# Research Papers — 2026-06 · bundle page 46 of 260 > Full-text markdown of papers #2251–2300 of 12993 published in 2026-06, newest first. AI-readable mirrors of the full 12993-paper 2026-06 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-06/page/46 [← Previous bundle](https://aipod.dev/papers/archive/2026-06/page/45.md) [Next bundle →](https://aipod.dev/papers/archive/2026-06/page/47.md) ### Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT Authors: Jinghan Wang, Yanjun Chen, Wei Zhang, Xiaotong Huang, Tianchen Liu, Gaoliang Peng Published: 2026-06-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26861v1 Deploying large language models (LLMs) on Industrial Internet of Things (IIoT) edge devices demands extreme compression, yet existing structured pruning methods collapse at high compression ratios due to one-shot importance estimation, and their cross-architecture behavior remains unpredictable. This article presents a cascaded multi-granularity pruning framework that removes layers, attention heads, and feed-forward channels in coarse-to-fine order, with lightweight low-rank recovery between stages to re-estimate component importance. An information-theoretic analysis motivates this ordering, and the Structural Independence Assumption (SIA) is formalized as a checkable condition predicting whether per-component pruning criteria are reliable for a given architecture: Multi-Head Attention (MHA)+GELU designs satisfy the SIA, whereas Grouped Query Attention (GQA)+SwiGLU designs violate it. On bearing fault diagnosis spanning 88M to 6.25B-parameter models, the framework extends achievable compression to 13.8 times on MHA+GELU architectures with 83.82% accuracy (+3.70 percentage points (pp) over the strongest baseline), while exposing a ~74pp accuracy collapse on GQA+SwiGLU architectures that violate the SIA. Deployed on an industrial slewing bearing fault diagnosis platform with NVIDIA DGX Spark, compressed models reduce inference latency by up to 67.2% and peak memory by 62.5%, demonstrating viability for IIoT edge inference. --- ### AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems Authors: Changxin Lao, Fei Pan, Guozhuang Ma, Han Li, Huihuang Lin, Jijun Shi, Kangzhi Zhao, Kun Gai, Mo Zhou, Qinqin Zhou, Quan Chen, Ruochen Yang et al. Published: 2026-06-25 Categories: cs.AI, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2606.26859v2 Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results. Innovation therefore scales linearly with headcount rather than compounding with evidence, compute, and accumulated experimental knowledge. We present AgentX, a production-deployed multi-agent system that fundamentally restructures this production function. AgentX operates as a self-evolving development engine: it autonomously generates, implements, evaluates, and learns from recommendation experiments at a scale and pace that no manual workflow can sustain. The system orchestrates four tightly coupled stages in a closed loop. A Brainstorm Agent synthesizes evidence from historical experiments, system architecture, data analysis, and external research into ranked, executable proposals. A Developing Agent translates each proposal into production-ready code through repository-grounded generation and multi-dimensional reliability verification. An Evaluation Agent conducts safe online rollout with guardrail-vetoed A/B judgment, converting both successes and failures into structured knowledge assets. A Harness Evolution layer (SGPO) then distills execution trajectories into semantic-gradient updates that continuously sharpen the agents themselves -- making the system not merely automated, but self-improving. --- ### LCAi: Life Cycle Assessment with big data fusion and retrieval-augmented generation-assisted interpretation Authors: Georgios Tsironis, Juan D. Medrano-Garcia, Gonzalo Guillen-Gosalbez Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26857v1 The interpretation phase of life cycle assessment often lacks structured mechanisms for translating quantified improvement opportunities addressing environmental hotspots into actionable strategic pathways under technological, social, and policy uncertainty. To overcome this limitation, this study introduces a perspective-conditioned retrieval-augmented generation framework for LCA interpretation, where a multi-perspective retrieval and controlled synthesis is incorporated in the artificial intelligence (AI)-assisted LCA. To operationalise large language models in LCA interpretation, a perspective fusion RAG architecture was developed, covering academic, industry, public discourse, and European union (EU) funding datasets. Our approach comprises three steps: (1) a scenario anchor defining system boundaries and decarbonization targets, (2) a set of perspective-specific micro-queries with constrained retrieval, and (3) a neutral synthesis step integrating only ledger-stored outputs without further retrieval. The framework is demonstrated through a hydrogen-enabled diesel reduction use case in an Italian apple production facility using GPT-5 nano as the reasoning model. Overall, the structured retrieval and constrained synthesis are designed to mitigate the risk of hallucination while preserving cross-domain diversity. The approach presented can support more disciplined translation of impact results into strategic pathways and opens up new avenues for the use of advanced AI tools in LCA studies, particularly those focused on technologies that could be deployed at scale. This proof-of-concept demonstrates how AI-assisted, evidence-grounded interpretation can support implementation-oriented decision-making beyond conventional LCA studies. --- ### Context-Aware Synthesis of Optimization Pipelines for Warehouse Optimization Authors: Janik Bischoff, Anne Meyer, Uta Mohring, Fabian Dunke, Maximilian Barlang, Özge Nur Subas, Hadi Kutabi, Stefan Nickel, Kai Furmans Published: 2026-06-25 Categories: cs.AI, cs.SE arXiv: https://arxiv.org/abs/2606.26852v1 Order fulfillment in manual picker-to-goods warehouses involves interconnected decisions such as item assignment, order batching, and picker routing. While integrated models capture interactions between these decisions, practical warehouse systems often require decomposed approaches due to organizational boundaries, differing responsibilities, or limited data availability. Existing studies primarily evaluate algorithms for isolated subproblems or fixed subproblem combinations for specific warehouse settings, but lack a general mechanism to determine applicable algorithm configurations, compose them into valid solution pipelines, and assess their performance. With Context-Aware Synthesis of Optimization Pipelines (CASOP), we propose a framework for constructing and evaluating context-specific optimization pipelines and apply these to order fulfillment. The framework comprises: (1) a modular repository of algorithms for common order fulfillment problems; (2) semantic data and algorithm cards to describe warehouse context and algorithm requirements; (3) a taxonomy that structures order fulfillment problems into relevant subproblems; (4) a pipeline synthesizer that identifies applicable algorithms for a given warehouse context and composes all valid optimization pipelines; and (5) a pipeline evaluator that assesses all resulting pipelines. We demonstrate the framework on 7 benchmark instance sets covering four problem classes, resulting in 1,063,044 valid pipelines. The framework supports researchers and practitioners in designing, automatically synthesizing, and selecting valid, high-performing algorithmic pipelines for warehouse operations. The software is open-source and available at https://github.com/kit-dsm/ware_ops_pipes and https://github.com/kit-dsm/ware_ops_algos. Keywords: Warehouse optimization, Algorithm selection, Pipeline synthesis, Order fulfillment --- ### Appearance-Preserving Refinement of Generated 3D Assets for Monochromatic Fabrication Authors: Chentao Shen, Chen Jia, Mingjie Huang, Zhuang Zhang, Haisen Zhao, Xiangru Huang Published: 2026-06-25 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2606.26850v2 Recent advances in 3D mesh generation have enabled the creation of visually realistic assets. However, much of their visual fidelity is encoded in textures rather than geometry. When such assets are fabricated using monochromatic materials, texture information is largely lost, causing visually important details to disappear even when the original geometry is faithfully preserved. A key challenge is that the geometric perturbations required to recover texture-dependent appearance cues often introduce sharp local features and high-frequency surface structures, which may increase stress concentration and fabrication risk. In this paper, we present GenMF, an appearance-oriented geometry refinement framework for monochromatic fabrication. GenMF transforms texture-dependent visual cues into geometry-induced shading effects and formulates geometry refinement as a balance between appearance preservation and fabrication-oriented robustness. To discourage structurally and narrow the gap between simulation and physical manufacturing, we further introduce a differentiable stress-aware regularization based on a learned thermal-stress predictor. Experimental results demonstrate that GenMF significantly improves appearance preservation under monochromatic rendering while reducing stress concentration under a consistent thermo-mechanical simulation setting. Physical 3D printing examples further show that the refined geometries preserve more recognizable visual details while remaining suitable for fabrication. These results suggest that appearance-aware geometry refinement provides an effective bridge between generated 3D assets and fabrication-ready monochromatic objects. --- ### Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection Authors: Ke Chen, Ling Zhou, Guangqi Jiang, Gengshen Wu, Yi Liu, Shoukun Xu Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26849v1 General Salient Object Detection (SOD) aims to identify and segment visually interesting objects from uni-modality or multi-modality scenes, recently advanced by cutting-edge State Space Models (SSMs). However, a critical limitation of current approaches is their neglect of the inherent spectral biases exhibited by different neural network paradigms. By digging to the dataset-level spectral analysis of Convolutional Neural Networks (CNNs) and SSMs, their semantic representations are inherently complementary based on their complementary frequency preferences. Inspired by this, we harmonize heterogeneous representations from SSMs and CNNs to bridge their spectral biases for general salient object detection. To this end, inspired by the dynamic information propagation of Liquid Neural Networks (LNNs), we introduce a liquid fusion to dynamically integrates features from two backbones, including VMamba and ConvNeXt, referred to Liquid Fusion Network (LFNet). Concretely, by treating the continuous VMamba features and ConvNeXt features as evolving states and exogenous stimulus, respectively, LFNet employs a dynamic gating mechanism for content-aware feature aggregation. Crucially, this state-stimulus paradigm enables to scale to multi-modal cues, resulting in flexibility in general SOD. Besides, a Saliency-Guided Upsampling (SGU) operator to propagate the features to the shallow layer, which leverages a spectral-spatial co-design to suppress upsampling artifacts while preserving semantics. Extensive experiments across five diverse tasks (RGB, RGB-D, RGB-T, VSOD, and VDT) demonstrate that LFNet achieves state-of-the-art performance, offering a superior trade-off between detection accuracy and model efficiency. Code has been released at https://github.com/cke520/LFNet. --- ### Ordinal Neural Collapse as a Representation Prior for Visual Navigation Authors: E-In Son, Jung-Taak Kim, Seung-Woo Seo Published: 2026-06-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2606.26839v2 Learning robust navigation policies directly from visual observations remains a fundamental challenge in vision-based robotic navigation. In end-to-end imitation learning approaches, the visual encoder and action decoder are jointly optimized using a single action loss, which provides only an indirect supervisory signal to the encoder. This indirect supervision frequently results in the encoder learning ambiguous, action-agnostic representations. The problem is further complicated by substantial variations in scene structure and appearance across diverse environments, as well as the prevalence of visual distractors inherent to real-world navigation settings. Such action-agnostic features cause the navigation policy to produce inconsistent actions at ambiguous decision points, leading to navigation failure. To overcome these limitations, we propose ORION (Ordinal Neural Collapse for Visual Navigation), a method that explicitly organizes the encoder's representation space according to the ordinal structure of navigation actions. In the context of goal-directed navigation, ego-centric control categories from Far Left to Far Right exhibit a natural ordinal relationship in which neighboring classes share similar visual contexts, while semantically opposing classes differ substantially in appearance. We encourage class representations to be arranged sequentially along a single discriminative axis, while suppressing off-axis variance within each class. The pretrained encoder is then integrated into a diffusion-based navigation framework, and the full pipeline is fine-tuned end-to-end. Extensive experiments in both simulation and real-world settings show that ORION consistently outperforms end-to-end and neural collapse baselines in navigation success rate and goal progress, with notable gains in visually challenging scenarios such as complex multi-way intersections. --- ### Ordinal Neural Collapse as a Representation Prior for Visual Navigation Authors: E-In Son, Jung-Taak Kim, Seung-Woo Seo Published: 2026-06-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2606.26839v1 Learning robust navigation policies directly from visual observations remains a fundamental challenge in vision-based robotic navigation. In end-to-end imitation learning approaches, the visual encoder and action decoder are jointly optimized using a single action loss, which provides only an indirect supervisory signal to the encoder. This indirect supervision frequently results in the encoder learning ambiguous, action-agnostic representations. The problem is further complicated by substantial variations in scene structure and appearance across diverse environments, as well as the prevalence of visual distractors inherent to real-world navigation settings. Such action-agnostic features cause the navigation policy to produce inconsistent actions at ambiguous decision points, leading to navigation failure. To overcome these limitations, we propose ORION (Ordinal Neural Collapse for Visual Navigation), a method that explicitly organizes the encoder's representation space according to the ordinal structure of navigation actions. In the context of goal-directed navigation, ego-centric control categories from Far Left to Far Right exhibit a natural ordinal relationship in which neighboring classes share similar visual contexts, while semantically opposing classes differ substantially in appearance. We encourage class representations to be arranged sequentially along a single discriminative axis, while suppressing off-axis variance within each class. The pretrained encoder is then integrated into a diffusion-based navigation framework, and the full pipeline is fine-tuned end-to-end. Extensive experiments in both simulation and real-world settings show that ORION consistently outperforms end-to-end and neural collapse baselines in navigation success rate and goal progress, with notable gains in visually challenging scenarios such as complex multi-way intersections. --- ### The Capability Frontier: Benchmarks Miss 82% of Model Performance Authors: Bradley Fowler, Ryan Smith, Daniel Thi Graviet, William Myers, Joshua Greaves, Narmeen Fatimah Oozeer, Antía García, Philip Quirke, Amirali Abdullah, Fazl Barez, Shriyash Kaustubh Upadhyay Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26836v1 Existing benchmarks typically report accuracy for a single model on a single run. This systematically understates real-world LLM capabilities, particularly under heterogeneous data distributions: (i) different models get different questions correct according to their specializations, and (ii) given a budget, multiple generations can be sampled and selectively retained. To quantify this gap, we introduce the Capability Frontier: a Pareto frontier over a set of models that characterizes the best achievable performance at each cost level under optimal selection across models and generations (i.e., via an oracle). Our construction corrects for two opposing biases: underestimation from single-model evaluation and overestimation from taking maxima over noisy samples. We study 21 LLMs across 16 widely used benchmarks spanning coding, reasoning, medicine, factuality, instruction following, and agentic tasks, comparing Capability Frontier performance at matched cost to each benchmark's top-performing model. Correcting for single-model evaluation yields a 54% error rate reduction; additionally correcting for single runs yields an 82% improvement, with SOTA accuracy matched at 85% cost reduction. Complementing these empirical results, we use controlled probabilistic simulations to show that higher query topic entropy produces a near-monotonic increase in the performance gap between oracle routing and the best single model. Our findings suggest collective LLM capabilities are substantially underestimated, with implications for evaluation and deployment in data-heterogeneous, multi-domain settings. --- ### Identifying the Unknown: Prompt-Free Open Vocabulary Anomaly Recognition for Robot-Object Interaction Authors: Philipp Allgeuer, Jan-Gerrit Habekost, Stefan Wermter Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26829v1 Robots operating in real-world environments must in general be able to recognize previously unseen objects. As robotic systems move toward open-world autonomy, there is a growing, yet largely unmet, need for open vocabulary object detectors that are prompt-free and efficient enough for continuous deployment. We present AnomNOVIC, a two-stage known-workspace framework that combines a masked autoencoder (MAE) trained for anomaly detection, with NOVIC, a powerful real-time prompt-free open vocabulary image classifier. The MAE produces generic object-agnostic bounding boxes, allowing NOVIC to classify salient image regions without requiring a predefined candidate class list. We evaluate AnomNOVIC against strong open vocabulary baselines in a tabletop robot-object environment featuring the NICOL humanoid robot, reaching 47.1% AP / 57.5% AP50 for prompt-free recognition, and 59.0% AP / 72.5% AP50 if class candidates are provided. Across additional datasets, including an in-the-wild test set with 48 unique objects, AnomNOVIC reaches up to 82.6% prompt-free detection and classification accuracy. These results significantly surpass all tested open vocabulary baselines, including YOLO-World-v2, OWLv2, and YOLOE. --- ### Learning Adversarial Augmentation Policies for Robust Garlic Seedling Detection Authors: Soeun Lee, Chanho Kim, Yeji Kang, YoungKi Hong, Byeongkeun Kang Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26828v1 Accurate seedling detection during early growth stages is essential for timely replanting and effective crop management in precision agriculture. However, existing studies are mostly evaluated under relatively stable imaging conditions, such as UAV imagery or greenhouse environments, leaving robust detection under severe and spatially heterogeneous illumination in ground-based outdoor monitoring insufficiently explored. In addition, many illumination-robust detection methods rely on additional enhancement or feature-extraction modules, which increase inference-time overhead and are not tailored to seedling detection and downstream missing seedling localization. To address these gaps, we construct a new garlic seedling dataset captured using a ground-based monitoring platform under real outdoor field conditions with highly variable illumination. We further propose an illumination-robust seedling detection framework based on adversarial augmentation policy learning. The proposed method jointly optimizes a stochastic augmentation policy agent and an object detector, enabling the detector to learn robust representations under challenging visual conditions. A structural penalty is introduced to prevent unrealistic distortions while encouraging challenging augmentations during training. Extensive experiments show that the proposed approach achieves an AP$_{50}$ of 91.6%, improving the baseline by 0.9 percentage points and outperforming the previous best-performing method by 0.2 percentage points. For downstream missing seedling localization, it achieves 75.0% precision and a 67.0% F1-score, improving the baseline by 4.8 and 2.0 percentage points, respectively. These results demonstrate the effectiveness of the proposed framework for practical ground-based agricultural monitoring under complex outdoor lighting conditions without additional inference-time computational overhead. --- ### Quantization in Federated Learning: Methods, Challenges and Future Directions Authors: Farwa Ikram, Dipanwita Thakur, Antonella Guzzo, Giancarlo Fortino Published: 2026-06-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26822v1 Federated Learning (FL) has become a foundational paradigm for privacy-preserving distributed intelligence, yet its scalability remains fundamentally constrained by communication bottlenecks, device heterogeneity, and the challenges of training under statistically non-IID data. Quantization is one of the most effective mechanisms for mitigating these limitations, reducing both uplink/downlink payloads and on-device computation. This paper provides the first FL-centric systematic review of quantization, introducing a novel taxonomy organized around FL-specific dimensions, including client heterogeneity, aggregation consistency, communication-scheduling adaptation, non-IID robustness, privacy/security integration, and hardware/energy co-optimization. Beyond cataloging existing methods, we analyze how quantization interacts with core FL behaviors such as client drift, partial participation, convergence stability, secure aggregation, and differential privacy. We further identify cross-method insights, open research gaps, and design guidelines for practitioners deploying quantized FL on mobile, IoT, and edge platforms. This survey thus establishes quantization not merely as a compression technique, but as a fundamental systems component shaping the performance, robustness, and practicality of modern FL. --- ### FBK's Long-form SpeechLLMs for IWSLT 2026 Instruction Following Authors: Zhihang Xie, Marco Gaido, Sara Papi, Matteo Negri, Luisa Bentivogli Published: 2026-06-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26819v1 This paper describes our submission to the IWSLT 2026 Instruction Following shared task. SpeechLLMs are developed for both short-form and long-form speech instruction following under constrained settings. For the short track, strong performance is achieved on MCIF, with a SIFS score of 2.0708. For the long track, three speech segmentation methods are explored, and the HIFS score is introduced to account for unstable long-form generation. Experimental results show that fixed 30-second segmentation provides the most robust long-form performance, achieving the highest HIFS score of 2.0663. Further analysis shows that hallucination mainly manifests as repetitive insertions in generated outputs, substantially affecting ASR and SSUM, while short-form capabilities are largely retained after long-form extension. --- ### Computational Analysis of Heart Rate Variability in Healthy Adults Authors: María J. Lado, Arturo J. Méndez, Leandro Rodriguez-Liñares, Baltasar García Pérez-Schofield, Pedro Cuesta-Morales, Brais Iglesias-Otero, Xose A. Vila Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26816v1 Heart Rate Variability (HRV) analysis is a key indicator of cardiac physiological state and aids in disease diagnosis. However, research on HRV parameters in healthy individuals remains limited, and no gold standard exists. This study evaluates HRV indices in 40 healthy adults (20 men, 20 women, aged 30-50) to improve HRV's clinical utility. Using computational methods for signal processing and data analysis, time, frequency, and nonlinear indices were analyzed to address five questions: (1) normality, (2) stability, (3) correlation, (4) reproducibility, and (5) consistency. Key findings: (1) Time-domain and nonlinear indices, particularly global and LF (low frequency), follow normal distributions, with gender differences noted. (2) Most indices are stable except HF (high frequency)-related ones. (3) High correlations in HF-related indices suggest redundancy, indicating only one is necessary in studies. (4) Comparisons with the Fantasia database revealed less than 10% error for most indices, except SD2 and SDNN in women (greater than 15%). (5) Time-domain and nonlinear indices show low inter-study variability, while frequency-domain indices exhibit high variability, limiting cross-study comparisons. The selected indices-ApEn and IRRR (global variability), HRVi and SD2 (LF), and MADRR or rMSSD (HF)-are best suited for accurately representing HRV components and enhancing its clinical and research relevance. --- ### Data-Driven Duration Management -- Term Structure Forecasting Using Machine Learning Authors: Tobias Lausser, Joao Eduardo Vuolo, Rudi Zagst Published: 2026-06-25 Categories: q-fin.PM, q-fin.CP, stat.ML arXiv: https://arxiv.org/abs/2606.26815v1 This paper compares different methods for forecasting the term structure of U.S. and European zero-coupon government bonds using both traditional econometric and Machine Learning (ML) approaches. We compare classical models (e.g., Dynamic Nelson-Siegel (DNS) and Principal Component Analysis (PCA)) with different Neural Network (NN) architectures, including those inspired by the classical models, on the U.S. Treasury market and bonds issued by the European Central Bank (ECB). To enhance predictive performance, macroeconomic variables are incorporated. The findings for both markets are separately analyzed and compared. To this end, we propose a robust model evaluation framework combining statistical accuracy metrics - such as RMSE, MAE, and directional accuracy - with the economic relevance of a quantitative bond trading strategy. Results show that NNs consistently outperform traditional models in both forecasting accuracy and portfolio performance. For the U.S., the most effective approach is a direct-forecasting NN that incorporates DNS factors to reduce the dimensionality of zero-rate data and an Autoencoder (AE) to extract macroeconomic features, while for Europe, the optimal model is a factor-based NN using PCA-derived zero-rate factors without the integration of macroeconomic variables. Overall, the paper demonstrates how combining traditional modeling approaches with modern ML techniques and evaluation can improve yield curve forecasts and support applications in fixed-income portfolio construction. --- ### Multi-modality Image Fusion under Adverse Weather: Mask-Guided Feature Restoration and Interaction Authors: Xilai Li, Xiaosong Li, Haishu Tan, Tao Ye, Huafeng Li, Hongbin Wang Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26812v1 Multi-modality image fusion (MMIF) enhances scene representation by exploiting complementary cues from different modalities. Adverse weather, however, causes significant image degradation, disrupting feature representation and requiring simultaneous feature restoration and cross-modal complementarity. Existing methods often struggle with effective representation learning under such conditions, limiting their practical performance. To address these challenges, we propose a mask-guided MMIF method that integrates feature restoration and interaction. We first introduce "Pseudo Ground Truth" to simplify training, promoting faster and more effective feature learning. Then, we design a mask generation mechanism based on the mapping relationship between the fused result and the source images, quantifying the relative contribution of each modality during the fusion process. By incorporating the proposed mask-guided cross-modal cross-attention mechanism, the network is encouraged to selectively attend to informative features during modality interaction, mitigating the risk of overfitting to the static distribution of the "Pseudo Ground Truth". Additionally, we propose a mask-guided learning strategy and a task-coupled degradation-aware learning strategy to balance feature restoration and interaction. Extensive experiments on synthetic and real-world datasets demonstrate that our method surpasses state-of-the-art approaches in visual quality, quantitative metrics, and downstream tasks. The source code is available at https://github.com/ixilai/AMG-Fuse. --- ### KARLA: Knowledge-base Augmented Retrieval for Language Models Authors: Francois Crespin, Fabian M. Suchanek, Nils Holzenberger Published: 2026-06-25 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.26807v1 We propose a new method that allows an LLM to automatically pull in factual knowledge from a knowledge base during token generation. This means that (1)~factual knowledge in the LLM output can be updated without retraining the LLM, (2)~facts in the LLM output can be traced to the knowledge base for transparency and explainability, and (3)~smaller models can achieve the same factual accuracy as larger models. Our core idea is to train the model to produce special tokens that trigger a query to the knowledge base. Our experiments show that our method improves factual grounding in both short and long-form generation, and allows factual revisions to take effect through KB edits rather than parameter updates. --- ### Memory Depth, Not Memory Access: Selective Parametric Consolidation for Long-Running Language Agents Authors: Haoliang Han Published: 2026-06-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.26806v1 Long-running language agents need more than memory access. Retrieval systems can fetch past facts at query time, but they do not decide which experiences should continue to shape behavior after the working context is unloaded. We study this separate problem as memory depth: durable goal-conditioned tendencies written into a small parametric store. We introduce the loop-drift protocol, a controlled stress test in which the retrieval index remains intact while working context is unloaded and goal-conditioned behavior must persist under long-loop interference. We evaluate EVAF, a surprise- and valence-gated LoRA consolidation mechanism. Across GPT-2 and TinyLlama, retrieval is strongest on shallow factual recall (short-fact accuracy 0.956--0.973), while EVAF is strongest on goal persistence and post-unload recovery (0.812--0.904) with only 2--3 parametric writes per 200 events. Mechanism controls show that selective consolidation factorizes into two controllable dimensions: selection and actuation. Matched random gates isolate selection beyond sparse writing; fixed-inner controls across GPT-2, TinyLlama, and Mistral-7B show that inner-loop write strength is model-dependent; and a Mistral-7B matched-gate inversion reveals asymmetric selection-actuation coupling under miscalibrated actuation. Public Memora event streams serve as an external diagnostic, exposing stale-memory invalidation as an unresolved boundary. Within this probe, selective parametric consolidation supplies memory depth distinct from and complementary to retrieval access. --- ### From Vajrayana Tara to Bengali Baul: A Computational Study of Lexical Transmission Across Buddhist, Shakta, and Vaishnava Traditions in Bengal Authors: Joy Bose Published: 2026-06-25 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2606.26803v1 We present a computational corpus study of vocabulary relationships across eight tradition layers of Bengali and Sanskrit devotional literature spanning the 8th to 19th centuries, encompassing Buddhist Vajrayana, Shakta Tantra, Vaishnava, and Baul traditions. Using a corpus of 75 texts and TF-IDF character n-gram vectorization with cosine similarity analysis, we address the historically argued but previously unquantified claim that Buddhist Vajrayana vocabulary survived the collapse of the Pala monasteries and was absorbed into the Shakta Tantra tradition of Bengal. The central finding is a specificity result: the Gitagovinda (Vaishnava Sanskrit, 12th century) has zero cosine similarity to Shakta Kali texts, while Bridge Tara texts (Buddhist-Shakta transitional, same century, same language) have cosine similarity 0.54 to Shakta Kali. This 8.5-fold contrast between two Sanskrit traditions from the same century demonstrates that the Buddhist-Shakta vocabulary overlap is not a generic property of Sanskrit devotional literature but is specific to the Buddhist-Shakta transmission chain. Three Brihannilatantra Tara texts show Shakta-to-Buddhist vocabulary ratios of 2.0 to 4.0, constituting measurable evidence of lexical transition within that chain. Ramprasad Sen's 18th-century Bengali Kali songs preserve Buddhist vocabulary residue including 56 occurrences of Tara alongside 103 occurrences of Kali. The Vaishnava Bengali tradition contributes a parallel chain to modern Baul vocabulary (similarity 0.29), slightly weaker than the Buddhist Sahajiya chain via Charyapada (0.31). These results provide the first quantitative multi-tradition corroboration of historically argued Buddhist-Shakta syncretism in Bengal. --- ### Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision Authors: Yuan Xu, Yixiang Chen, Kai Wang, Jiabing Yang, Peiyan Li, Qisen Ma, Yan Huang, Liang Wang Published: 2026-06-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2606.26801v1 Vision-Language-Action (VLA) models have shown strong potential for generalizable robotic manipulation. During fine-tuning, however, action supervision applies equally across all timesteps, without structured supervision on which manipulation stage the robot is in or what the next gripper-event target should be. This causes failures to concentrate around challenging gripper-event transitions. To address this, we propose StaKe, a plug-in auxiliary supervision framework that automatically derives two complementary signals from demonstration gripper states without manual annotation: a stage classifier that identifies the current manipulation stage, and a keyframe predictor that estimates the target joint action at the next gripper transition. Both are modeled as lightweight auxiliary heads that enrich the learned representations during training, while leaving the base VLA policy architecture and inference loop unchanged. Experiments on bimanual simulation and single-arm Franka real-robot tasks show that StaKe consistently improves success rates (relative gains of 14% and 56%, respectively), with larger improvements on longer-horizon tasks that involve more gripper-event transitions. Ablation studies validate each design choice, and qualitative analysis confirms that the learned representations faithfully track manipulation stages. These results indicate that structured supervision is an effective and general strategy for enhancing VLA fine-tuning in long-horizon manipulation. Project website: https://hi-yuanxu.github.io/StaKe-Web/ --- ### Reasoning Quality Emerges Early: Data Curation for Reasoning Models Authors: Hongyi Henry Jin, Wenhan Yang, Meysam Ghaffari, Carlos Morato, Baharan Mirzasoleiman Published: 2026-06-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26797v1 Supervised fine-tuning (SFT) on a small, high-quality set of long reasoning traces is an effective approach for eliciting strong reasoning capabilities in Large Language Models (LLMs). However, existing methods for curating high-quality SFT data rely heavily on strong reasoning models to filter examples based on diversity and difficulty, making the curation process costly while often yielding suboptimal data quality. In this work, we show that diverse and challenging reasoning examples can be identified using only the initial reasoning tokens. Specifically, we demonstrate that difficult problems can be reliably detected based on the loss of the first 100 reasoning tokens evaluated at a randomly perturbed checkpoint of the pretrained model. We further show that examples exhibiting similar loss patterns over their first 1k reasoning tokens across a small number of perturbed checkpoints extrapolating along the fine-tuning trajectory provably induce similar gradients. We validate our approach through extensive experiments on fine-tuning Qwen2.5-7B and Llama3.1-8B models on the M23K medical reasoning and OpenThoughts-Math datasets. Our method outperforms existing baselines by up to 1.7% while being 91% more token efficient. --- ### NaviCache: Test-Time Self-Calibration Caching for Video Generation Authors: Zheqi Lv, Zhibo Zhu, Jinke Wang, Qi Tian, Shengyu Zhang, Zhengyu Chen, Chengxi Zang, Zhou Zhao, Fei Wu Published: 2026-06-25 Categories: cs.CV, cs.AI, cs.MM arXiv: https://arxiv.org/abs/2606.26795v2 Video Diffusion Models (VDMs) is constrained by immense computational costs. While offline calibration-based acceleration suffers from calibration data dependency, prohibitive calibration duration, and susceptibility to distribution shifts, offline calibration-free methods eliminate these hurdles. However, since they rely on instantaneous zero-order approximations where the mapping between input and output differences varies in real-time, they are susceptible to observational noise and ignore the intrinsic momentum within the diffusion trajectory. In this paper, we propose NaviCache, a plug-and-play test-time self-calibration method re-conceptualizing feature evolution as an Inertial Navigation System (INS) problem. NaviCache bridges the fundamental domain gap and the non-stationary nature of diffusion by modeling the relative coupling between input and output variations. We introduce a dual-state estimation architecture that adaptively tracks the feature change ratio and its latent drift, initialized via a specialized Initial Alignment phase. By integrating a time-dependent noise schedule with an uncertainty-aware Measurement Update mechanism, NaviCache provides a theoretically grounded mechanism for error-bounded computation skipping. Extensive experiments on the HunyuanVideo, Wan, and Open-Sora series demonstrate that NaviCache exhibits more accurate error judgment for computation skipping and achieves outstanding comprehensive performance. --- ### ReasonCLIP-58M: Visually Grounded Commonsense Reasoning Supervision for CLIP Authors: Sicheng Zhang, Muzammal Naseer, Binzhu Xie, Naufal Suryanto, Shi Qiu, Jamal Bentahar, Naveed Akhtar, Mubarak Shah Published: 2026-06-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.26794v1 CLIP and its variants are widely adopted visual backbones in multimodal systems, but their pretraining remains dominated by descriptive image-text alignment. As downstream applications increasingly demand visually grounded commonsense inference and compositional reasoning, it remains unclear whether CLIP-style encoders can support such reasoning without architectural changes. To address this, we present ReasonCLIP-58M, a continual pretraining framework that integrates large-scale reasoning supervision into CLIP-style models through our two-stage strategy, which progressively integrates reasoning signals while preserving descriptive alignment, followed by category-structured reasoning supervision. To support this framework, we construct two complementary datasets and a benchmark: ReasonLite-42M, with open-form, visually verifiable reasoning captions; ReasonPro-16M, with category-specific reasoning supervision; and RCLIP-Bench for diagnostic evaluation of visually grounded reasoning. We train a family of ReasonCLIP that improves visually grounded commonsense and compositional reasoning while also enhancing zero-shot retrieval performance. As a drop-in visual encoder for multimodal large language models such as LLaVA-NeXT, ReasonCLIP delivers consistent gains without additional inference cost, demonstrating that structured reasoning supervision enhances the expressive capacity of CLIP-style visual representations. All datasets, models, and training code are available at https://github.com/RISys-Lab/ReasonCLIP. --- ### MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG Authors: Inderjeet Singh, Andrés Murillo, Motoyoshi Sekiya, Yuki Unno, Junichi Suga Published: 2026-06-25 Categories: cs.CR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2606.26793v1 Multimodal agentic retrieval-augmented generation (RAG) systems expand the attack surface beyond prompt injection to include text poisoning, image injection, direct-query attacks, and orchestrator-level tool manipulation. Existing red-teaming approaches are typically surface-specific and often recycle known attack templates; on text-poisoning benchmarks we measure 73-84% exact duplication. We present MIRROR, a unified cross-surface framework that performs memory-guided Monte Carlo tree search while conditioning candidate generation on retrieved context under an explicit novelty constraint. A deterministic Novelty Gate rejects any candidate matching the retrieval set under normalized comparison, allowing retrieval to inform search priors without enabling prompt copying. Across four attack surfaces on a multimodal agentic RAG target, MIRROR attains 76% ASR on image poisoning compared with 52% for baselines, 97% ASR on orchestrator attacks at half the query cost, and the lowest cross-surface variance (coefficient of variation 0.47). In contrast, specialized baselines collapse across surfaces: suffix optimization reaches 79% ASR on text poisoning but 1% on direct queries. We release ART-SafeBench with 41,815 in-package records and runtime adapters yielding 41,991+ total records across four surfaces. --- ### OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning Authors: Shuo Yang, Jinyang Wu, Zhengxi Lu, Yuhao Shen, Fan Zhang, Lang Feng, Shuai Zhang, Haoran Luo, Zheng Lian, Zhengqi Wen, Jianhua Tao Published: 2026-06-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2606.26790v1 Outcome-based reinforcement learning provides a stable optimization backbone for language agents, but its sparse trajectory-level rewards provide little guidance on which intermediate decisions should be reinforced or suppressed. On-policy self-distillation offers dense token-level supervision, yet existing skill-conditioned variants often rely on external skill memories or retrieved privileged context, which are costly to maintain and can be mismatched with the state distribution induced by the current policy in multi-turn interaction. We propose \textbf{OPID} (\textbf{O}n-\textbf{P}olicy Sk\textbf{i}ll \textbf{D}istillation), a framework that extracts skill supervision directly from completed on-policy trajectories. OPID represents trajectory hindsight as hierarchical skills: episode-level skills capture global workflows or failure-avoidance rules, while step-level skills capture local decision knowledge at critical timesteps. A critical-first routing mechanism uses step-level skills when critical decisions are identified and falls back to episode-level skills as default guidance otherwise. The selected skill is injected into the interaction history, allowing the old policy to re-score the same sampled response under both original and skill-augmented contexts. The resulting log-probability shift yields a token-level self-distillation advantage, which is combined with the outcome advantage for policy optimization. OPID thus preserves RL as the primary training objective while introducing dense, distribution-matched hindsight supervision. Experiments on ALFWorld, WebShop and Search-based QA demonstrate that OPID generally improves agent performance, sample efficiency, and robustness over outcome-only RL and existing skill-distillation baselines. Our code is available at https://github.com/jinyangwu/OPID/tree/main. --- ### AIGP: An LLM-Based Framework for Long-Term Value Alignment in E-Commerce Pricing Authors: Chennan Ma, Yanning Zhang, Siqi Hong, Xiuchong Wang, Fei Xiao, Keping Yang Published: 2026-06-25 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2606.26787v1 Traditional dynamic pricing models in large-scale e-commerce suffer from limited interpretability, poor utilization of unstructured information, and misalignment with long-term business objectives such as cumulative Gross Merchandise Value (GMV), Return on Investment (ROI) and milestone achievement. We propose AIGP, a novel framework that leverages a Large Language Model (LLM) prompted with domain knowledge, structured data and textual context to make interpretable, knowledge-aware pricing decisions. For efficient deployment while maintaining high-quality outputs, we employ supervised fine-tuning for knowledge distillation. Central to AIGP is the Long-Term Value Estimator (LTVE), trained via offline reinforcement learning on historical data, which serves as a reward model to score candidate pricing actions and select preference pairs for Direct Preference Optimization (DPO), thereby aligning the pricing policy with long-term business objectives. Extensive offline evaluations and large-scale online A/B tests on Tao Factory demonstrate that AIGP achieves significant improvements: +13.21% in GMV, +7.59% in ROI, and +8.20% in milestone achievement rate over 14 days compared to the production baseline, while simultaneously providing interpretable and transparent pricing rationales. --- ### Reproducibility Study of "AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models" Authors: Ananth K Suresh, Arya Hariharan Published: 2026-06-25 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.26783v2 Fang et al. (2025) introduced a null-space constrained projection, named AlphaEdit, for locate-then-edit knowledge editing methods, theoretically guaranteeing that edits do not disrupt previously preserved knowledge, and reports substantial gains over existing editing methods on LLaMA3, GPT2-XL, and GPT-J. In this work, we present a reproducibility study of AlphaEdit, reproducing its reported results under the original experimental setup and extending the evaluation along three axes: new model architectures, additional downstream benchmarks, and substantially longer sequential editing horizons. We successfully reproduce AlphaEdit's reported metrics across the original models, though we identify a discrepancy in the reported fluency and consistency metric. Extending AlphaEdit to newer model families, we find that its advantage does not generalize uniformly, which we trace to architectural assumptions in the locate-then-edit paradigm that are violated by these newer models. We further stress-test AlphaEdit's central sequential-editing claim by extending the number of edits well beyond those evaluated in the original paper, and find that performance, which is stable at the originally reported scale, degrades as edits reach a much higher count, indicating that the null-space projection's protection against catastrophic forgetting is bounded rather than unconditional. Finally, we extend evaluation of edited models on three extra benchmarks, namely, BoolQ, HellaSwag, and XSTest, and we find that large-scale sequential editing degrades both general downstream task competence and safety-relevant refusal behavior. Our results confirm that AlphaEdit performs as reported within its original scope, while showing that its core theoretical guarantees are sensitive to model architecture and editing scale in ways that have practical implications for its deployment. --- ### Event-based Gaze Control System for Accurate Real-time Spin Estimation in Professional Ball Games Authors: Yunpu Hu, Fabian Schilling, Valentina Cavinato, Asude Aydin, Agis Politis, Ricardo Tapiador Morales, Kirk Y. W. Scheper, Peter Dürr, Naoya Takahashi Published: 2026-06-25 Categories: cs.CV, eess.IV arXiv: https://arxiv.org/abs/2606.26780v2 Spin plays a crucial role in many ball sports due to its effect on the trajectory of the ball. Vision-based estimation of the ball's spin during a game with conventional cameras is challenging due to the ball's small size, high speed, and fast rotation. To address these challenges, we propose an event-based active vision system that can track unmodified balls and measure their spin in real time. The system consists of an event camera for its high temporal resolution and minimal motion blur, high-speed pan/tilt galvanometer mirrors to keep the ball in the field of view, and a low-latency focus-tunable telephoto lens to increase the spatial resolution on the ball and keep it in focus. To track the ball, we use a hybrid approach that combines 2D event-based detection for centering and 3D positions from a ball localization system for re-initialization. For high-accuracy spin estimation, we propose an offline method that performs contrast maximization on the sphere (s-CMax). This method achieves state-of-the-art accuracy on static balls across multiple sports (table tennis, baseball, tennis, and golf), with mean magnitude and axis errors of 1.2% and 1.5 degrees, respectively. We then develop a low-latency online method for table tennis as a case study in real-time applications. This method uses an uncertainty-aware convolutional neural network trained on pseudo-ground-truth spin labels from the offline approach, combined with a GPU-accelerated batch implementation of contrast maximization for refinement. We demonstrate reliable tracking and spin estimation with a three-view setup during professional table tennis matches, with high accuracy (8.8% magnitude and 6.4 degrees axis mismatch w.r.t. the offline method), 3 ms latency, and 750 Hz throughput. --- ### LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration Authors: Xuyue Huang, Zhe Chen, Wang Shen, Xiao-Ping Zhang Published: 2026-06-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.26778v1 Diffusion Transformers (DiTs) have driven substantial progress in image and video generation but suffer from prohibitive computational costs. Feature caching accelerates inference by reusing intermediate representations. Existing methods rely on historical features for implementation simplicity, yet suffer from severe error accumulation at high acceleration ratios. To address this limitation, we investigate the nature of the requisite feature correction. We demonstrate that the optimal calibration update is characterized by a shared low-rank subspace across diverse prompts. Guided by this structural insight, we propose LearniBridge, a learnable calibration mechanism for feature caching that bridges multiple timesteps through lightweight LoRA updates. This mechanism enables effective calibration requiring only 3-5 training samples. Extensive experiments on image and video generation show that LearniBridge achieves up to $5.87\times$, $5.75\times$, and $4.10\times$ acceleration on FLUX, HunyuanVideo, and WAN2.1, respectively. On WAN2.1, it improves VBench by 1.28% over the previous SOTA at $4.10\times$ acceleration. Our code is available at https://github.com/Iiiiiiirene/LearniBridge. --- ### Evaluation Pitfalls and Challenges in Multimedia Event Extraction Authors: Philipp Seeberger, Steffen Freisinger, Tobias Bocklet, Korbinian Riedhammer Published: 2026-06-25 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2606.26775v1 Multimedia event extraction aims to jointly identify events and their arguments across multiple modalities, such as text and images, to support more comprehensive event understanding. While recent work reports steady and substantial progress, the reliability and comparability of these results critically depend on consistent and rigorous evaluation. In this work, we present the first systematic analysis of evaluation pitfalls in multimedia event extraction and identify three major sources of issues: inconsistent data processing, inconsistent task assumptions, and overly relaxed evaluation settings. We demonstrate, through a series of controlled experiments under a strict evaluation framework, that minor evaluation choices can cause large performance variations and lead to overestimation of a model's ability to ground real-world events across modalities. Our findings highlight the need for comparable evaluation standards and encourage a shift toward more rigorous evaluation in multimedia event extraction. --- ### Escaping Iterative Parameter-Space Noise: Differentially Private Learning with a Hypernetwork Authors: Naoki Nishikawa, Shokichi Takakura, Satoshi Hasegawa Published: 2026-06-25 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2606.26772v1 Differentially private (DP) training of neural networks is often hindered by the large amount of noise required by gradient-based methods such as DP-SGD, which repeatedly inject high-dimensional noise in parameter space throughout training. In this paper, we propose a new framework for DP learning that avoids iterative optimization in parameter space. Instead of updating the target model using privatized gradients, we employ a hypernetwork trained on public datasets to map a private dataset to the parameters of the target model. Specifically, each example is embedded into a low-dimensional representation, the embeddings are aggregated and perturbed to obtain a DP dataset embedding, and the hypernetwork generates the target model parameters from this noisy embedding. Because privacy noise is injected only once into a low-dimensional dataset representation, our approach can significantly reduce the adverse effect of noise. We theoretically show in a synthetic setting that, under a fixed privacy budget, models produced by our approach achieve higher utility than those trained with DP-SGD. Moreover, we apply our approach to LoRA fine-tuning of diffusion models and show that it achieves lower FID than LoRA models trained with DP-SGD and other public-data-guided methods. --- ### ResilPhase: Plug-and-Play Phase Mapping and Noise-Resilient Macro-Trajectory Extrapolation for Diffusion Acceleration Authors: Qicheng Zhao, Yu Li, Qi Sun, Zheyu Yan Published: 2026-06-25 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2606.26769v1 The adoption of powerful diffusion models is hindered by their significant inference latency. Recent ``cache-then-forecast'' schemes alleviate this issue by accelerating DiTs using derivative-based polynomials, but they suffer from severe quality degradation at high acceleration ratios. Our analysis reveals its root cause: the discrete extrapolation performed on representations that are misaligned with the continuous diffusion trajectory and are numerically unstable. Thus, accelerated DiTs suffer from accumulated spatial errors, noisy derivative amplification, and high-order instability. We therefore reformulate accelerated inference as stable macro-trajectory extrapolation in ordinary differential equation (ODE) space. Instead of predicting intermediate features, we align forecasting with the model's Global Drift (GD), i.e., the end-to-end state evolution, thereby eliminating feature inconsistency and memory overhead. However, even this smooth macro-trajectory remains vulnerable to the derivative fallacy: its higher-order temporal derivatives are intrinsically noisy. Thus, we introduce a derivative-free barycentric Lagrange extrapolator to effectively bypass derivative instability and approximation error. We further propose a bounded Phase Mapping that regularizes the extrapolation domain, suppressing oscillatory error growth. These elements collectively constitute ResilPhase, a noise-resilient acceleration framework. Experiments on FLUX.1-dev and HunyuanVideo demonstrate state-of-the-art fidelity under aggressive acceleration ratios. --- ### Anatomy-Guided Residual Motion Diffusion for Controllable 4D Cardiac MRI Synthesis Authors: Yiheng Cao, Gustavo Andrade-Miranda, Jiatian Zhang, Lingxiao Zhao, Xin Gao Published: 2026-06-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.26764v1 Developing robust artificial intelligence models for 4D (3D + time) medical imaging is constrained by limited annotated data, inter-device domain shifts, and privacy restrictions. To address this, we propose a 4D controllable generative framework for anatomically consistent data augmentation. A semi-supervised variational autoencoder learns a compact latent representation of anatomical volumes while jointly predicting aligned segmentation masks in a unified framework. Anatomical structure is then disentangled from temporal dynamics through a cascaded latent diffusion model (LDM). A static LDM generates subject-specific anatomy conditioned on clinical priors (diagnosis and volumes measures) and a subsequent motion LDM estimates residual latent motions, ensuring strict temporal coherence across the 4D sequence. The proposed approach was evaluated on cine cardiac MRI as a representative 4D imaging application. Experiments across multiple datasets demonstrate high controllability of static anatomy (Pearson r > 0.8) and strong temporal coherence (FVD = 288.08). In cross-vendor generalization experiments, augmenting training sets with synthetic 4D sequences significantly improves downstream segmentation performance. Using nnU-Net, the proposed augmentation strategy improves the average Dice score by 1.4% and reduces the Hausdorff Distance by 3.0mm compared to training on real data alone, for the left ventricle, Dice improves by 2.8% with a 5.4mm reduction in boundary error. Overall, this framework provides a scalable and controllable solution for 4D medical image synthesis, supporting the development of more robust models with limited annotations and cross-vendor variability. Code available on https://github.com/cyiheng/4DCardiacMRISynthesis. --- ### Calibrated Harmonic Overlaid Implicit Neural Representations for Multi-Dimensional Data Authors: Honghang Chen, Xiujun Zhang, Xiaoli Sun, Mingqing Xiao Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26763v1 Implicit neural representation (INR) has emerged as a powerful prior for multi-dimensional data (e.g., multispectral images and videos). However, most INR methods employing periodic activation functions (e.g., Sine) predominantly rely on function composition. This mechanism introduces optimization instability as network depth increases, thereby limiting their performance. Meanwhile, these methods fail to incorporate proper physical priors to effectively alleviate spectrum bias. To address these issues, inspired by the commonalities between deep periodic networks and generalized Fourier series, we propose a novel Calibrated Harmonic Overlaid Implicit Neural Representation (CHOIR). Specifically, we utilize Coordinated Harmonic Superposition (CHS) to replace the conventional function composition used in most INRs, thereby ensuring optimization stability when scaling network depth. Furthermore, we introduce a Perceptual Spectrum Calibration (PSC) to mitigate spectrum bias. This calibration embeds the ubiquitous power-law spectrum prior of natural images and adjusts the globally fixed spectrum towards a physically plausible log-uniform distribution. Extensive experiments on various multidimensional data recovery problems demonstrate that our method achieves superior performance over state-of-the-art approaches. Code is available at https://github.com/chorl0229/CHOIR. --- ### ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory Authors: Le Tu Ngoc Minh, Jinyeong Lim, Dongsu Han Published: 2026-06-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2606.26762v1 Streaming video understanding (SVU) must answer queries that arrive asynchronously while visual tokens stream continuously under strict GPU-memory and query-time latency budgets. A key challenge is delayed query: decisive cues may appear briefly, yet many subsequent updates occur before the query arrives, increasing the risk that those cues are evicted or diluted under bounded memory. We propose ProtoKV, a constant-footprint SVU memory that represents far history as a fixed-capacity summary state rather than retaining token instances. ProtoKV keeps an exact near-window KV cache and aggregates older content into a semantic-spatial prototype bank with residual statistics. At query time, each prototype is exposed through a bounded pseudo-token interface that is drop-in compatible with standard attention. Under matched budgets and comparable query-time cost, ProtoKV improves accuracy by up to 12.5 points over token-retention baselines on SVU benchmarks in the long-delay regime, with gains that grow as query delay increases. --- ### EGG: An Expert-Guided Agent Framework for Kernel Generation Authors: Yaochen Han, Ke Fan, Hongxu Jiang, Wanqi Xu, Weiyu Xie, Runhua Zhang, Chenhui Zhu, Yixiang Zhang Published: 2026-06-25 Categories: cs.AI arXiv: https://arxiv.org/abs/2606.26758v1 High-performance GPU kernels are critical for reducing the exponentially growing computational costs of large language models (LLMs), but their development heavily relies on manual tuning by domain experts. While recent advances in LLM-based approaches show promise for automating kernel generation, they still struggle to achieve both correctness and high performance. This limitation primarily arises from the lack of domain-specific optimization guidance, hindering effective exploration of the optimization space. We propose EGG, an Expert-Guided Agent Framework for Kernel Generation, which incorporates expert optimization principles to guide LLMs' decisions. Inspired by expert workflows, we decompose kernel generation into two hierarchical stages: 1) algorithmic structure design, which establishes a high-quality computational structure foundation; 2) hardware-specific tuning, which performs targeted adjustments through parallel mapping, tensor tiling, and memory optimization. This staged decomposition defines explicit optimization objectives, structuring the design space to achieve progressive refinement. To this end, a stage-aware multi-agent collaboration mechanism is designed for inter and intra-stage context management, ensuring stable optimization trajectories. Experiments on KernelBench and real-world workloads show that EGG achieves a 2.13x average speedup over PyTorch, outperforming existing agent-based and RL-based approaches. --- ### Batch-Invariant Spectral Intelligence for Robust and Explainable Insect Authentication Authors: Majharulislam Babor, Giacomo Rossi, Annalisa Altavilla, Oliver Schlüter, Marina M. -C. Höhne Published: 2026-06-25 Categories: cs.LG arXiv: https://arxiv.org/abs/2606.26757v1 Edible insects offer an efficient source of alternative protein, requiring less land, water and emitting less greenhouse gas than conventional livestock. However, their successful integration into the food supply chain demands reliable species authentication to control allergen exposure, prevent adulteration, and meet regulatory standards. Near-infrared spectroscopy provides a rapid analytical tool, but its performance drops when applied to production batches unseen during training due to batch-to-batch variation in spectral measurements. We introduce the Batch-Invariant Spectral Network (BISN), an end-to-end framework that combines a learnable preprocessing module, initialised with Savitzky-Golay filtering, with an entropy-regularised adversarial objective to suppress batch-specific spectral variation. In contrast to Domain-Adversarial Neural Networks, which enforce domain adaptation only after feature extraction, BISN suppress batch-effects before species-specific features are learned. Using 2,700 spectra from three species (Acheta domesticus, Hermetia illucens, and Tenebrio molitor) collected across three independent production batches, BISN achieves a mean leave-one-batch-out accuracy of 0.93 (standard deviation 0.04), outperforming the strongest baseline by four percent. Further insights gained by using explainable AI confirm that model decisions consistently rely on the lipid and protein absorption regions across all folds, connecting predictive performance to known insect biochemistry. BISN addresses both cross-batch robustness and biochemical interpretability for automated insect species authentication under realistic industrial conditions. The source code and dataset are publicly available at https://github.com/majharB/bisn. --- ### Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting Authors: Zhihao Wen, Yixin Yang, Bojian Wu, Yang Zhou, Dani Lischinski, Daniel Cohen-Or, Hui Huang Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26754v1 While 3D Gaussian Splatting (3DGS) provides an efficient and explicit representation for novel view synthesis, enforcing stylistic coherence across viewpoints remains challenging. Existing 3D stylization methods typically apply 2D feature-matching losses independently per rendered view, which leads to unstable style allocation, many-to-one feature reuse, and limited cross-view consistency. We propose a capacity-controlled framework for multi-view stylization of 3DGS, grounded in optimal transport. Specifically, we reformulate local style matching as a semi-balanced optimal transport problem. By introducing explicit column-capacity constraints with tunable strength, our formulation mitigates many-to-one matching and enables controllable allocation of style features. This transport-based objective provides a principled mechanism for balancing feature coverage and stylistic diversity while maintaining stable correspondences across viewpoints. To further enhance cross-view coherence, we incorporate a novel cross-view matching guidance to constrain correspondences between scene content and style patterns. In addition, we introduce several geometric regularizations to enhance the vanilla 3DGS, thereby enabling optimized Gaussian primitives to represent finer-grained textures during stylization. Extensive experiments demonstrate that our approach significantly improves multi-view stylistic consistency and produces stable, expressive 3D stylizations while preserving the core semantic structure of the scene. --- ### ConvMemory v3: A Validity Context Layer for Conversational Memory via Target-Conditioned Relation Verification Authors: Taiheng Pan Published: 2026-06-25 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2606.26753v1 Conversational memory retrieval optimizes relevance, yet a retrieved memory can be relevant and simultaneously outdated: a later turn updates, corrects, or supersedes it. ConvMemory v3 adds a validity context layer that detects and surfaces this update evidence through target-conditioned relation verification, sitting after the v1/v2 retrieval path. The core mechanism is a dual-evidence gate that conditions a relation judgment on the specific target proposition, scoring a (target, source) pair through the product of a MiniLM slot head and a DeBERTa-v3 slot head and gating it by conservative event/operation evidence. On a synthetic multi-hop validity benchmark the gate reaches 90.12% +/- 1.73 accuracy; through a real-data feedback loop that mines failure patterns but trains on synthetic pairs only, the verifier transfers to Memora role binding with zero target-side labels, reaching 98.8% +/- 0.9 group-all-correct. The deployed layer preserves retrieval by default: a context mode attaches structured validity metadata while keeping the candidate set and rank order fixed, and a query-conditioned demote mode is an explicit opt-in for dense current-state workloads, where it raises current-active H@1 from a never-demote baseline of 45.1% to 95.7% +/- 1.2 while protecting non-superseded memories at 99.4% recall. Six machine-verifiable safety contracts pin the layer's behavior. Multi-hop graph propagation is validated as a mechanism; fully automatic construction of strict prerequisite edges is characterized as a boundary, since strict necessity requires counterfactual world knowledge. This report extends ConvMemory v1 (arXiv:2605.28062) and v2 (arXiv:2606.10842). --- ### Structure Before Collapse: Transient semantic geometry in next-token prediction Authors: Yize Zhao, Isabel Papadimitriou, Christos Thrampoulidis Published: 2026-06-25 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.26749v1 Neural Collapse predicts that balanced one-hot classification pushes model representations to be equally far from each other; a symmetric configuration that depends only on the output label and ignores any semantic similarity in the inputs. This creates a puzzle: next-token prediction language models are trained predominantly (as context length increases) with one-hot labels: the same context is very unlikely to appear twice in training with different labels. However, they clearly learn latent structural features. That is, despite the one-hot training regime, a language model's contextual embeddings represent the fact that the next word in ''Mary broke the ___'' is likely to be filled by tokens in the latent classes of a) medium-sized, b) rigid, c) inanimate nouns. How does gradient descent find such categorical semantic structure when co-occurrence statistics collapse to one-hot sparsity, eliminating any shared next-tokens among different contexts? To investigate this tension we identify three synthetic controlled settings where inputs have latent semantic factors but are mapped to distinct one-hot labels. We find that semantic geometry emerges early in training, and that representations cluster by shared attributes despite receiving no explicit supervision to do so. This structure is transient: with sufficient capacity and time, the model eventually reaches the predicted symmetric state where all representations are equally separated. We study this phase transition through Gram matrix analysis and propose a preliminary modification to the commonly used unconstrained features model to capture the emergent semantic geometry. --- ### HyperDFlash: Hyper-Connection-Aligned Block Speculative Decoding with Gated Residual Reduction Authors: Luxi Lin, Shuang Peng, Rui Ma, Junhao Hua, Shuwei Fan, Zhengda Qin, Qiang Wang, Hongjian Sun, Fangmin Chen, Songwei Liu Published: 2026-06-25 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2606.26744v2 We present HyperDFlash, a block-parallel speculative decoding framework tailored to DeepSeek-V4's Hyper-Connections (HC). Despite the strong performance of DeepSeek-V4's native Multi-Token Prediction (MTP) module on initial token drafting, its draft accuracy degrades sharply at later positions, as error accumulation from unverified intermediate tokens harms draft acceptance rates. Although the original DFlash method supports efficient one-pass block drafting, it cannot be seamlessly adapted to the HC paradigm, since DeepSeek-V4's multi-path residual stream induces inherent feature misalignment with conventional drafting designs. To resolve this architectural mismatch, we propose two dedicated, model-aligned optimizations for HC residual streams. First, we adopt pre-collapse residual states as the exclusive conditioning signal, preserving complete multi-path structural information and better aligning the drafter with the target's native prediction pathway. Second, we replace the heavy generic linear compressor with a lightweight gated residual reducer, whose parameters are directly inherited from the target model's built-in hc_head module. This design yields input-aware path aggregation with three orders of magnitude fewer parameters while maintaining precise architectural alignment. We further enhance model training via a targeted KL distillation loss applied to the LM-head, regularizing predictions against the target distribution to improve early draft quality. Extensive experiments across math reasoning, code synthesis, and conversational benchmarks demonstrate that HyperDFlash consistently outperforms both the native MTP baseline and vanilla DFlash adaptation, achieving substantial gains in average accepted draft length and decoding speedup. These results validate HC alignment, gated reduction, and targeted distillation for high-performance speculative decoding. --- ### Depth-Semantic Alignment and Affinity-Guided Fusion for Structured Radar Point Cloud Generation Authors: Amjad Hussain, Wenjie Liu, Yuchen Tan, Fuyuan Ai, Zecheng Li, Chunyi Song, Xin Qiu Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26743v2 Point clouds are an important carrier of three-dimensional spatial information, and their quality directly affects the performance of downstream perception tasks such as object detection and tracking. However, millimeter-wave radar point clouds are typically sparse, noisy, and structurally incomplete. To address these limitations, this paper proposes a multimodal point cloud generation method based on vision-radar fusion. The proposed method leverages image semantic information to impose structural constraints and achieve spatial alignment for radar point clouds, while incorporating a sparse completion strategy to enhance point density and recover missing structures. The generated point clouds are further evaluated in object detection and tracking tasks. Experimental results demonstrate that the proposed method effectively improves point cloud quality and enhances the detection accuracy and robustness of perception models in complex environments, providing a practical solution for multisensor point cloud generation and intelligent perception systems. --- ### PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation Authors: Yi Lu, Shenghao Ren, Tianyu Xiong, Zhaoxiang Li, Jiaqi Li, He Zhang, Tao Yu, Qiu Shen, Xun Cao Published: 2026-06-25 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2606.26741v1 Humanoid motion imitation requires not only accurate perception of human kinematics but also faithful reproduction of physical interactions with the environment. However, existing pipelines rely primarily on vision-based motion capture and kinematic imitation, largely ignoring contact dynamics, leading to artifacts such as foot sliding, floor penetration, and unstable behaviors. In this work, we revisit humanoid motion imitation from the perspective of physical grounding and leverage pressure as a unified modality across perception and control. We present PressMimic, a framework that integrates pressure into the full pipeline from motion capture to humanoid control. In the perception stage, we introduce FRAPPE++, a multimodal model that fuses RGB and pressure to jointly estimate 3D pose and global motion, where pressure provides explicit contact and support constraints to resolve ambiguity in vision-based estimation. In the control stage, we propose a pressure-supervised policy (PSP) that incorporates pressure-derived signals into reinforcement learning, enabling physically consistent contact patterns during execution. We further construct MotionPRO, a large-scale dataset with synchronized RGB, pressure, and motion capture data. Experiments show that pressure improves motion estimation accuracy, trajectory consistency, and execution stability. These results demonstrate that pressure serves as an effective physical grounding signal, bridging perception and control for physically consistent humanoid motion imitation. --- ### LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing Authors: Xinyu Wang, Chongbo Zhao, Fangneng Zhan, Yue Ma Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26740v2 Streaming video editing has made rapid progress, yet practical deployment is still limited by two core issues: maintaining stable backgrounds and non-edited regions over time, and achieving the low latency required for real-time interactive scenarios. Meanwhile, recent streaming video generation methods are mostly developed for synthesis and cannot be directly applied to editing due to the strict preservation requirement and region-specific control. In this work, we present a novel streaming video editing framework that performs causal, frame-by-frame editing with strong content preservation and real-time responsiveness. Our key design is a three-stage distillation pipeline that progressively transfers editing capability from a powerful bidirectional foundation model to an efficient unidirectional streaming editor, enabling stable long-horizon edits without sacrificing visual fidelity. To further support real-time deployment, we introduce an AR-oriented mask cache that reuses region-related computation across frames, substantially reducing redundant processing and accelerating inference. Finally, we establish a dedicated benchmark for streaming video editing. Extensive evaluations demonstrate that our method achieves state-of-the-art visual quality among streaming baselines while drastically boosting inference speed to 12.66 FPS, making it suitable for interactive and augmented reality applications. --- ### Do Image Editing Models Understand Lighting? Authors: Tim Küchler, Johann-Friedrich Feiden, Matthias Nießner, Carsten Rother Published: 2026-06-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2606.26738v2 While recent advancements in generative image editing models have achieved stunning visual fidelity, it remains an open question whether these systems possess an intrinsic knowledge of real-world lighting. Existing benchmarks typically evaluate high-level plausibility of perceptual light transport on curated internet imagery, using VLMs or human judgement, or they rely on synthetically generated datasets. In this work, we introduce the 3D-anchored Light Probe (3DLP) benchmark, for which we have captured a new high-fidelity HDR dataset of real-world lighting changes. The dataset consists of 1K image pairs of diverse indoor scenery in which light probes are physically turned on and off. To allow for a granular performance analysis, we annotated specific image regions such as cast shadows or metallic surfaces. With this data, we evaluate a range of state-of-the-art image editing models by measuring how well their light probe edits align with reality. The evaluation uses two new scores to compensate for AI-generated photographic effects, such as adjusted white balance. Our results show that the overall performance of models differs considerably, with differences slightly less pronounced for specular highlights. The best image editing models are remarkably consistent with real-world physics, however, they still leave room for improvement. We observe that image regions that receive less light from the light probe are more prone to errors for all models. Furthermore, building on their success in evaluating macroscopic lighting plausibility, we test VLMs on our task but find that they are unsuitable for pixel-level light transport analysis. We will make the benchmark, together with the real-world dataset, publicly available to encourage future research on this topic. --- ### Robust Onion: Peeling Open Vocab Object Detectors Under Noise Authors: Priyank Pathak, Mukilan Karuppasamy, Aaditya Baranwal, Shruti Vyas, Yogesh S Rawat Published: 2026-06-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2606.26734v2 The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity. We present our comprehensive analysis Robust Onion, an empirical study that uses controlled synthetic visual degradations to peel OV-ODs layer-by-layer, revealing how, why, and where robustness degrades, systematically analyzing feature collapse. Our findings reveal that models with similar vision backbones exhibit comparable robustness, driven by similar feature collapse at similar layers, while factors such as pretraining strategy, architectural nuances, and caption supervision contribute little. Robustness is primarily governed by the image domain rather than annotations, explaining the similar robustness impact on COCO and LVIS, and why datasets like ODinW-13 can give an impression of inflated robustness due to large, isolated objects. Finally, we validate our insights by improving robustness on real-world BDD100K, WiderFace, and VisDRONE via our lightweight plug-and-play NN & TK0 approach, using 96x fewer trainable parameters than end-to-end training. We also explain the prior works' robustness observations. --- ### Surviving by Serving: Functional Relevance Drives Self-Organization in Complex Adaptive Systems Authors: Claus Metzner, Ali Ghebleh, Achim Schilling, Andreas Maier, Thomas Kinfe, Patrick Krauss Published: 2026-06-25 Categories: q-bio.NC, cs.NE, nlin.AO arXiv: https://arxiv.org/abs/2606.26733v1 Complex adaptive systems often develop organized structures without centralized control. Yet the local mechanisms by which functional organization emerges and persists remain incompletely understood. Here we propose Surviving by Serving (SBS) as a general principle of self-organization: components persist as long as their outputs are utilized by other components, whereas prolonged non-utilization promotes adaptation and exploration. To investigate this idea, we introduce a minimal multi-agent model in which agents transform shared resources and receive only local feedback when their outputs are subsequently utilized elsewhere in the system. Despite the absence of global objectives, the system spontaneously self-organizes into functional interaction networks. We observe the emergence of stable transformation chains, core-periphery organization, and the generation of novel states that enable previously inaccessible target conditions to be reached. Remarkably, self-sustaining interaction networks can arise even without external selection pressures, creating a pre-adaptive search phase from which later functional solutions emerge. These findings suggest that functional utilization may provide a simple, substrate-independent mechanism for the emergence and stabilization of organized structure in complex adaptive systems. --- ### Scientific discovery as meta-optimization: a combinatorial optimization case study Authors: Yuan-Hang Zhang, Chesson Sipling, Massimiliano Di Ventra Published: 2026-06-25 Categories: cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2606.26728v1 Scientific discovery is fundamentally an optimization problem, defined by a vast "state space" of theories and experiments, and an evaluation criterion based on quality, novelty, and validity. Large language models (LLMs) have enabled automated exploration of this space, but we argue that simultaneous modification of the evaluation criteria is equally important. Here, we propose formalizing research as meta-optimization, where the optimization objective itself is also being optimized. Our key contribution is "consensus objective aggregation," where LLM-generated objective functions are combined via correlation-weighted voting, yielding a stable, self-correcting evaluation criterion that evolves as understanding deepens. We apply this framework to algorithm discovery for 3-SAT problems based on digital MemComputing machines, reducing the baseline scaling with problem size $N$ from $\sim N^{2.51}$ to $\sim N^{1.33}$ and delivering a $\sim 67\times$ speedup on the largest instances tested. As a problem-agnostic framework, we hope this approach will considerably aid scientific discovery. --- ### State-specific respiratory signatures for affective and stress recognition: Interpretable respiratory markers, autocorrelation lags, and compact CNN models Authors: Andrei Velichko, Mehmet Tahir Huyut Published: 2026-06-25 Categories: eess.SP, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2606.26723v2 Respiratory activity is a direct and interpretable physiological channel for wearable stress and affective-state recognition, yet many studies emphasize classification accuracy without identifying which respiratory properties separate different states. Using the chest respiratory channel of the WESAD dataset, we analyze 60 s windows under leave-one-subject-out validation and combine two complementary branches: compact raw-signal one-dimensional convolutional neural networks (1D-CNNs) and physically grouped handcrafted respiratory signatures. The primary task is stress versus non-stress detection, while baseline, stress, amusement, and meditation are additionally analyzed in a one-vs-rest setting to reveal state-specific respiratory markers. The feature space is organized into respiratory timing, breath-to-breath variability, waveform statistics, spectral/time-frequency descriptors, and autocorrelation/nonlinear predictability descriptors, with the raw 60 s signal treated as a sixth representation for the CNN branch. We introduce autocorrelation transition lags (Zpm/Zmp) as interpretable markers of respiratory correlation scale and separately evaluate exploratory forecast-error-growth/Lyapunov-like descriptors. In the final CNN refit setting, the raw-signal model achieved the strongest stress-vs-rest performance (accuracy 96.72%, macro-F1 95.30%, MCC 90.61%). In contrast, compact feature models were stronger for baseline (MCC 65.34%), amusement (MCC 35.69%), and especially meditation (MCC 88.65%). Strict nested reanalysis of the auxiliary Top-20 stress search yielded mean MCC=82.29% versus 85.45% originally, indicating modest selection optimism. These results show that CNNs are most useful for the practical stress detector, whereas interpretable respiratory signatures provide stronger and more physiologically transparent state-specific markers for several non-stress conditions. --- ### State-Specific Respiratory Signatures for Affective and Stress Recognition: Interpretable Respiratory Markers, Autocorrelation Lags, and Compact CNN Models Authors: Andrei Velichko, Mehmet Tahir Huyut Published: 2026-06-25 Categories: eess.SP, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2606.26723v1 Respiratory activity is a direct and interpretable physiological channel for wearable stress and affective-state recognition, yet many studies emphasize classification accuracy without identifying which respiratory properties separate different states. This work reframes RESP-based recognition as a joint predictive and explanatory problem. Using the chest respiratory channel of the WESAD dataset, we analyze 60 s windows under leave-one-subject-out validation and combine two complementary branches: compact raw-signal one-dimensional convolutional neural networks (1D-CNNs) and physically grouped handcrafted respiratory signatures. The primary application task is binary stress versus non-stress detection, while baseline, stress, amusement, and meditation are additionally analyzed in a one-vs-rest setting to reveal state-specific respiratory markers. The feature space is organized into respiratory timing, breath-to-breath variability, waveform statistics, spectral/time-frequency descriptors, and autocorrelation/nonlinear predictability descriptors, with the raw 60 s signal treated as a sixth representation for the CNN branch. We introduce autocorrelation transition lags (Zpm/Zmp) as interpretable markers of respiratory correlation scale and separately evaluate exploratory FEG-Pro/Lyapunov-like descriptors. In the final CNN refit setting, the raw-signal model achieved the strongest stress-vs-rest performance, with accuracy 96.72 percent, macro-F1 95.30 percent, and MCC 90.61 percent. In contrast, compact feature models were stronger for baseline, with MCC 65.34 percent, amusement, with MCC 35.69 percent, and especially meditation, with MCC 88.65 percent. These results show that CNNs are most useful for the practical stress detector, whereas interpretable respiratory signatures provide stronger and more physiologically transparent state-specific markers for several non-stress conditions. ---