# Research Papers — 2026-07 · bundle page 182 of 222 > Full-text markdown of papers #9051–9100 of 11075 published in 2026-07, newest first. AI-readable mirrors of the full 11075-paper 2026-07 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-07/page/182 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/181.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/183.md) ### Privacy-Preserving Robustness Verification for Neural Networks Authors: Nianyun Song, Xiaokun Luan, Yu Guo, Rongfang Bie, Meng Sun, Xiyue Zhang Published: 2026-07-06 Categories: cs.CR, cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2607.05251v1 Neural network verification and data privacy are inherently in tension: verification demands full access to model parameters and input data, yet both are increasingly restricted by privacy regulations and intellectual property constraints. This tension has left robustness verification impractical in privacy-sensitive domains. In this work, we address this gap with SecureCROWN, the first framework for privacy-preserving neural network robustness verification. Built upon secure two-party computation (2PC), our framework enables a model owner and a data owner to jointly compute certified robustness bounds -- revealing only the final result while provably protecting both parties' private data under the semi-honest security model. A key challenge is securely computing the conditional operations in Linear Bound Propagation, where the data-dependent branching is incompatible with standard secure computation protocols. We eliminate branching by formulating conditional logic as continuous arithmetic operations. Additionally, we introduce a Newton--Raphson refinement method to improve numerical stability. Extensive analysis and experiments show that SecureCROWN strictly matches plaintext verification results, while completing in 0.1--200s across varied model sizes and communication settings (LAN/WAN), demonstrating the feasibility of privacy-preserving neural network verification. --- ### Streaming Neural Speech Codecs through Time-Invariant Representations Authors: Kélian Estève, Salima Mhdaffar, Mickael Rouvier, Richard Dufour, Yannick Estève Published: 2026-07-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.05250v1 Neural speech codecs are increasingly used as intermediate representations in codec-based speech generation systems. TiCodec introduces a factorized representation that separates time-varying speech content from time-invariant information through a Time-Invariant Representation Extraction (TIRE) module, potentially reducing the amount of information that must be modeled at the frame-level. In this work, we investigate the nature of the information captured by TIRE representations and their suitability for low-latency speech processing. Using a series of probing tasks, we analyze the influence of the encoder layer and show that intermediate layers capture complementary speaker- and environment-related information while containing little linguistic content. We further study several segment selection strategies for TIRE training and demonstrate that cross-file sampling improves the robustness of invariant representations. Based on these findings, we propose Dual-TIRE, a multi-level architecture that exploits the complementarity of different encoder layers and improves speech reconstruction quality and speaker similarity. Finally, we evaluate TiCodec in a streaming inference setting using successive 660ms processing blocks. Results show that streaming operation can be achieved without significant degradation in reconstruction performance, highlighting the potential of factorized neural codec representations for future low-latency speech generation systems. --- ### Vision Pretraining for Dense Spatial Perception Authors: Zelin Fu, Bin Tan, Changjiang Sun, Shaohui Liu, Kecheng Zheng, Yinghao Xu, Xing Zhu, Yujun Shen, Nan Xue Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.05247v1 Dense spatial perception is essential for physical intelligence, where visual systems are expected to recover structured, metric, and actionable representations from pixel observations. Modern visual foundation models tend to prioritize semantic invariance, often at the expense of detailed spatial understanding. In this work, we study vision pretraining through a boundary-centric lens, motivated by the premise that boundaries and shape discontinuities offer essential cues for perceiving geometric properties. Concretely, we propose masked boundary modeling, a self-supervised paradigm that dynamically learns sub-pixel boundary representations and subsequently leverages the discovered boundary-bearing tokens as masked targets to facilitate dense visual token learning. By scaling this framework, we develop LingBot-Vision and demonstrate its efficacy across a diverse set of downstream vision tasks with DINOv3 as a strong baseline. Remarkably, LingBot-Vision drives the progression from LingBot-Depth 1.0 to LingBot-Depth 2.0 for depth completion, and thereby yields enhanced depth estimation, a key pillar for embodied artificial intelligence. Our findings reveal that boundary modeling goes beyond simple line segments and instead serves as a scalable pretraining principle for learning spatially structured visual representations. --- ### GUSH3R: Everyone Everywhere All at Once as Gaussians Authors: Keito Abe, Kaede Shiohara, Takashi Otonari, Toshihiko Yamasaki Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.05243v1 Reconstructing dynamic human-scene environments from monocular videos is a challenging problem that requires jointly modeling scene geometry, camera motion, and non-rigid human dynamics while enabling photorealistic rendering. Recent feed-forward methods can efficiently predict geometry, but they are often limited to non-photorealistic representations such as point clouds and meshes, or they fail to handle non-rigid objects, particularly dynamic humans. To fill this gap, we present GUSH3R (Gaussian-Unified Scene Human 3D Reconstruction), a feed-forward framework for online dynamic human-scene reconstruction. From a monocular human-scene video, our method reconstructs dynamic humans (everyone) and static scenes (everywhere) in a single forward pass (all at once) as 3D Gaussian Splatting (3DGS) primitives (as gaussians), which are geometrically consistent and capable of novel view synthesis. Experiments on monocular human-scene datasets demonstrate that our approach achieves competitive novel view synthesis quality while significantly improving inference efficiency compared to optimization-based methods. --- ### CanniUplift: A Holistic Framework for Mitigating Seller and Incentive Cannibalization in E-commerce Uplift Modeling Authors: Zuwang He, Shihao Shu, Yuli Qu, Hanyu Gao, Ziliang Zhang, Diwei Chen, Xiangda Yan, Buyu Gao, Tanchao Zhu, Yumeng Li, Junxiong Zhu Published: 2026-07-06 Categories: cs.LG, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.05242v1 Personalized incentive allocation is vital for e-commerce, where uplift modeling is the standard for estimating Individual Treatment Effects (ITE). However, traditional models often fail in complex multi-seller environments with violations of the Stable Unit Treatment Value Assumption (SUTVA). We identify two critical challenges: Seller-level Cannibalization, where incentives shift expenditure between shops without growing the platform, and Incentive-level Cannibalization, where organic conversions or alternative rewards introduce significant noise into incrementality estimation. In this paper, we propose CanniUplift, a unified framework to mitigate these dual-source cannibalization effects. Specifically, we design Platform-level Global Alignment (PGA) to capture cross-shop substitution through global GMV consistency constraints. To tackle incentive-driven noise, we introduce Redemption-based Decomposition Denoising (RDD), which uses redemption behavior to decompose treated outcomes and reduce attribution noise within an entire-space framework. Furthermore, a Treat-Attention mechanism is designed to model intricate interactions between users' historical behaviors and current treatment options. Extensive experiments on both synthetic and large-scale industrial datasets demonstrate that CanniUplift significantly outperforms state-of-the-art baselines. Ablation studies confirm that the integration of PGA and RDD consistently improves wAUUC and wQINI. Successfully deployed online, our framework achieved a 4.08% relative increase in platform-wide incremental GMV (Delta GMV) over the production baseline and improved ROI in online A/B tests, proving effective in driving global platform growth. --- ### Optimizing ML Workload Partitioning between CPUs and CIM Accelerators for Heterogeneous Computing Authors: Joel Klein, Rebecca Pelke, Roberto Laudani, Jan Moritz Joseph, Rainer Leupers Published: 2026-07-06 Categories: cs.ET, cs.AI, cs.AR, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2607.05240v1 Computing-in-Memory (CIM) accelerators execute Matrix-Vector Multiplications (MVMs) in memory, making them a compelling solution for Machine Learning (ML) workloads. However, existing ML workload partitioning approaches for CIM accelerators do not fully account for Resistive Random Access Memory (RRAM) constraints such as limited memory, high write latency, and limited endurance. They also neglect parallelism, low-level architectural effects, or the Central Processing Unit (CPU) as a complementary compute resource. To address these limitations, we propose an Integer Linear Programming (ILP)-based workload partitioning framework for heterogeneous CPU-CIM systems. It minimizes end-to-end inference latency under RRAM constraints, captures parallelism, and combines empirical profiling with analytical models. Using our framework, heterogeneous CPU-CIM execution achieves speedups of up to 30.9x over CPU-only execution on an edge CPU and 7.3x over a high-performance CPU. A Design Space Exploration (DSE) yields further design insights for future CIM accelerators. --- ### Branch-JEPA: Finite-Support Predictive Distributions for JEPA World Models Authors: Zhi Song, Ximing Xing, Zhenchao Tang, hanbo Huang, Jiehui Huang, Weilong Yan, Tianxu Lv, Minghao Yang, Zhongzheng Niu, Bing He, Lusheng Wang, Jianhua Yao Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.05238v3 Joint-embedding predictive architectures (JEPAs) learn dynamics by predicting future observations in representation space. Yet most JEPA world models return one latent successor, even when hidden intent, partial observation, or stochastic dynamics make several futures plausible. We introduce Branch-JEPA, which replaces this point-valued transition with a context-weighted finite set of latent successors. Every branch is decoded independently, and the complete set is retained at inference. The architecture supports two complementary training regimes: specialization for recovering separated successors and full-set Energy-Score training for distributional fidelity. In a locked five-seed evaluation on the Argoverse~2 official validation split, full-set training improves trajectory Energy Score by $5.8$--$6.5\%$ and probability-weighted trajectory distance by $9.3$--$10.4\%$ over matched-$K{=}6$ assignment and transport objectives, while retaining $5.36$ endpoint-deduplicated effective branches. In a parameter-exact official-validation comparison, latent branching retains $10.3\%$ more effective modes and improves Energy Score, expected ADE, and Brier in all five paired seeds over branching only at the output decoder; every paired 95\% interval excludes zero. In an OGBench graph audit, Branch-JEPA increases teleport verified-route existence to $19.2\%$ versus $3.9\%$ for the MDN. Its raw-support advantage also persists with 29-D state and RGB observations. Together, latent branching preserves more distinct futures, while full-set scoring improves the quality of the resulting predictive distribution. --- ### Video-based detection of cessation of breathing in pre-term infants using machine learning Authors: Dineo Serame, Lionel Tarassenko, Mauricio Villarroel Published: 2026-07-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.05230v1 Pre-term infants are susceptible to potentially harmful apnoea-related cessations of breathing due to immature respiratory control. However, reliable respiratory monitoring in the neonatal intensive care unit (NICU) remains challenging because motion artefacts, sensor displacement, and skin fragility can compromise contact-based measurements. Non-contact video monitoring offers a complementary approach that does not depend on adhesive sensors while providing additional respiratory information. We investigated whether camera-based signals can detect apnoea-related cessation of breathing (COBE) and provide complementary information to routinely acquired physiological signals. Using video and clinical recordings from 30 pre-term infants, respiratory motion was extracted from dynamically tracked torso regions to generate camera-derived time-series signals. Camera-only models were trained using residual network (ResNet) architectures, while hybrid models combined video-derived signals with impedance pneumography (IP), ECG-derived respiration (EDR), and the PPG-derived respiratory envelope. Camera-only models achieved a balanced accuracy of 76.9%, demonstrating the feasibility of non-contact COBE detection. Combining video-derived features with IP improved balanced accuracy to 90.6%, outperforming either modality alone and indicating that video provides respiratory information beyond standard physiological signals. These findings show that video-derived signals contain clinically relevant respiratory features and enhance COBE detection when combined with conventional physiological signals. This supports non-contact video as a complementary modality for automated COBE detection and highlights its potential to improve the robustness of neonatal respiratory monitoring. --- ### msPCA: An R Package for Sparse PCA with Multiple Components Authors: Ryan Cory-Wright, Jean Pauphilet Published: 2026-07-06 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2607.05229v1 We present msPCA: an open-source R package for sparse principal component analysis with multiple components. It implements an alternating maximization algorithm to generate a set of sparse loading vectors that collectively explain a large fraction of the variance in a dataset, while remaining non-redundant. The algorithm supports two definitions of non-redundancy: either orthogonality of the loading vectors or zero pairwise correlation between principal components (PCs). In the reported benchmarks, msPCA solves sparse PCA problems with thousands of features, achieving competitive runtimes while producing sparse components with controlled feasibility violations and a high fraction of variance explained. --- ### The Exact Worst-Case Tail Probability under Bounded Kurtosis Authors: Xiaoyu Li, Andi Han, Jiaojiao Jiang, Junbin Gao Published: 2026-07-06 Categories: math.PR, math.ST, stat.ML arXiv: https://arxiv.org/abs/2607.05226v2 We determine exactly what a kurtosis bound buys for one-sided tail control. For the class $\mathcal{C}(κ)$ of real random variables with mean $0$, variance $1$, and fourth moment at most $κ$, the skewness left free, we compute the worst-case tail probability $V_1(t,κ)=\sup_{X\in\mathcal{C}(κ)}\mathbb{P}(X\geq t)$ for every threshold $t>0$ and every $κ\geq 1$. The answer is a four-regime map: a Cantelli tongue $b(κ)\le t\le c(κ)$ on which the two-moment bound $1/(1+t^2)$ remains tight and the kurtosis constraint is worthless; a tail regime $t\geq c(κ)$ with the closed form $V_1=(κ-1)/((t^2-1)^2+κ-1)$; a plateau regime, present only for $κ\le 3/2$, on which the worst case freezes and the value does not depend on $t$; and a central regime described exactly by an explicit algebraic system, provably admitting no closed form in nested square roots. Beyond $c(κ)$ the one-sided and two-sided worst cases coincide: Cantelli's improvement over Chebyshev is annihilated by fourth-moment information. The minimal degree of a sum-of-squares proof of the tight bound is $2$ on the closed tongue and $4$ everywhere else, an exact phase diagram of proof degree. Every closed-form regime carries an explicit dual certificate and an explicit extremal distribution, re-verified on parameter grids by an independent checker in exact arithmetic. The closed forms invert to exact worst-case quantiles, sharpen a median-of-means constant, and give the exact per-direction tail available to degree-4 reasoning under certifiable kurtosis. We found the map through an AI-guided search around the certifying pipeline, LemmaForge, which is validated on classical benchmarks, independently reproduces the symmetric-slice bound of Zelen (1954), and recovers the $2\sqrt{3}-3$ constant of He, Zhang, and Zhang (2010) at $t=0$. --- ### Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR Authors: Qu Yang, Cakra Wardhana, Tim Ng Published: 2026-07-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.05224v1 Code-switching (CS), alternating languages within the same utterance, poses significant challenges for automatic speech recognition (ASR) due to limited CS training data. This paper applies an iterative pseudo-labeling training approach to CS-ASR for the first time, demonstrating its effectiveness in leveraging unlabeled data to improve CS-ASR performance. The approach comprises three phases: pseudo-label generation, two-stage bilingual model training, and iterative improvements. It begins by generating pseudo-labels from a large unlabeled corpus, creating a semi-supervised dataset. This dataset supports a two-stage training framework where the model is pre-trained and then fine-tuned on supervised CS data. Iterative refinements further enhance the model's accuracy in handling complex CS scenarios. Our approach significantly advances CS-ASR systems, achieving notable Mix Error Rate (MER) reductions on SEAME's devman (6.35%) and devsge (8.29%) subsets. --- ### A Multimodal Reasoning Typology for Grounding Chart-Image Coherence in Science Communication Authors: Avina Nakarmi, Sohom Sen, Xun Song, Sreyashi Samaddar, Aritra Dasgupta Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.05222v1 Charts and images appear together throughout scientific publications, yet most computational work does not characterize their coherence. We argue that a chart, its accompanying image, and the caption that links them form a multimodal unit, and that the inferential work required to read it varies systematically. To capture this variation, we develop a typology of reasoning gaps, R1 through R5, that characterizes how chart, image, and text jointly convey a scientific claim, and the interpretive work this demands of the reader. Some pairs restate the same data, while in other pairs, charts are used to quantify a structure the image localizes, project image content onto an external variable, audit an image-based claim, or jointly construct a frame that neither panel can establish alone. The typology is anchored in the grounding theory of communication and was derived bottom-up, with a neuroscience expert, from a corpus of 79 traumatic brain injury papers and 32 chart-image pairs. Crucially, the levels provide a systematic mechanism for identifying where grounding succeeds or breaks down, rather than leaving it to subjective inference. We show this in a study in which a domain expert and three non-experts judge vision-language model (VLM) descriptions of 25 pairs: the level predicts where their judgments align and where they diverge, isolating the points at which contextual knowledge, not the figure, carries coherence. This typology thus offers figure designers a systematic way to balance text against chart-image pairs, bridging the expert-to-non-expert divide in reading a scientific takeaway. --- ### Curated retrieval versus open web search in public AI information services: a coverage-trust trade-off Authors: Hafsteinn Einarsson, Hafsteinn Birgir Einarsson, Jón Gunnar Ólafsson, Jón Gunnar Þorsteinsson Published: 2026-07-06 Categories: cs.CY, cs.CL, cs.IR arXiv: https://arxiv.org/abs/2607.05217v2 Public institutions increasingly use large language models (LLMs) to answer citizens' questions, often pairing a curated knowledge base with live web search, yet whether the sources behind these answers can be trusted has received little empirical scrutiny. We report a pre-launch expert evaluation of Evrópuvefur, an independent, government-funded service run by the University of Iceland that answers questions about the European Union, conducted as Iceland prepared for its referendum of 29 August 2026 on whether to resume EU accession talks. Five domain experts produced 551 evaluations of 449 AI-generated answers, scoring each against a seven-criterion quality rubric and, separately, flagging individual cited sources. We compared two retrieval paths: a curated local corpus (RAG) and open web search. In more than a third of the reviewed web-search answers (35%, 65 of 187), at least one cited source was flagged, almost always as untrustworthy or irrelevant; curated sources were flagged far less often and only for being out of date. Web search answered more questions, but at the cost of source quality; the curated corpus was trustworthy yet limited in coverage, and the model declined to respond when it fell short. The citation mix also passed over strong sources: across all 287 web-search answers, the system never cited RÚV, the public broadcaster and the country's most widely used news source. A companion prompt ablation shows how weak prompt-level steering is: a trusted-domain list in the system prompt raised the share of citations to listed domains only from 12% to 21%. Fluency and topical fit did not predict source trustworthiness. We argue that source trustworthiness is a measurable yet largely invisible dimension of information quality in public AI services, and we discuss transparency-oriented responses and their trade-offs. --- ### Probing Geospatial SSL Representations with Environmental Signals Authors: Rohita Mocharla, Vishal M. Patel Published: 2026-07-06 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.05207v1 Self-supervised learning (SSL) is designed to learn generic, transferable representations rather than representations optimized for a single task. Most geospatial benchmarks evaluate representations solely through downstream tasks, providing limited insight into the information encoded within the representation itself. We ask a different question: do SSL representations of satellite imagery preserve statistical associations with environmental variables that co-vary with the imaging process? To answer this question, we probe SSL representations using co-located ERA5 reanalysis variables, a global dataset of physically consistent environmental variables, including temperature, precipitation, surface solar radiation, surface pressure, and volumetric soil water. These variables are physically related to the spectral reflectance and radar backscatter recorded by Sentinel-1 and Sentinel-2, making them meaningful evaluation targets despite not being used during SSL pretraining. We complement this probing analysis with intrinsic representation metrics to characterize representation geometry and investigate how these properties relate to downstream performance and the encoding of environmental signals. Using DINO, MAE, and MoCo models trained under identical conditions, we show that representation-level metrics distinguish models with similar downstream benchmark performance, providing complementary information beyond task-driven benchmarks. We further find that the linear accessibility of environmental signals is associated with performance on environmentally dependent tasks in the PANGAEA benchmark. Finally, we release ERA5 annotations co-located with the SSL4EO dataset to enable physically grounded representation evaluation for future geospatial foundation models. --- ### An Event-Driven Framework for Fly-Inspired Visual Motion Detection Authors: Qinbing Fu, Jingyu Huang, Yan Xie, Jigen Peng, Yuchao Tang Published: 2026-07-06 Categories: cs.CV, cs.NE arXiv: https://arxiv.org/abs/2607.05205v2 Fast and reliable motion detection is essential for machine vision and autonomous systems operating in dynamic environments. This work integrates emerging event-based sensing with biologically structured neural computation to establish an efficient computational paradigm for visual motion detection. The proposed framework is built upon a recently developed fly-inspired neural network that emulates motion-processing circuits in the optic lobe. Owing to its feed-forward and training-free architecture, the neural model requires only a small number of interpretable parameters and is well suited for real-time implementation. Event cameras provide low-latency, low-power, and high-dynamic-range visual sensing by asynchronously transmitting brightness-change events. However, their performance can be degraded by event noise, including temporal noise and junction-leakage-induced activity, particularly under low-light conditions. Moreover, effective integration between event-based visual representations and biologically inspired neural processing remains under-explored. To address these challenges, we propose an event-driven computational framework that combines time-surface encoding for front-end event representation with a fly optic-lobe-inspired neural network for foreground motion-direction estimation. A bottom-up attention mechanism is further incorporated to suppress background motion and enhance the saliency of foreground targets. The proposed method is evaluated via real-world datasets of ground-vehicle detection and compared with a baseline frame-based model and an optimization-based approach. Experimental results demonstrate that the framework effectively combines the temporal advantages of event-driven vision with the efficiency and interpretability of bio-inspired neural processing. --- ### An event-driven framework for fly-inspired visual motion detection Authors: Qinbing Fu, Jingyu Huang, Yan Xie, Jigen Peng, Yuchao Tang Published: 2026-07-06 Categories: cs.CV, cs.NE arXiv: https://arxiv.org/abs/2607.05205v1 Fast and reliable motion detection is essential for machine vision and autonomous systems operating in dynamic environments. This work integrates emerging event-based sensing with biologically structured neural computation to establish an efficient computational paradigm for visual motion detection. The proposed framework is built upon a recently developed fly-inspired neural network that emulates motion-processing circuits in the optic lobe. Owing to its feed-forward and training-free architecture, the neural model requires only a small number of interpretable parameters and is well suited for real-time embedded implementation. Event cameras provide low-latency, low-power, and high-dynamic-range visual sensing by asynchronously transmitting brightness-change events. However, their performance can be degraded by event noise, including temporal noise and junction-leakage-induced activity, particularly under low-light conditions. Moreover, effective integration between event-based visual representations and biologically inspired neural processing remains under-explored. To address these challenges, we propose an event-driven computational framework that combines time-surface encoding for front-end event representation with a fly optic-lobe-inspired neural network for foreground motion-direction estimation. A bottom-up attention mechanism is further incorporated to suppress background motion and enhance the saliency of foreground targets. The proposed method is evaluated on real-world ground-vehicle datasets and compared with a baseline frame-based model and an optimization-based approach. Experimental results demonstrate that the framework effectively combines the temporal advantages of event-driven vision with the efficiency and interpretability of bio-inspired neural processing. --- ### Causal-RetiGraph: Cross-Cohort Retinal Support and Same-Subject Pathway Analysis for Diabetic Retinopathy Authors: Inam Ullah, Imran Razzak, Shoaib Jameel Published: 2026-07-06 Categories: cs.CV, math.PR, stat.CO arXiv: https://arxiv.org/abs/2607.05204v1 Diabetic retinopathy (DR) is a local retinal lesion process and a visible manifestation of systemic microvascular injury. Modern retinal AI can grade images accurately, but often leaves unanswered how local lesion evidence, retinal vascular structure, and systemic disease pathways are connected. This paper introduces \emph{Causal-RetiGraph}, a compact biomedical informatics framework that links retinal graph phenotypes with NHANES-anchored pathway modelling. The retinal-image fold constructs an interpretable $X1234$ phenotype from vessel maps, lesion evidence, image embeddings, and AutoMorph biomarkers through spatial $X_{12}$ and Jacobian $X_{34}$ branches. The NHANES fold models systemic exposures, covariates, a same-subject retinal mediator family $R^*$, and downstream outcome families. $X1234$ is used for retinal support and pathway prioritisation, while $R^*$ is used for participant-level pathway summaries. On the retinal fold, $X1234$ achieves 0.9055 binary DR accuracy and 0.9711 AUROC, with graded DR QWK of 0.8312. The results show that lesion and biomarker streams improve contextual retinal representation under scarce and imbalanced data. In NHANES, HbA1c, urine albumin, pulse pressure, fasting glucose, and systolic blood pressure are the strongest binary DR anchors. Participant-level pathway analysis identifies glycaemic--renal and glycaemic--haemodynamic pathways as the clearest mediator-style signals. These results suggest that retinal graph phenotypes can help prioritise systemic pathways in DR while preserving the distinction between image-derived support and same-subject mediation. --- ### EvoAgentBench: Benchmarking Agent Self-Evolution via Ability Transfer Authors: Xingze Gao, Chuanrui Hu, Hongda Chen, Pengfei Yao, Zhao Wang, Yi Bai, Zhengwei Wu, Yunyun Han, Xiaofeng Cong, Jie Gui, Yafeng Deng, Teng Li Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.05202v1 Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for searching, debugging, and verification. Yet current evaluations do not isolate this form of transfer. Agent benchmarks test single-episode task solving; memory benchmarks target information retention rather than procedural reuse. We introduce EvoAgentBench, a benchmark for agent self-evolution via Ability-guided transfer across four agentic domains: web research, algorithmic reasoning, software engineering, and knowledge work. EvoAgentBench extracts trace-grounded Abilities from agent executions, canonicalizes them into operational units, and builds domain-specific Ability Graphs linking tasks that share procedural overlap. By design, every test task is backed by verified training-side Ability support. Across a 528/267 train/test split, two scaffolds, and three backbones, curated Ability content transfers reliably across model families, but no current automatic method sustains positive gain in all settings. EvoAgentBench shifts self-evolution evaluation from aggregate accuracy comparison to fine-grained diagnosis of experience encoding, routing, and uptake. The benchmark is publicly available at https://huggingface.co/datasets/EverMind-AI/EvoAgentBench. --- ### FlatManifold: Robust Continual Learning under Severe Label Noise and Domain Shifts via Intrinsic Manifold Flattening Authors: Rai Hisada, Kanji Tanaka Published: 2026-07-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.05201v1 In non-stationary streaming environments, simultaneously adapting to complex, non-linear domain shifts via continual learning while mitigating the catastrophic effects of severe, uncalibrated label noise poses a fundamental mathematical challenge. In this paper, we propose \FlatManifold{}, a novel, streamlined robust continual learning framework that utilizes a Nyström manifold flattening map based on the kernel trick and projection onto an orthogonalized Reproducing Kernel Hilbert Space (RKHS). Unlike traditional methods that rely on complex, error-prone sample-filtering pipelines, the proposed approach exploits the intrinsic mathematical robustness of the flattened space itself. By mapping feature distributions onto a fixed orthogonal target topology with a ridge regularizer, the framework naturally smoothes and counteracts the influence of extreme label noise during the optimization process. Concurrently, catastrophic forgetting is prevented via a continual topology brake term that leverages the covariance matrix of past experiences. Extensive evaluation on real-world multi-session robotics datasets demonstrates that even under severe conditions featuring 40\% symmetric label noise, \FlatManifold{} successfully mitigates gradient corruption. Under extreme cross-session domain shifts spanning various seasons and lighting conditions, the proposed framework establishes high generalization capabilities, significantly outperforming standard sequential optimization baselines and proving that structural linearization itself serves as a powerful mathematical barrier against distributed label corruption. --- ### Reason, Reward, Refine: Step-Level Errors Corrections with Structured Feedback for Physics Reasoning in Small Language Models Authors: Raj Jaiswal, Dhruv Jain, Rishabh Dhawan, Sree Krishna Uppalapati, Shin'ichi Satoh, Tanuja Ganu, Rajiv Ratn Shah Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.05199v1 Physics reasoning fails structurally in small language models: an error at any step propagates forward, corrupting every inference that follows. Limited domain knowledge, hallucination under multi-step derivation, and distributional sensitivity compound this failure. We propose a step-level reward framework that identifies the first reasoning error, generates targeted structured feedback, and trains the model to revise its solution via policy gradient with KL regularization, without exposing it to ground truth solutions as generation targets. Unlike annotation-dependent step-level methods, no preference data construction is required and the external verifier operates exclusively at training time. Across five physics benchmarks, our framework delivers accuracy gains of 17-20% over CoT prompting and 10-16% over the strongest baseline, reduces calculation errors from 56.9% to 23.5%, and reduces miscomprehension errors from 22.3% to 12.0% in the best observed cases. Conceptual errors reduce from 89.7% to 68.7%, yet persist as the hardest failure mode across all conditions. --- ### Noisy-Channel Minimum Bayes Risk Decoding Authors: Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe Published: 2026-07-06 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.05198v1 Minimum Bayes Risk (MBR) decoding yields more robust and higher-quality text generation than maximum a posteriori (MAP) decoding by selecting hypotheses that maximize expected utility over sampled pseudo-references. However, there exists a discrepancy in the design: hypothesis selection calculates expected utility scores conditioned on given pseudo-references, while commonly used evaluation metrics, e.g., BLEU and COMET, are asymmetric. Therefore, it is important to consider both hypothesis-to-reference and reference-to-hypothesis directional effects. In this study, we introduce a noisy channel decomposition of MBR decoding that naturally incorporates bidirectional effects to account for these asymmetries. We decompose MBR decoding into four interacting components: hypothesis-to-reference likelihood, reference-to-hypothesis likelihood, hypothesis prior, and reference prior. This decomposition provides a unified interpretation of existing MBR variants and enables metric- and task-specific interpretability by isolating the contribution of each channel. Our comprehensive analysis reveals that channel-wise contributions exhibit distinct characteristics across metrics while remaining consistent across tasks, and suggests that appropriate channel weighting may lead to improvements over original MBR decoding. --- ### Unified Audio Intelligence Without Regressing on Text Intelligence Authors: Zhifeng Kong, Sang-gil Lee, Jaehyeon Kim, Boxin Wang, Zihan Liu, Sungwon Kim, Yang Chen, Arushi Goel, Rajarshi Roy, Wenliang Dai, Zhuolin Yang, Yangyi Chen et al. Published: 2026-07-06 Categories: cs.CL, cs.AI, cs.LG, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2607.05196v2 Audio intelligence involves understanding, reasoning about, and generating both audio and speech. In this work, we introduce Nemotron-Labs-Audex-30B-A3B (Audex), a unified audio-text LLM built on Nemotron-Cascade-2-30B-A3B, a strong text-only MoE LLM. Audex adopts a simple unified design with a single Transformer decoder: audio inputs are encoded and projected into the text embedding space, while text tokens and quantized audio output tokens are treated uniformly during generation. This architecture enables strong audio-text fusion, seamless multimodal generation, and compatibility with standard LLM training and inference infrastructure. For training, we meticulously curate audio-text datasets comprising 157.4B audio tokens and 320.5B text tokens. We apply multi-stage supervised training on these datasets, followed by text-only Cascade RL and multi-domain on-policy distillation. Audex delivers state-of-the-art audio understanding, speech recognition and translation, text-to-speech, audio generation, and speech-to-speech generation, while preserving very compelling reasoning, alignment, knowledge, long-context, and agentic capabilities of its text-only LLM backbone with marginal or no regression. We release the model checkpoints to facilitate open research. --- ### When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents Authors: Yechao Zhang, Shiqian Zhao, Jiawen Zhang, Jie Zhang, Gelei Deng, Xiaogeng Liu, Chaowei Xiao, Tianwei Zhang Published: 2026-07-06 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.05189v1 Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution. This integration also creates a new path to compromise: untrusted external content can be silently written into persistent memory and later reused as trusted state. We study this threat as stealth memory injection, in which a remote black-box adversary delivers a single email payload that must induce the agent to write poisoned memory, stay hidden in the agent's response to the user, and affect future behavior. We introduce WhisperBench, a 108-case benchmark spanning five risk categories and both fact and preference poisoning. Built on a real IMAP/SMTP workflow and an authentic email agent skill, it enables full-cycle evaluation of stealth memory injection attacks. To enable this black-box attack under single-email delivery and without runtime feedback, we propose MemGhost, a one-shot payload generation framework. MemGhost uses an environment proxy to emulate persistent-agent execution and an objective proxy to convert memory adoption and conversational stealth into dense rubric-based rewards, then trains the attacker policy with supervised fine-tuning and reinforcement learning. Across 56 held-out test cases, MemGhost achieves 87.5% end-to-end success on OpenClaw with GPT-5.4 and 71.4% on Claude Code SDK with Sonnet 4.6. It also transfers across personal-agent architectures (NanoClaw and Hermes Agent) and memory backends (filesystem and vector-based Mem0), and remains effective against input-level, model-level, and system-level defenses. These results suggest that persistent memory can turn ordinary external processing into a practical pathway for long-term agent compromise. --- ### Latent Programming Horizons in Coding Agents Authors: André Silva, Han Tu, Martin Monperrus Published: 2026-07-06 Categories: cs.LG, cs.SE arXiv: https://arxiv.org/abs/2607.05188v1 A coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests, yet little is known about what the underlying language model internally represents about the program it is working on. We show that the residual streams of language models under coding agents linearly encode properties of the evolving program: a logistic-regression probe on hidden states is able to decode whether the current code parses, passes its test suite, reduces the number of failing tests, and introduces regressions, reaching AUC up to 0.83 for correctness across two models and two benchmarks. Our second finding is more surprising: these representations run ahead of the agent's own edits. Probes trained to predict the outcome of future edits (before they are materialized and written on disk) achieve performance above chance up to roughly 25 steps in advance. We call this the agent's latent programming horizon. As a proof of external validity, we show that the probes transfer across benchmarks without retraining. Our positive results open calls for more research in mechanistic interpretability of coding agents. --- ### SMART: A Machine Learning and Monte Carlo Framework for Rapid Analysis of Stochastic Transistor Aging and Process Variation in Digital Circuits Authors: Arash Esshaghi, Siavash Es'haghi, Gholamreza Shahabadi, Alireza Moradi Published: 2026-07-06 Categories: cs.LG, cs.AR arXiv: https://arxiv.org/abs/2607.05187v2 As CMOS technology scales into the deep nanometer regime, digital circuit reliability is increasingly threatened by the combined stochastic effects of Bias Temperature Instability (BTI) and Process Variation (PV). Traditional reliability analysis methods, which rely on computationally intensive simulations or extensive lookup tables, fail to scale efficiently for large designs, creating a critical bottleneck in design space exploration. To address this, we propose SMART, a novel framework that integrates Machine Learning (ML) with Monte Carlo simulation to enable rapid, high-fidelity reliability analysis. SMART employs Random Forest regression to predict gate delay distributions directly, bypassing time-consuming atomic model parameter extractions. Crucially, the model utilizes Bayesian Optimization for automated hyperparameter tuning, ensuring maximum predictive robustness across diverse libraries. Experimental validation on ISCAS85 benchmark circuits demonstrates that SMART achieves a 94.54% reduction in analysis time compared to state-of-the-art methods, while maintaining a remarkable average accuracy error of just 1.63%. By shifting computational complexity to an offline training phase, the proposed framework offers a scalable, accurate solution for designing resilient, reliability-aware digital systems. --- ### ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization Authors: Mahnoor Shahid, Hannes Rothe Published: 2026-07-06 Categories: cs.AI, cs.SC arXiv: https://arxiv.org/abs/2607.05185v1 Compositional generalization, the ability to understand and produce novel combinations of known components, remains a fundamental challenge for modern artificial intelligence. While few benchmarks exist, many focus on linguistic tasks and lack complex, explicit compositional structures. We introduce ClassicLogic, a new benchmark suite designed to evaluate an agent's ability to learn and compose problem-solving strategies. The benchmark consists of four classic logic puzzles: Sudoku, KenKen, Kakuro, and Futoshiki. Its core innovation is a hierarchical, explicit knowledge base for each game, where complex solving strategies are formally defined as compositions of simpler, foundational strategies. This structure allows for fine-grained evaluation of an agent's reasoning capabilities, from learning basic rules to applying multi-step compositional strategies to solve puzzles of increasing, mathematically validated difficulty. The open-source benchmark provides a challenging new testbed for advancing neuro-symbolic and other advanced AI reasoning systems. --- ### Rethinking On-Policy Self-Distillation for Thinking Models Authors: Simran Kaur, Narutatsu Ri, Yinghui He, Liam Fowl, Sanjeev Arora Published: 2026-07-06 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.05184v1 Self-distillation is a promising recipe for self-improvement in language models. In this setting, a model can serve as its own teacher when given privileged information, such as a solution to a math problem. This seems especially appealing for thinking models, which can use test-time reasoning to absorb the privileged information. Surprisingly, we show that privileged self-distillation degrades thinking models on long reasoning traces: across five Qwen3 and OLMo thinking models evaluated on AIME24, AIME25, and HMMT25, privileged-context distillation causes a relative drop of up to 17% in avg@16 accuracy. The degradation scales with the amount of privileged context withheld from the student and is most pronounced at long rollout budgets, where thinking models otherwise obtain their largest gains. This failure mode is not specific to self-distillation: on-policy distillation (OPD) improves thinking models, but privileged OPD reverses these gains. Our diagnostics link this failure mode to how privileged teacher context reshapes learning at high-entropy forking positions, where multiple continuations remain plausible and may lead to different reasoning paths. Privileged context lowers fork rates in thinking-model rollouts but not in instruction-model rollouts. This leads to an interesting dichotomy, where privileged context can help instruction-tuned models but hurts stronger thinking models. The effect is visible when the student begins a self-correction branch, where privileged OPD penalizes sampled reconsideration tokens that vanilla OPD supports. Thinking models trained with a privileged teacher produce fewer verification, backtracking, and hedging markers, even after length normalization. These findings indicate that self-distillation for strong thinking models requires attention to token-level signal, especially around correction and reasoning steps. --- ### VLM-CASE: Vision-Language Model Enabled Context-Adaptive Safety Envelopes for Anticipatory Safe Autonomous Driving Authors: Tianjia Yang, Ke Li, Ruwen Qin, Xianbiao Hu Published: 2026-07-06 Categories: cs.RO, cs.CV, eess.SY arXiv: https://arxiv.org/abs/2607.05180v1 Adverse driving conditions, such as bad weather, remain a principal barrier to autonomous driving because they degrade two things at once: what the vehicle can perceive and what it can physically do. Human drivers cope by anticipation, reasoning about the scene and re-budgeting speed, following distance, and steering before grip or sight is lost, whereas current autonomous driving systems at best react after the fact. This paper proposes VLM-CASE, a framework that gives an autonomous vehicle this anticipatory capacity while keeping its motion bounded by a formal safety model at all times. A vision-language model (VLM), fine-tuned with low-rank adaptation (LoRA), reasons about the scene from the front-camera image and reports the road surface and visibility conditions. This output parametrizes a context-adaptive safety envelope (CASE), derived from physical limits and the guarantees of responsibility-sensitive safety, that couples braking and steering through a shared friction budget. A model predictive controller then drives freely within the envelope, while the VLM runs asynchronously so it never blocks the real-time control loop. We validate the framework in closed-loop CARLA simulation on tasks that demand both lateral and longitudinal control, across a range of weather, road-surface, and lighting conditions. The resulting controller, VLM-CASE-MPC, completes all trials, outperforming a conventional MPC baseline and a state-of-the-art VLM-integrated controller. Ablations confirm that the gains come from context adaptation, with the friction and visibility adaptations proving complementary. Furthermore, the framework is controller-agnostic and pairs with almost any low-level controller, offering a promising direction for safe autonomous driving. The dataset and supplementary materials for VLM-CASE are available at https://github.com/ytj254/VLM-CASE. --- ### Relational Multi-Agent Reinforcement Learning for Dynamic Pricing in High-Speed Railway Markets Authors: Enrique Adrian Villarrubia-Martin, David Muñoz-Valero, Luis Rodriguez-Benitez, Giovanni Montana, Luis Jimenez-Linares Published: 2026-07-06 Categories: cs.LG, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2607.05179v1 In liberalised railway systems, operators must set prices dynamically in an environment with partial observability, as they retain private information about their objectives and performance, where regulatory constraints prohibit communication or direct information exchange between competitors to prevent explicit collusion. Consequently, agents must learn to infer strategic interactions only from observable market data which presents a significant challenge for multi-agent reinforcement learning, where standard approaches typically treat observations as unstructured vectors, ignoring the underlying market topology that governs strategic interactions. To address this, an entity graph modelling approach is proposed, which represents the environment as a graph of operational units, rather than decision-making agents or static infrastructure, encoding competition, coordination, and connectivity relations between entities. Then, an extension of the multi-agent twin delayed deep deterministic policy gradient algorithm with graph-based representation learning processes the features of the entities through a multi-layer relational graph convolutional network and aggregates them via a learnt attention mechanism. Experimental results in a rail pricing reinforcement learning environment show that this novel framework achieves higher revenue and stability in two different settings of increasing market complexity compared to a representative selection of relational and non-relational baselines. The code is publicly available at: https://github.com/Kinrre/RelationalRailPricing-RL --- ### CP-WSP: A Declarative CP-SAT Framework for Configurable Multi-Constraint Workforce Scheduling Authors: Vipul Patel, Anirudh Deodhar, Dagnachew Birru Published: 2026-07-06 Categories: cs.AI, math.OC arXiv: https://arxiv.org/abs/2607.05177v1 Workforce scheduling is an NP-hard combinatorial optimization problem requiring simultaneous satisfaction of labor regulations, coverage requirements, employee preferences and operational objectives. Existing CP formulations typically model simplified instances with 6-12 constraints at shift-level granularity and critically lack explicit support for: mandatory break scheduling with midpoint placement control; acuity weighted workload equity; sub-shift temporal granularity enabling demand-driven staffing; inter-week schedule stability; and cross-midnight shift patterns common in 24-hour operations. This paper presents CP-WSP: a declarative CP-SAT framework enforcing 14 hard constraints as mathematically inviolable requirements (zero regulatory violations by construction) while optimizing 15 soft objectives through a unified weighted penalty function -- all configurable via a JSON specification with no code changes required. Key contributions include: a shift-window variable decomposition enabling mandatory break scheduling with centrality control; acuity-weighted workload equity; multi-granularity temporal resolution from 30 minutes to 2 hours; inter-week schedule stability; a grid-offset preprocessing technique for cross-midnight shifts; and a reproducible 36-configuration benchmark suite for community comparison. Evaluated on INRC-II benchmarks at both hourly and shift-level granularity and on 36 synthetic configurations. --- ### FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection Authors: Aiwen Liu, Chengguang Zhu, Gang Wang, Dandan Zhu, Haodong Lin, Yan Wang, Huiyu Zhou, Zhengyi Pan Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.05176v3 Small object detection (SOD) remains a challenging task in real-world applications. Despite recent advances, existing detectors remain limited by rigid processing that entangle spatial aggregation with implicit frequency aliasing and truncation, leading to inadequate preservation of high-frequency components for SOD. To tackle these limitations, we propose a Frequency-Spatial Domain Collaborative Detection Transformer (FSDC-DETR), a novel collaborative framework that explicitly models complementary spatial and frequency representations. Specifically, we first introduce Dual-Branch Frequency-Spatial Adaptive Fusion (DBFSAF) to enhance frequency diversity and adaptively capture frequency-spatial domain discriminative representations. Building on these representations, a frequency-spatial interaction scheme is further explored within the hybrid encoder to enable progressive feature propagation to the decoder. In particular, structure-aware frequency-spatial aggregation is achieved through Shunt Frequency-Spatial Feature Fusion (SFS-FF), establishing bidirectional interaction and progressive cross-scale propagation between frequency and spatial representations for coherent discriminative modeling. Meanwhile, informative high-frequency responses are preserved during scale transitions through Frequency-Spatial Dynamic Downsampling (FSD-Down), thereby minimizing frequency degradation throughout multi-scale fusion for the precise SOD. Experimental results demonstrate that FSDC-DETR achieves state-of-the-art performance, improving AP by 6.4 on VisDrone-DET2019 and 6.6 on AITODv2, with gains of 6.8 and 6.9 AP for small objects. The code is available at github.com/nevereverinsomnia/FSDC-DETR. --- ### FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection Authors: Aiwen Liu, Chengguang Zhu, Gang Wang, Dandan Zhu, Haodong Lin, Yan Wang, Huiyu Zhou, Zhengyi Pan Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.05176v2 Small object detection (SOD) remains a challenging task in real-world applications. Despite recent advances, existing detectors remain limited by rigid processing that entangle spatial aggregation with implicit frequency aliasing and truncation, leading to inadequate preservation of high-frequency components for SOD. To tackle these limitations, we propose a Frequency-Spatial Domain Collaborative Detection Transformer (FSDC-DETR), a novel collaborative framework that explicitly models complementary spatial and frequency representations. Specifically, we first introduce Dual-Branch Frequency-Spatial Adaptive Fusion (DBFSAF) to enhance frequency diversity and adaptively capture frequency-spatial domain discriminative representations. Building on these representations, a frequency-spatial interaction scheme is further explored within the hybrid encoder to enable progressive feature propagation to the decoder. In particular, structure-aware frequency-spatial aggregation is achieved through Shunt Frequency-Spatial Feature Fusion (SFS-FF), establishing bidirectional interaction and progressive cross-scale propagation between frequency and spatial representations for coherent discriminative modeling. Meanwhile, informative high-frequency responses are preserved during scale transitions through Frequency-Spatial Dynamic Downsampling (FSD-Down), thereby minimizing frequency degradation throughout multi-scale fusion for the precise SOD. Experimental results demonstrate that FSDC-DETR achieves state-of-the-art performance, improving AP by 6.4 on VisDrone-DET2019 and 6.6 on AITODv2, with gains of 6.8 and 6.9 AP for small objects. The code is available at github.com/nevereverinsomnia/FSDC-DETR. --- ### Platonic Projection Structures: Operator-Induced Observability in Representation Learning Authors: Kazuo Ishii, Bishnu Prasad Gautam, Jieling Wu, Javaid Saher Published: 2026-07-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.05175v1 We characterize observability in representation learning through Platonic Projection Structures (PPS), an operator-theoretic framework for analyzing representation accessibility under partial observation. Rather than treating observable outputs as direct reflections of latent representations, PPS models observation through a self-adjoint positive semidefinite operator acting on a latent representation space. A system is represented as a triple $(H, Π, O)$, where $H$ is a latent representation space, $Π\succeq 0$ is an observation operator, and $O(v)=\langle v,Πv\rangle$ defines an induced scalar observable. Observability is characterized by the quotient geometry $H/\ker(Π)$, representing equivalence classes of latent states indistinguishable under observation. We show that quantum measurement and representation inference under linear observation models share this operator-theoretic structure while differing in the algebraic properties of their observation operators; the correspondence is structural rather than physical. Representation transfer and knowledge distillation can likewise be interpreted as approximate preservation of observable geometry through $ΦΠ_T \approx Π_S Φ$. PPS also reveals a structural limitation of output-based interpretability: latent components in $\ker(Π)$ are inaccessible from induced observables, imposing intrinsic constraints on attribution and explanation methods. Controlled empirical validations demonstrate kernel-invariant observability, projection-induced attribution gaps, and rank-controlled observable geometry in latent representation spaces. PPS thus provides an explicit characterization of observability through operator-induced quotient geometry and a unified perspective on representation accessibility, interpretability, and projection-mediated inference. --- ### AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments Authors: Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang et al. Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.05174v1 Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for rigorous and realistic evaluations. However, most existing benchmarks evaluate agents in simplified, idealized settings. They typically rely on pre-packaged tool interfaces, overlook critical steps, and assume inputs are clean and fully specified. Consequently, they understate the difficulty of real deployments, where uncertainty and noise are ubiquitous and agents must proactively explore the environment to uncover new tools. To bridge this gap, we present AgentGym2, a new evaluation framework with task instances grounded in real-world end-to-end working demands. Beyond reasoning and planning, it measures agents' ability to execute end-to-end procedures, discover tools via exploration, compose tools for unseen tasks, and remain robust to noisy and underspecified information. Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2, revealing a substantial gap between the capability of current agents and the demands of real-world applications. --- ### RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain Authors: Omer Moussa, Mariya Toneva Published: 2026-07-06 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.05171v1 Language understanding in the brain is context-dependent, varying across experimental stimuli and individuals, which makes it difficult to build computational models that generalize across both. This calls for a foundation model of language-evoked brain activity that can capture shared structure while adapting efficiently to new participants and inputs. We introduce RABBiT (Rapidly Adaptive BOLD foundation model via BraIn-Tuning), a compact audio-to-fMRI encoder designed for accurate zero- and few-shot prediction. A comprehensive evaluation on 324 participants across multiple unseen fMRI datasets shows that RABBiT enables accurate zero-shot prediction of fMRI responses to natural speech across auditory and language-selective regions, surpassing the SOTA foundation model for fMRI and predictions based on group averages. With as little as 10 minutes of participant-specific data, RABBiT further improves performance via parameter-efficient tuning, substantially outperforming per-participant linear models. RABBiT's performance is driven by two key innovations: (1) learned region-specific attention, and (2) a decomposition of brain responses into shared and subject-specific components, combined with a brain-tuned speech backbone. In addition to supporting strong predictive accuracy, the structured, region-specific representations that RABBiT learns enable interpretability. By eliminating the need for extensive per-participant data and model fitting, RABBiT enables scalable population-level analyses of language in the human brain. We make the code available at https://github.com/bridge-ai-neuro/rabbit. --- ### The Changing Role of Symbolic Methods in Artificial Intelligence Authors: Jun Sun Published: 2026-07-06 Categories: cs.AI, cs.LO arXiv: https://arxiv.org/abs/2607.05168v1 Why do intelligent systems need to perform explicit symbolic reasoning? Computer science has traditionally regarded symbolic reasoning as a defining component of intelligence. Yet the remarkable success of modern foundation models raises a fundamental question: if increasingly capable AI systems can operate with little explicit symbolic reasoning, what role do symbolic methods actually play? This article argues that explicit symbolic reasoning is not a fundamental property of intelligence, but a computational consequence of operating on simplified models of reality. We propose the Compression Principle: every computational model is a simplified representation of reality, and explicit symbolic reasoning compensates for information omitted during model construction. From this principle, we derive the Modeling--Reasoning Trade-off: as computational models preserve richer representations of the world, the need for explicit symbolic reasoning correspondingly decreases. This perspective provides a unified explanation for both the historical success of symbolic methods and the remarkable effectiveness of modern foundation models. Paradoxically, the same development makes symbolic methods increasingly important for humans. As intelligent systems become more capable and more opaque, symbolic representations increasingly serve as interfaces through which humans specify requirements, verify behavior, regulate autonomous systems, and establish trust. We therefore argue that the future of symbolic methods lies not primarily as the computational engine of intelligent systems, but as the symbolic interface between increasingly capable AI systems and the humans who build, govern, and depend upon them. --- ### MeGA-MP: Metric Graph Advection Message Passing -- A Physics-Informed Message Passing Operator for Advection-Dominated Metric Graphs Authors: Janine Strotherm, Luca Hermes, André Artelt, Barbara Hammer Published: 2026-07-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.05167v1 Many real-world systems are organized as networks where spatio-temporal dynamics unfold along connections and not discretely between nodes. Examples include utility networks such as water distribution systems or gas networks, electrical grids, and traffic flow networks. Such systems are naturally modeled as metric graphs, where edges correspond to one-dimensional Euclidean subspaces connected at vertices. Metric graphs are independent of an underlying global Euclidean space, limiting direct application of typical PINNs and operator-learning methods. Especially transport dynamics like advection require a methodology able to capture antisymmetric and long-range dependencies on graphs, which is itself a challenge. We propose a novel physics-informed message passing operator that encodes linear advection on metric graphs as an inductive bias. In the purely advective setting, the operator provably recovers the exact dynamics up to a theoretically derived discretization error without any training. Combined with trainable components like MLPs, our message passing operator extends to realistic advection-reaction dynamics in water distribution systems, where we achieve superior performance compared to baselines and zero-shot generalization across different graph topologies. --- ### Physiological Noise Augmentation Improves Non-Invasive Brain-to-Speech Authors: Benjamin Ballyk, Teyun Kwon, Miran Özdogan, Oiwi Parker Jones Published: 2026-07-06 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.05165v1 Non-invasive brain-to-speech decoding aims to restore communication to patients suffering from neurodegenerative disease, without the risks of neurosurgery. Existing MEG- and EEG-based methods, while scalable, continue to suffer from high word error rates driven by relatively low signal-to-noise ratios compared to invasive recordings. We propose physiological noise augmentation (PNA), a data augmentation method that explicitly trains decoders to become invariant to task-agnostic artifacts (e.g. ocular and cardiac activity). PNA draws inspiration from automatic speech recognition systems, where environmental noise (e.g. dogs barking, city traffic) is added to clean speech to improve robustness. Analogously, we decompose brain recordings into clean data and noise artifacts using independent component analysis (ICA), before scaling and remixing to generate biophysically realistic, label-preserving training examples. We show that PNA approximates anisotropic regularization, penalizing decoder sensitivity along artifact-dominated directions. On MegNIST, a 12k-trial imagined-digit MEG dataset, PNA with 10-trial averaging improves EEGNet decoding accuracy by 4.7 percentage points (absolute) over training on real data alone. Our results suggest that artifact-aware augmentation and trial averaging are complementary tools for improving robustness in non-invasive speech BCIs. --- ### Open Problems in AI Incident Governance Authors: Harleen Kaur Sidhu, Rebecca Scholefield, Nour Annan, Kevin Hernandez, Isabel Nieh Hou, Abdulrahman Alshaikhi, Ze Shen Chin, Rokas Gipiškis Published: 2026-07-06 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2607.05163v1 AI systems may produce failures after deployment that pre-deployment safety assessments do not anticipate. Managing these failures requires what we refer to as adequate \textit{AI incident governance}, where having good definitions, taxonomies, monitoring practices, reporting mechanisms, and incident analysis is essential. We examine existing frameworks related to AI incident governance by regulatory bodies and independent efforts, and find that while there are frameworks that describe how individual functions can be performed, there is a lack of consistency within the aspects of definitions, classification, monitoring, and reporting. These inconsistencies apply to the types of incident data that is collected and reported, the ways in which they are categorised, and as a result, the depth, representativeness, and accuracy of analysis that can be performed. --- ### EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments Authors: Deyao Zhu, Xin Zhou, Shengling Qin, Xuekai Zhu, Hangliang Ding, Shu Zhong, Zixin Wen, Zhonglin Xie, Chenhui Gou, Linxuan Ren, Yueyang Wang, Junfeng Zhong et al. Published: 2026-07-06 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2607.05155v1 Pretraining scaling laws reveal that model capability improves predictably with data and compute. But learning from real world environments after deployment remains far less understood. Analyzing roughly 38,000 hours of agent interaction with the environment across 134 real world tasks, we find, to the best of our knowledge, the first evidence that overall performance during environment learning follows a log-sigmoid scaling law with remarkably high precision, reaching R^2 = 0.998. Across model generations, we also find that agent learning speed roughly doubles every three months. This discovery stems from EdgeBench, a suite of 134 real world tasks with ultra-long horizons, spanning scientific discovery, software engineering, combinatorial optimization, professional knowledge work, formal mathematics, and interactive games. Each task sustains at least 12 hours of continuous agent operation under rich, multilevel feedback, and is built through substantial expert effort. We publicly release 51 tasks and our full evaluation framework to accelerate the study of how agents learn from real world experience. --- ### Geometric Causal Models Authors: Eli N. Weinstein, David M. Blei Published: 2026-07-06 Categories: stat.ML, cs.LG, q-bio.BM arXiv: https://arxiv.org/abs/2607.05153v2 Scientists often seek to draw causal inferences from structured data that is not independently and identically distributed, such as spatial data, network data, or molecular data. We develop geometric causal models (GCMs), a framework for causal inference from dependent data that exploits underlying symmetries of the data generating process. For example, in spatial data, we consider processes that are symmetric under translations, or in graph data, symmetric under permutations of the nodes. We show how symmetries, formalized with group theory, can enable causal identification and estimation. We deploy ergodic theory for amenable groups to establish identification, and combine geometric deep learning with scalable Bayesian inference for estimation. We recover i.i.d. causal models and do-calculus when the data is a sequence and the symmetry is permutation equivariance, and find novel types of causal models when we use alternate structures and symmetries. As an example, we construct a causal model that satisfies the symmetries of DNA. This GCM enables new estimators for the effects of genetic variation, combining deep functional genomics models to describe outcomes and DNA language models to describe propensities. We illustrate on semisynthetic data. --- ### Claim-Level Rubric Rewards for Video Caption Reinforcement Learning Authors: Mingqi Gao, Hongyuan Dong, Yifei Chen, Zhisheng Zhong, Zheng Ruan, Wenjin Hou, Yu Chen, Han Hu, Yansong Tang Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.05150v1 In this paper, we introduce Claim-Level Rubric Rewards (CuRe), a structured reward framework designed to address the reward-design bottleneck in reinforcement learning for dense video captioning. Existing reward designs generally fall into two categories: holistic response-level judgment across heterogeneous criteria, or alignment-based evaluation against reference captions. However, both paradigms suffer from fundamental limitations. Holistic rewards struggle to ensure factual accuracy and are prone to stylistic reward hacking, while reference-based rewards overly rely on rigid textual alignment, failing to preserve the completeness and diversity inherent to open-ended generation tasks. To address these challenges, CuRe reformulates reward modeling as fine-grained claim-level verification. Specifically, CuRe decomposes captions into category-aware atomic claims through a structured rubric, converting holistic evaluation into simpler and more reliable claim-level verification. --- ### Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detection Authors: Peng Zhang, Tingfa Xu, Shuaihao Han, Jianan Li Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.05148v2 Existing multispectral detectors are limited by discrete spectral processing, a scale-dependent shift in the relative reliability of spectral and spatial cues across pyramid levels, and the lack of explicit rotation-equivariant geometric priors for arbitrarily oriented objects. To tackle these limitations, we propose FressDet, a fully rotation-equivariant spectral-spatial learning framework for multispectral object detection, capable of capturing the continuous, ordered nature of spectral structure and enabling reliable spectral-spatial fusion across pyramid levels under arbitrary in-plane rotations. FressDet integrates three complementary components. Spectral Implicit Warp (SpeIW) enables query-based spectral resampling via a coordinate-conditioned implicit field, yielding a monotone, order-preserving warp. Rotation-Equivariant Consistency Weighting (ReCoW) adaptively fuses spectral and spatial branches based on branch reliability, reinforcing informative cues while suppressing noise across pyramid levels. The oriented-aware head exploits group-indexed features to stably predict oriented objects without parameter replication. Taken together, FressDet learns more discriminative and robust spectral-spatial representations even under rotational perturbations. By achieving state-of-the-art performance with 93% fewer parameters on five public benchmarks, FressDet demonstrates its effectiveness and generalizability. --- ### DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation Authors: Xin Cheng, Xingkai Yu, Chenze Shao, Jiashi Li, Yunfan Xiong, Yi Qian, Jiaqi Zhu, Shirong Ma, Xiaokang Zhang, Jiasheng Ye, Qinyu Chen, Chengqi Deng et al. Published: 2026-07-06 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.05147v1 Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel drafters efficiently propose long token sequences in a single forward pass, they suffer from rapid acceptance decay due to a lack of inter-token dependencies. Furthermore, indiscriminately verifying these extended blocks wastes critical batch capacity on tokens with high rejection risks, severely degrading throughput in high-concurrency serving systems. We introduce DSpark, a speculative decoding framework that unifies high-throughput parallel generation with adaptive, load-aware verification. To maintain draft quality, DSpark utilizes a semi-autoregressive architecture, coupling a parallel backbone with a lightweight sequential module, to introduce intra-block dependency modeling and mitigate suffix decay. To optimize system efficiency, DSpark employs confidence-scheduled verification, dynamically tailoring the verification length for each request based on estimated prefix survival probabilities and engine-specific throughput profiles. On offline benchmarks across diverse domains, DSpark substantially improves the accepted length over state-of-the-art autoregressive and parallel drafters. When deployed within the DeepSeek-V4 serving system under live user traffic, DSpark successfully mitigates verification waste. Compared to the established production baseline (MTP-1), DSpark accelerates per-user generation speeds by 60 to 85 percent at matched throughput levels. More importantly, by preventing severe throughput degradation under strict interactivity constraints, it enables performance tiers that were previously unattainable, shifting the Pareto frontier of our serving system. --- ### PDEFlow: Autonomous Agentic PDE Pipelines for Neural Operator Learning and Solver-Free Inference Authors: Akshat Jani, Prathamesh Gadekar, Sakhinana Sagar Srinivas, Venkataramana Runkana Published: 2026-07-06 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.05134v1 We present PDEFlow, an autonomous agentic framework that turns user-level ODE and PDE descriptions into solver-backed neural-operator pipelines. The workflow links problem specification, data generation, operator training, and checkpoint-based inference. A stateful input graph converts multi-turn natural-language input and user edits into validated problem specifications. The data-generation module then samples parameters, solves the configured governing-equation with FEniCSx finite-element backend, and stores the solutions as operator-ready tensors. The training and inference stages use a registry-based interface, allowing different neural operators to be trained and deployed without changing the surrounding pipeline. In the current implementation, we instantiate this interface with a multi-branch Bayesian DeepONet. Experiments on benchmark ODE and PDE tasks show that PDEFlow can construct valid specifications, generate solver-backed datasets, train neural operators across steady and transient problem classes, and provide solver-free predictions from saved checkpoints. The framework is designed for repeatable scientific and engineering workflows where many related physics configurations must be specified, simulated, learned, and queried with minimal manual intervention. --- ### UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation Authors: Mengmeng Liu, Diankun Zhang, Jiuming Liu, Jianfeng Cui, Hongwei Xie, Guang Chen, Hangjun Ye, Francesco Nex, Hao Cheng, Michael Ying Yang Published: 2026-07-06 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.05133v1 World Action Models (WAMs) have shown strong potential for improving action generalization in autonomous driving by using future video prediction as dense supervision for scene dynamics and temporal causality. However, it remains unclear which architecture better transfers video-modeling benefits to trajectory generation. Existing cascaded or dual-DiT designs separate video imagination from action prediction, weakening the transfer of video-learned world dynamics to the trajectory branch: the action model may still overfit dataset-specific driving priors, while the video model only indirectly regularizes planning. We propose UNIVERSE, a unified video-action model built upon a single mask-modulated Diffusion Transformer. By co-training future video latents and ego-trajectory tokens within shared generative parameters, UNIVERSE allows dense video supervision to directly shape trajectory denoising, leading to stronger cross-domain action generalization. To ensure causal validity and efficient deployment, we introduce a Modality-Decoupling Visibility Mask, which shares historical context across modalities while blocking mutual attention between future video and trajectory tokens. This prevents future-target leakage and enables trajectory-only inference by removing future-video denoising at test time, achieving a $4.3\times$ speedup over joint video-action rollout while maintaining comparable planning accuracy. The same model also supports video-only and joint video-action rollouts. Experiments show that UNIVERSE achieves 91.0 PDMS on NAVSIM (vs. 89.6 for the Two-DiT variant), and demonstrates strong zero-shot transfer to nuScenes and Bench2Drive without fine-tuning, while ablations confirm the importance of single-DiT unification, video co-training, and mask-based modality decoupling. --- ### When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games Authors: Jerick Shi, Terry Jingcheng Zhang, Bernhard Schölkopf, Vincent Conitzer, Zhijing Jin Published: 2026-07-06 Categories: cs.CY, cs.CL arXiv: https://arxiv.org/abs/2607.05132v2 As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents that publicly commit to actions will honor those commitments. We place LLM agents in repeated $n$-player games with a three-stage protocol that separates private intent, public announcement, and final action, allowing us to identify whether each deviation from a stated announcement was already planned during private deliberation. Evaluating three frontier models across six games in homogeneous and heterogeneous groups over 10 rounds, we report two findings. First, when agents deviate from their announcements, the deviation is predominantly already stated in their private plan (exceeding 90% in the highest-deception conditions), yet this is not a fixed model property: the same model ranges from perfect honesty to near-total deviation across games. Second, different models interpret announcements incompatibly, some as binding commitments and others as cheap talk, producing payoff gaps that emerge in Round~0 and persist across all 10 rounds. Systems that combine models from different providers therefore cannot assume shared announcement semantics and require empirical testing of model interactions before deployment. --- ### TacReasoner: A Dynamic Tactile-Language Framework for Interactive Reasoning in Real-World Scenarios Authors: Kailin Lyu, Di Wu, Long Xiao, Jianning Zeng, Jianwei He, Chang Lin, Lianyu Hu, Lin Shu, Jie Hao, Ce Hao Published: 2026-07-06 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.05131v1 Among the five primary human senses, tactile is arguably the most fundamental to survival, as it enables the perception of physical contact and interaction in real-world environments. In this paper, we explore two key challenges of integrating tactile sensing into intelligent systems for multimodal reasoning: (i) insufficient modeling of dynamic tactile signals, which restricts reasoning over temporally evolving properties, and (ii) hallucination in tactile foundation models caused by the absence of explicit reasoning mechanisms, leading to unstable real-world inference. To address these challenges, we propose TacReasoner, a dynamic tactile-language framework for interactive reasoning in real-world scenarios. First, TacReasoner incorporates a Dynamic-aware Tactile Encoder to enhance the perception and representation of dynamic tactile signals. More importantly, we introduce TouchCoT-10k, the first tactile chain-of-thought dataset for structured reasoning over tactile inputs. Upon it, we establish DynTac-Bench to systematically evaluate dynamic tactile perception and real-world commonsense reasoning. Experimental results demonstrate that TacReasoner achieves competitive performance against state-of-the-art models across multiple datasets. Notably, despite using only 7B parameters, TacReasoner outperforms the 14B VTV-LLM model on most subtasks, highlighting its effectiveness and efficiency in tactile commonsense reasoning. --- ### Physically-Relevant Information Learning in High-Dimensional Time-Derivatives Spaces Authors: Domiziano Doria, Matteo Becchi, Giovanni M. Pavan Published: 2026-07-06 Categories: physics.chem-ph, cs.LG arXiv: https://arxiv.org/abs/2607.05127v3 Understanding the physics of many-body complex dynamical systems may be a non-trivial task. High-dimensional analysis approaches are often deemed necessary to prevent losing important information. Typically, these use order parameters or descriptors capturing information related to, e.g., relative positions, symmetries, etc., of the units in the studied system. However, in many cases, gaining information related to the relative positions of the constitutive units (or their velocities) alone may be insufficient, and to reach a more complete physical knowledge, one should ideally learn and correlate with each other both structure and dynamics. Here we demonstrate how to achieve such a goal efficiently by building and navigating high-dimensional Time-Derivatives (TiDe) spaces. A TiDe space can be generated for virtually any type of system/phenomenon from the time-series data collected along its observation over time. Each TiDe's dimension corresponds to a growing-order time-derivative of the extracted data, thus containing information related to different physical phenomena/events, which can be easily extracted via unsupervised approaches. We demonstrate how, by definition, TiDes can be directly analyzed without a need for prior dimensionality reduction, providing results that are intrinsically intuitive to interpret. We show the potential of the method by analyzing two prototypical example datasets extracted from molecular dynamics simulations or experimental tracking of different types of complex dynamical systems. Our results demonstrate how efficiently one can navigate and learn in information-rich TiDe spaces, which provide a robust general framework for data analysis and for studying complex dynamical systems from the data collected along their observation over time. --- ### Three-Phase Evaluation of AI-Assisted Software Development Life Cycle Authors: Joshua Strubel, Professor Carrie Russell, Carson Crockett, Jason Ferraro, Nathan Londhe, Uzayr Syed, Jacob Viehe Published: 2026-07-06 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.05125v1 This paper presents an exploratory evaluation of how increasing levels of AI autonomy affect software development productivity, requirement adherence, and developer cognitive workload. A team of four developers reimplemented the same full-stack web application across three sequential phases: partial AI-assisted development using GitHub Copilot, an AI-exclusive workflow using GitHub Copilot, and an AI-exclusive workflow using AWS Kiro. Evaluation metrics included development effort (hours), requirement adherence (RITM score), AI-interaction efficiency, and NASA-TLX workload measures. Across phases, higher levels of AI autonomy were associated with reduced development effort, improved requirement adherence, and lower self-reported mental workload, while developer frustration increased modestly. The AWS Kiro phase achieved the strongest overall performance on most measured dimensions, suggesting that tooling architecture may influence outcomes independently of AI autonomy level. ---