reliance on GenAI. We employed epistemic network analysis to examine collaborative discourse, thematic analysis to analyze student reflections, and paired-samples t-tests to assess changes in prompt self-efficacy. Results revealed a phenomenon of strategic repurposing: initially, students instrumentalized strategy talk to coordinate efficient copying; however, after the intervention, they realigned strategic planning to scaffold critical evaluation and peer co-construction. Qualitative findings further indicated that the teacher's scaffolding helped students overcome their initial authority bias and prompt paralysis, repositioning themselves as active gatekeepers of AI-generated content; these shifts were corroborated by a significant increase in students' prompt self-efficacy. The study suggests that, particularly for ethnic minority students, technical training alone is insufficient; educators should design targeted pedagogical interventions around human-AI collaboration to prevent cognitive complacency and cultivate epistemic agency. --- ### OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systems Authors: Konstantinos I. Roumeliotis, Ranjan Sapkota Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.28629v1 The rapid transition from reactive large language models (LLMs) to persistent, action-capable systems has exposed critical gaps in the architectural understanding of Agentic AI, particularly in separating inference, orchestration, and execution layers for autonomous AI agents. Despite recent advances, unified frameworks for designing and evaluating full-stack agentic systems remain limited. This paper presents a comprehensive, layered architecture for Agentic AI, outlining the evolution from reactive LLM interfaces to persistent, goal-driven autonomous AI agents with memory, planning, and continuous execution. We analyze OpenClaw and Ollama as a full-stack Agentic AI system, where Ollama serves as the LLM inference layer and OpenClaw enables agent runtime orchestration, integrating reasoning, tool use, and action execution. A prototype experimental validation of the OpenClaw-Ollama architecture demonstrates that capabilities such as persistent memory, tool utilization, and adaptive decision-making emerge from system-level integration rather than standalone models, with performance improving consistently as architectural complexity increases. The study further examines challenges in scalability, security, privacy, governance, and evaluation of agentic systems, highlighting the need for robust benchmarking and system-level design. Future directions include scalable multi-agent architectures, distributed autonomous systems, and human-aware Agentic AI frameworks for responsible deployment. Overall, this work establishes a unified architectural foundation for Agentic AI, validates the effectiveness of full-stack autonomous AI agents, and provides a roadmap for building scalable, secure, and trustworthy agentic systems. All models, code, and datasets are publicly released to support reproducibility and benchmarking. --- ### Design and Embedded Validation of Compact ML Models for Affective Touch Classification in a Soft Interactive Companion Authors: Aleksandrs Vališevskis, Aleksandrs Okss, Inese Tīģere, Aleksejs Kataševs, Dina Bethere, Anete Hofmane, Airisa Šteinberga, Undīne Gavriļenko, Santa Meļķe, Lucie Matouškova Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.16196v2 Soft plush companions provide a safe and intuitive platform for affective human-robot interaction, but their deformable structure and distributed tactile signals make reliable gesture recognition difficult. This study presents a complete workflow for developing and validating compact affective-touch classifiers for an interactive plush companion. A newly collected dataset comprised 1,326 labelled recordings before curation, including interactions from 25 children, teenagers, and adults. Each classifier received 2.5-s windows containing ten capacitive channels and one accelerometer-magnitude channel. MATLAB supported acquisition, quality control, window generation, and a 468-run exploratory study of dilated one-dimensional convolutional neural networks (1D CNNs). A closely matched Python workflow then preserved participant provenance, fitted preprocessing inside each fold, and evaluated shortlisted models by 25-fold leave-one-subject-out cross-validation (LOSO-CV). On the operational 10-class task, the compact dilated CNN achieved 81.96% mean macro-F1 and 85.42% mean accuracy. The depthwise-separable CNN achieved the strongest neural result (84.50% macro-F1), whereas a linear support-vector machine using 66 predefined time-domain features achieved the best overall result (87.98% macro-F1 and 91.05% mean accuracy). Paired fold analysis showed that the linear support-vector machine and constrained random forest outperformed the compact dilated CNN, whereas differences among the tested neural models were not statistically significant after correction. Direct measurements on a 240-MHz ESP32-S3 confirmed valid deployment of the dilated CNN, depthwise-separable CNN, temporal convolutional network, linear support-vector machine, and random forest; the linear model required a 3.2 kB serialized payload and 1.405 ms mean end-to-end classifier time. --- ### Design and Validation of a Lightweight 1D CNN for Affective Touch Classification in Soft Plush Companions Authors: Aleksandrs Vališevskis, Aleksandrs Okss, Inese Tīģere, Aleksejs Kataševs, Dina Bethere, Anete Hofmane, Airisa Šteinberga, Undīne Gavriļenko, Santa Meļķe, Lucie Matoušková Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.16196v1 Soft, sensorized companions offer a physically safe and emotionally intuitive interface for socially assistive technologies, yet their deformability and multichannel tactile sensing complicate the robust interpretation of human affect. This study presents a complete open-source MATLAB-based framework for the development and validation of compact deep learning models for affective touch recognition in soft interactive companions. As a primary contribution, a diverse FAIR-compliant dataset of 1326 labelled gesture sequences collected from 25 participants spanning children, teenagers, and adults is made publicly available, providing a reusable resource for future research in affective touch recognition. Through systematic architecture and hyperparameter exploration across 468 CNN models, the study identifies compact dilated one-dimensional convolutional neural networks (1D CNNs) as the most effective solution, with a 13.2k-parameter model achieving 75% test accuracy and 85% mean leave-one-subject-out cross-validation accuracy. Theoretical inference-time analysis shows that quantized deployment requires 3.2 MMAC per window, compatible with 20 Hz real-time operation on the target microcontroller. PC-based real-time simulation with the physical toy streaming sensor data demonstrates that the CNN resolves subtle social touches that the previous heuristic system failed to detect, whereas high-force negative interactions are captured more reliably by trivial threshold-based logic. The resulting hybrid inference pipeline - instantaneous heuristic filtering followed by CNN-based nuanced gesture classification - is proposed as the embedded deployment strategy. The study demonstrates that emotionally meaningful, privacy-preserving touch interpretation is computationally feasible for direct embedding within soft therapeutic companions, with hardware integration addressed in a forthcoming study. --- ### RegNetAgents: A Multi-Agent Framework for Cross-Network Regulatory Driver Identification in Cancer Genomics Authors: Jose A. Bird Published: 2026-04-16 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.14097v2 We introduce RegNetAgents, an AI-oriented multi-agent framework for structured, query-driven regulatory candidate identification across heterogeneous gene regulatory networks. The system enables unified analysis of bulk tumor and single-cell-derived ARACNe networks by integrating TCGA-derived cancer networks with large-scale single-cell regulatory networks from the GREmLN project. For a given focal gene, the framework performs dual-network classification, cancer gene filtering using OncoKB annotations, and mode-of-action (MoA) assignment for tumor-derived regulatory relationships. Candidates are ranked by evidence consistency across networks (Both, TCGA-only, GREmLN-only). The system is implemented as a multi-agent LangGraph DAG workflow, accessible through a unified Python API and Model Context Protocol (MCP) client, operating as a downstream analytical layer over precomputed regulatory networks rather than a network inference method. Across eleven breast cancer (BRCA) and twelve colorectal cancer (COAD) focal genes, RegNetAgents identifies candidate regulators significantly enriched for OncoKB-annotated cancer genes. TCGA-derived candidates show strong enrichment (Stouffer Z = 6.69 for BRCA and 6.95 for COAD), while GREmLN-derived candidates also demonstrate significant enrichment (Z = 5.51 for BRCA and 7.06 for COAD; all p < 0.0001). No enrichment is observed in housekeeping or non-driver control gene sets, supporting signal specificity. An extended module enables structured evaluation of oncogenic potential, druggability, clinical relevance, and network vulnerability, supporting end-to-end interpretation from candidate identification to biological hypothesis generation. RegNetAgents establishes an interpretable AI framework for cross-network regulatory candidate identification in cancer genomics. ---