# Research Papers — 2026-07 · bundle page 151 of 222 > Full-text markdown of papers #7501–7550 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/151 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/150.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/152.md) ### VEXAIoT: Autonomous IoT Vulnerability EXploitation using AI Agents Authors: Katherine Swinea, Kshitiz Aryal, Lopamudra Praharaj, Maanak Gupta Published: 2026-07-10 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.09653v1 Internet of Things (IoT) systems are inherently vulnerable due to constrained hardware, outdated firmware, and insecure default configurations, creating a need for scalable and adaptive security testing approaches. While recent adoptions of Large Language Model (LLM) agents have demonstrated promise in penetration testing and Capture-the-Flag (CTF) environments, their application to IoT specific vulnerabilities remains unexplored. This paper presents an autonomous multi-agent framework, referred to as Vulnerability EXploitation using AI Agents (VEXAIoT), for vulnerability discovery and exploitation in IoT environments using LLM-based reasoning and offensive security tools. The framework combines a vulnerability detection agent and an attack execution agent to perform reconnaissance, plan attack sequences, and execute exploits against vulnerable IoT services. The system is evaluated in IoTGoat and Metasploitable environments across ten attack scenarios mapped to OWASP IoT vulnerabilities. Experimental results show attack success rate of up to 100% with low token overhead and average execution times under two minutes for most attacks. Across 260 attack executions, VEXAIoT achieves a 95.0% overall success rate, including 94.5% success in IoTGoat and 96.7% success in Metasploitable2. These results demonstrate the potential for LLM-driven agents to automate IoT vulnerability assessment and offensive security workflows in controlled environments --- ### Revisiting Euler-Angle Regression with Kolmogorov-Arnold Networks Authors: Yangting Sun, Zijun Cui, Yufei Zhang Published: 2026-07-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.09650v1 In many real-world systems, including articulated robots and biomechanical models, rotations are defined in joint space and naturally parameterized by Euler angles with bounded ranges. Yet regressing Euler angles remains challenging, as their discontinuities and singularities often destabilize training. In this work, we revisit Euler-angle regression and show that its effectiveness depends critically on the interaction between rotation representation, regression architecture, and domain constraints. We introduce a new framework that combines range-aware Euler modeling with Kolmogorov-Arnold Networks (KAN), which replace fixed node-wise activations with learnable univariate functions on edges. We further provide theoretical analysis indicating that bounded Euler ranges motivate a near-additive structure in the regression function, which favors the additive functional form of KAN, and we confirm this trend empirically. Extensive experiments on controlled rotation regression, object pose estimation, and robotic and human inverse kinematics demonstrate consistent improvements in accuracy, convergence, and efficiency. The code will be publicly available. --- ### ConceptSMILE: Auditing the Trustworthiness of Concept-Based Explainable AI Authors: Mohadeseh Mollapour, Koorosh Aslansefat, Zeinab Dehghani, Bhupesh Kumar Mishra, Tejal Shah, Zhibao Mian Published: 2026-07-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.09649v1 Concept-based explainable artificial intelligence (AI) can make model reasoning more human-understandable, but concept-level outputs are not automatically trustworthy. We introduce ConceptSMILE, a model-agnostic perturbation-based auditing framework for evaluating the reliability of concept-based explanations. Rather than replacing SMILE, ConceptSMILE extends its perturbation-based logic from feature- or region-level attribution to the auditing of human-understandable concept explanations. The framework perturbs input regions, measures concept-response shifts, applies locality weighting, and fits an XGBoost surrogate to approximate local concept behaviour. Reliability is assessed through attribution accuracy, surrogate fidelity, faithfulness, stability, and consistency. We evaluate ConceptSMILE on retinal fundus images by comparing MedSAM-derived visual concepts with VLM-based semantic concepts. Results show that reliability varies across concepts and pathways: MedSAM achieves stronger spatial attribution and the highest surrogate fidelity ($R^2 = 0.8503$, $R_w^2 = 0.8465$), while the VLM pathway shows stronger vessel faithfulness and stronger stability under selected artefact conditions. ConceptSMILE provides an independent audit layer for evaluating the trustworthiness of concept-based XAI. --- ### Deep Gaussian Processes on Directed Acyclic Graphs Authors: Federico L. Perlino, Oliver Hamelijnck, Adam M. Johansen, Theodoros Damoulas Published: 2026-07-10 Categories: stat.ML, cs.LG, math.ST, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2607.09645v1 Many real-world processes can be represented as compositions of functions along a directed acyclic graph (DAG). In causal modelling, these correspond to the underlying mechanisms; in engineering, to multiple fidelity levels; and in gene-regulatory networks, to transcription factors. These functions are partially observed across the DAG, with noisy and heterogeneously sampled measurements, posing significant challenges for reconstruction, uncertainty propagation, and inference. To tackle these challenges, we place priors over functions and naturally arrive at Deep Gaussian Processes over DAGs. We theoretically study their prior-collapse behaviour, and the effect of graph topology and intermediate observations on the preservation of information. We obtain almost-sure lower bounds on the asymptotic frequency of depths at which the distinction between inputs is preserved, identify broad kernel classes for which these hold, and prove an observation by \cite{dunlop2018} on the role of input connections. We offer a structured variational approximation that retains graph dependencies, preserves compositional uncertainty, and captures the explaining-away behaviour of colliders. Finally, we empirically validate our theoretical results and our methodology, and model a latent-collider DAG, a protein signalling network, and a multi-fidelity heavy-ion collision emulation task, attaining state-of-the-art performance while recovering low-fidelity contributions and yielding interpretability of the simulator hierarchy. --- ### Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detection Authors: Cláudio Lúcio do Val Lopes, Lucca Machado da Silva Published: 2026-07-10 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.09641v1 Financial anomaly detection suffers from extreme class imbalance, causing traditional single-objective algorithms to exhibit ``fraud collapse'', defaulting to the majority class and failing to balance anomaly interdiction with customer friction. To overcome this without distortive data resampling, we propose the Semantic Pareto-DQN, a multi-objective reinforcement learning framework. Our approach synthesizes heterogeneous transaction features into cohesive natural-language narratives, encoded by large language models, thereby producing a robust, scale-invariant state representation. The agent optimizes a vectorial reward that explicitly decouples financial efficacy, operational friction, and semantic discovery. By mapping the continuous Pareto frontier, the system dynamically navigates the asymmetric costs of missed anomalies versus false positives. Empirical evaluations across E-Commerce fraud and UCI Credit datasets show that semantic Pareto-DQN successfully shatters the zero-recall trap. It achieves superior minority-class recall compared to scalarized baselines, providing an alternative to trade bounded operational friction for financial anomaly discovery. --- ### Lean-QIT: Towards a Formal Infrastructure for Quantum Information Theory Authors: Chengkai Zhu, Ziao Tang, Guocheng Zhen, Yimeng Cao, Yusheng Zhao, Ranyiliu Chen, Xuanqiang Zhao, Lei Zhang, Xin Wang Published: 2026-07-10 Categories: quant-ph, cs.AI arXiv: https://arxiv.org/abs/2607.09632v1 Quantum information theory (QIT) characterizes the capabilities and fundamental limits of quantum information processing, underpinning quantum communication, computation, and error correction. Formalizing its coding theorems requires connecting finite-block protocols, analytic inequalities, and asymptotic limits within a unified machine-checked framework. Existing developments, however, lack a reusable operational layer that defines codes, error criteria, achievable rates, and capacities independently of their information-theoretic characterizations. In this work, we present LeanQIT, a Lean 4 library for finite-dimensional QIT. It provides composable, kernel-checked interfaces for quantum states and channels, source and channel codes, finite-block performance criteria, hypothesis testing, one-shot quantities, and asymptotic rate constructions. Using this infrastructure, we formalize Schumacher's quantum source-coding theorem, the Holevo--Schumacher--Westmoreland classical-capacity theorem, and the entanglement-assisted classical-capacity theorem together with its strong converse. By separating operational definitions from analytic characterizations and exposing reusable achievability, converse, and asymptotic components, Lean-QIT provides a machine-readable foundation for formal QIT and a compositional knowledge substrate for emerging AI-assisted formalization, automated proof search, and agentic reasoning in quantum information and computation. --- ### The Effects of Synthetic Data and Label Distribution on Canola Branch Counting Authors: Amirsalar Darvishpour, Mikolaj Cieslak, Adam Runions Published: 2026-07-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.09630v1 Collecting annotated plant images for automated phenotyping is often slow and expensive. Plant models simulating growth and development can generate unlimited synthetic images with exact labels. However, previous work has established that whether incorporating synthetic data improves performance depends on the ratio of synthetic to real images and the label distribution of the synthetic dataset. To systematically quantify both factors, we train ResNet-18 models on a canola branch-counting task using a calibrated L-system plant model. We vary each factor independently. Synthetic-to-real ratios of 1:5 to 1:22 broadly improve performance; the best ratio (1:7) reduces mean absolute difference by 7.6% over real-only training. For label distribution, a uniform synthetic distribution is strongly suboptimal (abs. diff. of approximately 1.70); interpolating 90% toward the real distribution yields abs. diff. 0.927, whereas Gaussian smoothing of the real label distribution yields the best overall result (abs. diff. 0.912, a 14.7% improvement over real-only). A minimum of 10 synthetic images per label offers a simpler alternative with modest gains, while 100 per label over-corrects and hurts performance. --- ### 4DR360: State Reasoning for Joint 3D Detection and Occupancy Prediction in 4D Radar-Camera Full-Scene Perception Authors: Xiaokai Bai, Lianqing Zheng, Runwei Guan, Songkai Wang, Siyuan Cao, Hui-liang Shen Published: 2026-07-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.09629v2 Reliable autonomous driving requires full-scene perception that couples foreground objects with dense semantic layout. Recently, 4D millimeter-wave radar has emerged as a robust and affordable sensor, yet its sparse returns make radar-camera fusion necessary for comprehensive scene understanding. Existing radar-camera methods mainly optimize detection, while dual-task systems usually decode boxes and occupancy with limited interaction. To address this gap and advance radar-based multi-task learning, we propose \method, a 4D radar-camera framework for 360$^\circ$ full-scene perception, which models semantic occupancy as a persistent scene state rather than a terminal output. \method{} follows a cross-modal state reasoning paradigm, where the occupancy state is modeled and propagated through stages for coarse-to-fine feature aggregation. Specifically, State-guided BEV Enhancement (SBE) strengthens intra-frame BEV representation, while Doppler-guided Temporal Fusion (DTF) preserves state evidence over longer temporal horizons. Beyond the model, we further extend ManTruckScenes with satellite-map-based generated occupancy labels and pair it with OmniHD-Scenes in a unified cross-dataset detection-and-occupancy protocol. The resulting experiments cover accuracy, robustness, ablation, and efficiency under one radar-camera multi-task evaluation framework. Code and labels will be released upon acceptance. --- ### Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Incremental Reasoning for QANTA 2026 Authors: Nirjhar Das, Md. Al-Mamun Provath Published: 2026-07-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2607.09623v1 We present our submission to the QANTA 2026 shared challenge at the ICML 2026 Workshop on Efficient Multimodal Question Answering (EMM-QA). Quanta evaluates multimodal quizbowl systems that answer pyramid-style questions from incrementally revealed text and accompanying images while operating under realistic efficiency constraints. The challenge consists of two distinct tasks: Tossup questions, which require deciding when to answer under uncertainty, and Bonus questions, which emphasize accurate answer selection and human adoption. To address these differing objectives, we develop a task-specific two-agent architecture. Our Tossup agent utilizes a GPT-4o-mini-class model (referred to as GPT-4.1-mini in the competition logs) with confidence-calibrated answering and a domain-specific numeric reasoning policy that reduces overconfident predictions from isolated quantitative clues. Our Bonus agent uses GPT-4o-class model (referred to as GPT-4.1) with leadin-aware reasoning, structured relational reasoning, and multimodal evidence integration to improve exact answer selection. Rather than relying on a retrieval pipeline or model ensembles, our approach emphasizes efficient reasoning policies and confidence calibration within a hosted-only environment. Our system achieved the highest overall leaderboard score of 0.402, including a Tossup score of 0.238 and a Bonus Effect score of 0.164. The results demonstrate that lightweight, task-specific reasoning strategies can provide strong performance on resource-constrained multimodal question answering benchmarks. --- ### LLM for EDA in Front-End Design: Challenges and Opportunities Authors: Kangwei Xu, Bing Li, Ulf Schlichtmann Published: 2026-07-10 Categories: cs.ET, cs.AR, cs.LG, eess.SY arXiv: https://arxiv.org/abs/2607.09616v1 As chip complexity increases and time-to-market pressures grow, front-end design has become a critical bottleneck in chip development. Recently, Large Language Models (LLMs) have shown great potential in Electronic Design Automation (EDA). Beyond specification understanding, LLMs show the potential to serve as a unified intelligent interface for hardware description language (HDL) generation, testbench construction, and design space exploration. The rise of agentic AI, represented by pioneering systems such as OpenClaw, offers a strategic roadmap for the next generation EDA. From this perspective, this paper discusses the evolution of EDA from localized assistance to autonomous agentic execution. Then, we review representative advances of LLMs in front-end design, focusing on key tasks such as circuit and testbench generation from a shared specification, as well as design quality improvement in established workflows such as high-level synthesis. Finally, we discuss the key challenges and limitations of integrating LLMs into EDA, and outline future opportunities for advancing LLM-enabled front-end design, offering a systematic perspective for researchers interested in leveraging agentic AI technologies for EDA. --- ### Dynamic Frechet Regression with Feature Selection for Distributional Data Authors: Kiran Adhikari, Amrutha Dinesh, Mathew Kuttolamadom, Ying Lin Published: 2026-07-10 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.09613v1 Many scientific and engineering applications generate responses that are not scalars or vectors, but statistical objects whose form evolves over an ordered index such as time, depth. Probability distributions are a prominent example, capturing variability and uncertainty that cannot be summarized by low-dimensional statistics. When such responses are observed sequentially, the resulting dynamic distributional trajectories pose significant challenges for regression, particularly in relating scalar predictors to both within-index variability and cross-index evolution. We propose Dynamic Fréchet Regression (DFR), a framework for modeling index-dependent trajectories of distribution-valued responses. DFR extends Global Fréchet Regression by introducing an index-aware weighting mechanism. At each index, predictions are defined as weighted Fréchet means in a metric space of distributions (e.g., Wasserstein space), preserving the intrinsic geometry of the response. The weights depend jointly on predictor similarity and index proximity, enabling index-specific prediction while borrowing strength across neighboring indices. To improve interpretability in high-dimensional settings, DFR incorporates a geometry-aware feature selection approach based on sparse metric learning, which identifies predictors driving distributional dynamics without relying on Euclidean coefficients. Simulation studies show improved predictive accuracy and feature recovery over existing methods. An application to additive manufacturing data demonstrates its ability to produce interpretable, index-specific distributional predictions. --- ### Toward Real-Time Sentence-Level Sign Language Translation Authors: Thanh-Hoang Nguyen Doan Published: 2026-07-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.09611v1 Most sign language understanding systems operate at the level of isolated signs, limiting their usefulness in natural communication. We study sentence-level sign language translation (SLT) with the primary goal of real-time deployment rather than proposing a new translation architecture. We fine-tune a SHuBERT-ByT5 translation stack on a uniformly sampled 9,872-example subset of How2Sign, selected because of compute and storage constraints, using QLoRA while keeping SHuBERT frozen. The model obtains a validation BLEU of 16.7 and, on the test split, BLEU 15.9 and BLEURT 44.7. The main contribution is a hardware-aware streaming system: a Raspberry Pi 4B reference client provides camera capture, local text display, and speech output, while compute-intensive perception and translation run on a CPU/GPU backend. The capture protocol remains client-agnostic, so the same backend can serve a browser, phone, or laptop. Chunked ingestion, bounded queues, parallelized perception, temporal reordering, and a sentence-boundary state machine reduce mean post-finalization response latency from 1.873 to 1.354 seconds (27.71%) and P95 latency from 2.919 to 2.130 seconds (27.03%) over the complete 9,872-example working subset. --- ### Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation Authors: Kaiji Zhou, Aleš Leonardis, Yue Feng Published: 2026-07-10 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.09600v2 Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typically call APIs, based on coarse-grained matching between tasks and the functions of expert models or tools, while overlooking critical factors such as performance variability and cost efficiency among functionally similar alternatives. To address this, we propose Agora, a framework that uses a confidence-calibrated auction to dynamically allocate tasks to expert models and tools. By treating reasoning steps as tradeable items, Agora bases allocation on calibrated competence rather than raw confidence. Across five main benchmarks, Agora improves or remains competitive with single-model, routing, and cascade baselines under matched candidate pools. --- ### Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation Authors: Kaiji Zhou, Ales Leonardis, Yue Feng Published: 2026-07-10 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.09600v1 Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typically call APIs based on coarse-grained matching between tasks and the functions of expert models or tools, while overlooking critical factors such as performance variability and cost efficiency among functionally similar alternatives. To address this, we propose Agora, a framework that introduces an incentive-compatible auction mechanism for dynamically allocating tasks to expert models and tools. By treating reasoning steps as tradeable items, Agora enables agents to bid based on their rectified competence-ensuring that critical logic is routed to the most capable solver rather than the most overconfident one. Evaluations across five benchmarks show that Agora improves over matched single-model, routing, and cascade baselines under comparable candidate pools, while exposing a controllable cost-quality trade-off through a single auction parameter. --- ### Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR Authors: Sanjid Hasan, Md. Abdur Rahman Published: 2026-07-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.09598v2 Lightweight speech recognition models are critical for edge deployment, yet highly optimized architectures like Moonshine often fail on morphologically rich, non-Latin languages such as Bengali. This study identifies the root cause of this failure as the model's English-centric byte-level tokenizer, which fragments Bengali words into high-fertility byte chains and triggers catastrophic autoregressive collapse during inference. To resolve this, a novel vocabulary transplantation pipeline is proposed to replace the decoder vocabulary with the native-script BanglaBERT WordPiece vocabulary and resize the corresponding token embedding matrix. Experimental results demonstrate a reduction in token fertility from 9.16 to 1.30. By decreasing autoregressive sequence length by 85.8%, decoding instability is entirely mitigated. When evaluated on the 882-hour Lipi-Ghor dataset, the modified architecture achieves a competitive 21.54% Word Error Rate (WER) and a Real-Time Factor (RTF) of 0.0053. Ultimately, this research provides a scalable, reproducible blueprint for cross-script adaptation of compact ASR models without the need for resource-intensive pre-training. --- ### Characterization of the Basin of Convexity for Multi-Snapshot Spike Deconvolution via Variable Projection Authors: Meghna Kalra, Maxime Ferreira Da Costa, Kiryung Lee Published: 2026-07-10 Categories: stat.ML, eess.SP, math.NA, math.OC arXiv: https://arxiv.org/abs/2607.09593v2 The problem of multi-snapshot spike deconvolution is studied, where the goal is to recover the locations of sparse impulses from their noisy convolution with a known point spread function (PSF) across multiple snapshots. A variable-projection formulation is adopted, in which the amplitudes are eliminated in closed form, thereby reducing the task to a nonconvex least-squares problem over the spike locations alone. This formulation is referred to as the variable-projection formulation of spike deconvolution (VarProSD). An explicit characterization of the basin of convexity of the VarProSD objective is provided in terms of key PSF properties, including its power spectral density and smoothness, revealing how sampling bandwidth and spike separation affect the local geometry. Within this basin, consistency of the estimator in the number of snapshots is established under stochastic noise, and a complementary, sharper error bound is derived under adversarial noise through the local Lipschitz property of the inverse map. Local convergence guarantees for gradient descent are further established when initialization is performed within the basin. A central role throughout the analysis is played by Beurling--Selberg extremal approximations, which enable sharp, PSF-agnostic bounds on the conditioning of the structured matrices arising in the optimization landscape. Numerical experiments are presented to corroborate the theoretical findings and demonstrate the effectiveness of modified ESPRIT initialization followed by gradient-based refinement. --- ### PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers Authors: Yujie Pang, Zudong Li Published: 2026-07-10 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.09590v1 Precision industrial contact manipulation requires reliable robot policies under pose perturbations and contact-force constraints. Vision-language-action models offer broad generalization but often introduce high inference latency and GPU-memory cost, while vision-action chunking policies are more suitable for real-time industrial control. However, these policies are usually trained by behavior cloning and suffer from distribution shift in contact-rich tasks. This paper proposes PAC-ACT, a reinforcement-learning post-training framework for pretrained Action Chunking Transformer policies. PAC-ACT reformulates policy optimization at the chunk level, constructs an ACT-transferred actor-critic architecture, and introduces a hybrid behavior-prior constraint to preserve the pretrained action distribution during online fine-tuning. Experiments on industrial precision-contact benchmarks show that PAC-ACT improves task success, contact stability, and force safety while retaining low latency and low GPU-memory usage. On the Contour task, PAC-ACT significantly reduces peak contact force and decreases the proportion of force readings above 60 N by 46 times. Sparse-reward ablations further show that the proposed behavior-prior constraint enables effective exploration under randomized initial poses. --- ### TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI Systems Authors: Hannah M. Liu, Rhea Saxena, Shiv Asthana Published: 2026-07-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.09586v1 The proliferation of agentic AI systems across enterprise and public-sector contexts has outpaced the capacity of general-purpose AI risk frameworks to classify and govern them. In this paper, we introduce the TrustX Agent Risk Classification Framework, a structured, repeatable instrument that can be applied to seven types of agentic AI systems and is grounded in foundational pre-existing AI governance frameworks. At the core of the framework is a twelve-dimension scoring rubric that robustly quantifies the risk. This rubric is combined with other components, such as the GPA + IAT classification model and the five-level autonomy framework derived from existing literature. These inputs produce a three-tier governance output with mapped control recommendations. A specialised Coding Assistant extension is also included to account for nuances specific to this type of agentic AI system. We then use an illustrative example to show our framework in practice. ARC is intended for AI governance practitioners, risk officers, developers, and regulators, and it will regularly undergo iteration as we continue to expand it and make it more robust. The community can access the interactive framework here: https://arc.responsible.ai/ --- ### Promptable Concept Segmentation from Above: Evaluating SAM 3's Zero-Shot and One-Shot Capabilities in Remote Sensing Authors: Mohammad Dabaja, Turgay Celik Published: 2026-07-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.09583v1 The deployment of large-scale foundation models, such as the Segment Anything Model 3 (SAM 3), promises a transition toward open-vocabulary, training-free computer vision. However, their capacity to generalize out-of-distribution to the complex, top-down geometric structures of Earth Observation imagery remains largely unquantified. Driven by SAM 3's performance disparities in highly specialized domains, we present a comprehensive, multi-task empirical evaluation across remote sensing scene classification, object detection, and instance segmentation under strict zero-shot and one-shot constraints. To achieve this, we introduce a structural adaptation of SAM 3 by repurposing its decoupled binary presence head into a standalone zero-shot classifier. Furthermore, by systematically isolating textual and visual prompt modalities across five configurations, we explicitly diagnose the alignment mechanics within the model's multimodal decoder. Our findings reveal severe cross-modal interference: while visual prompts successfully align the decoder to complex remote sensing geometry, textual prompts inject misaligned, ground-level semantic bias, actively degrading coordinate regression. To benchmark these capabilities without resource-intensive training, we formulate a novel training-free proxy evaluation protocol for Generalized Zero-Shot tasks (scene classification and instance segmentation). Ultimately, our results demonstrate that SAM 3 avoids the overfitting commonly seen in legacy domain-adapted models, achieving high Harmonic Mean scores in segmentation tasks. However, it remains fundamentally constrained by sub-pixel resolution limits and overhead semantic blind spots, charting a definitive mandate for parameter-efficient geospatial fine-tuning of its multimodal decoder. --- ### Entropy-Constrained Machine Learning with Residual Data Augmentation for Modeling Chemical Kinetics Authors: Okezzi Ukorigho, Opeoluwa Owoyele Published: 2026-07-10 Categories: physics.flu-dyn, cs.LG arXiv: https://arxiv.org/abs/2607.09582v1 We present a physics-constrained machine learning framework for accelerating the direct numerical simulation (DNS) of turbulent reacting flows. The model replaces the direct evaluation of detailed chemical source terms with a surrogate that predicts reaction rates from a reduced thermochemical state. To improve physical consistency, the second law of thermodynamics is incorporated as a training constraint by enforcing non-negative entropy generation, which restricts the evolution of the thermochemical state to physically admissible directions and improves stability during time integration. The approach is demonstrated on DNS of a two-dimensional planar lean premixed methane-air flame interacting with a turbulent flow field. The model reproduces detailed-chemistry results with high fidelity while achieving more than an order-of-magnitude reduction in computational cost. Furthermore, a residual-based synthetic data augmentation strategy enables parametric exploration by constructing new training data from the original dataset, allowing accurate simulation at new inlet conditions without additional detailed-chemistry CFD runs. These results demonstrate that thermodynamically constrained machine learning can provide reliable and computationally efficient surrogates for detailed chemistry in high-fidelity combustion simulations. --- ### Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation Authors: Mingyang Huang, Peng Zhang, Li Hu, Guangyuan Wang, Ruoshi Zhang, Yi Lu, Gang Cheng, Bang Zhang Published: 2026-07-10 Categories: cs.CV, cs.SD arXiv: https://arxiv.org/abs/2607.09581v3 Generating long-duration, high-definition, and rhythmically synchronized dance videos directly from music remains a significant challenge, primarily due to the temporal constraints of current diffusion models, which typically fail beyond 20 seconds. Existing approaches, whether they rely on intermediate 3D skeletons or on end-to-end video synthesis, suffer from temporal drift, identity inconsistency, and repetitive motion patterns when extended to longer horizons. To address these limitations, we propose a novel hierarchical framework for minute-scale coherent music-to-dance generation. Our method decouples the process into global keyframe planning and local temporal refinement, leveraging full-track musical context to ensure long-range coherence. Key innovations include dynamic frame rate adaptation via time-mapped RoPE embeddings for precise alignment, an optical-flow-based loss function to enhance motion continuity, and motion-speed control to preserve high-fidelity details during rapid movements. Extensive experiments demonstrate that our framework surpasses the conventional duration barrier, generating stable, 720p/30fps videos exceeding one minute with superior temporal stability. Furthermore, the model exhibits robust versatility across five distinct dance genres, conditioned on both audio and textual prompts, establishing a new state-of-the-art in coherent, long-form dance video synthesis. --- ### Knowledge Graphs and Explainable AI as Complementary Resources for Urban Mining Authors: Jan Gronewald, Andreas Emrich, Nijat Mehdiyev Published: 2026-07-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.09578v1 Pre-demolition assessment, the regulated audit process at the heart of urban mining, is an information process in which AI support must serve qualified auditors who remain accountable for the decisions taken. The relevant unit of value is not prediction accuracy alone, but the defensibility of the supported decisions: their legibility, plausibility, sourcing, and contestability. Explainable AI techniques and domain knowledge graphs each address parts of this requirement, and existing taxonomies have catalogued their integration. The literature is descriptively rich but structurally under-specified: what remains less developed is a structural account of why specific integrations produce artefacts neither resource can provide alone. This paper offers a complementarity-theoretic interpretation grounded in the IS resource-based tradition. We propose four consolidated KG-XAI integration modes (Lifting, Constraining, Typing, and Revising), each defined as a typed operation over XAI artefacts and knowledge-graph substrate structures. Each mode unlocks a distinct property of defensibility and contributes to the kind of regulatory artefact pre-demolition assessment demands. A fire-door example from the urban-mining process illustrates the modes using the W3C Linked Building Data stack and valuation extensions. --- ### SurvFM enables tabular foundation models for right-censored survival prediction Authors: Yue Lyu, Steven H. Lin, Xuelin Huang, Ziyi Li Published: 2026-07-10 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.09577v2 General-purpose tabular foundation models can be adapted across prediction tasks, but right censoring leaves many event times unknown and prevents their direct use as regression labels. SurvFM converts censored follow-up into observation-level targets for restricted mean survival time (RMST), the expected event-free time accumulated up to a chosen horizon. These targets allow multiple tabular foundation models to predict RMST without architectural modification. In simulations with known RMST, SurvFM achieved leading RMST accuracy and competitive discrimination across heterogeneous settings. Its targets were more accurate than simpler outcome constructions, with larger gains as censoring increased. Across 55 public datasets, SurvFM models remained in the leading performance band under full and restricted training. Models fitted in either of two public myelodysplastic syndrome cohorts retained competitive performance in the other without refitting. SurvFM separates censoring handling from prediction architecture, allowing advances in general-purpose tabular prediction to enter survival analysis without model-specific redesign. --- ### A censoring-aware target interface for tabular foundation models in survival prediction Authors: Yue Lyu, Steven H. Lin, Xuelin Huang, Ziyi Li Published: 2026-07-10 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.09577v1 Time-to-event prediction from tabular patient data is central to prognosis and biomedical decision support, but right-censored follow-up prevents direct use of ordinary regression labels. Tabular foundation models offer reusable prediction machinery for modest heterogeneous datasets, yet they generally assume fully observed outcomes. We introduce SurvFM-RMST, a censoring-aware target-interface framework that converts survival outcomes into jackknife pseudo-observation targets for restricted mean survival time, enabling multiple tabular backbones to perform horizon-specific RMST regression without survival-specific fine-tuning. In controlled simulations with known conditional RMST, SurvFM-RMST recovered restricted event-free time accurately, and pseudo-RMST targets outperformed naive restricted observed-time and event-only targets. Across 36 eligible static SurvSet datasets, SurvFM backbones were competitive with established survival and RMST-regression comparators, though relative performance varied by endpoint, horizon and practical constraints. Predicted RMST further stratified held-out patients into groups with ordered observed event-free time and event enrichment. Overall, the results support pseudo-RMST target construction as a portable interface between censored survival data and tabular foundation-model prediction. --- ### Conceptual Networks for Cross-Linguistic Idiomatic Expressions: A Feature-Based Graph Approach Authors: Kiran Pala, Punam Silu, Luxin Yu Published: 2026-07-10 Categories: cs.CL, cs.AI, cs.ET arXiv: https://arxiv.org/abs/2607.09576v2 We present an interpretable network-based framework for representing idiomatic and figurative meaning across eight typologically diverse languages, totaling 160 conventional expressions, the large majority of which are idiomatic. Each expression is annotated with binary conceptual features (containment, concealment, emotional, social, etc.) derived from cognitive-linguistic theory, and pairwise Jaccard similarities define a weighted graph. Community detection reveals that idioms cluster by conceptual schema rather than by language, producing a structure consistent with cognitive-linguistic predictions. The conceptual network captures unique semantic information not present in distributional embeddings, can be scaled via automatic annotation with LLMs, improves downstream idiom detection, and remains robust when enriched with corpus frequencies. Cross-lingual transfer experiments show that conceptual proximity alone can identify acceptable translation equivalents across five language families, with substantial gains over embedding-based baselines. Ablation studies demonstrate that all three feature dimensions -- schemas, roles, and valence -- contribute non-redundantly to both the network's organizational properties and its performance on idiom detection, and that specific graph-derived signals (community membership, neighbor similarity) are particularly informative. The framework offers an interpretable, cross-linguistically stable representation of idiomatic meaning, combining theoretical grounding with practical utility. --- ### Large-Scale Portfolio Optimization Problem Under Cardinality Constraint With Enhanced Multi-Objective Evolutionary Algorithms Authors: Danial Ramezani, Mostafa Abouei Ardakan Published: 2026-07-10 Categories: cs.CE, cs.AI, math.OC, q-fin.PM, q-fin.RM arXiv: https://arxiv.org/abs/2607.09566v1 Decision-making is posing an increasingly formidable challenge to investors because of the growing number of alternatives available in financial markets. A hot area of research over the past few decades has been portfolio optimization that seeks to determine how much an investor should invest in which asset. Introducing real-world conditions to the optimization model turns the problem into an NP-hard one for whose solution exact methods become inefficient; hence, researchers have turned to evolutionary algorithms to approximate solutions. In this paper, strengthening strategies are presented for multi-objective evolutionary algorithms that can provide a faster convergence rate and extensive search ability in the portfolio optimization problem under the cardinality constraint. To implement those features, a unique solution representation, a novel operator, and new repair mechanisms are introduced for solving the aforementioned problem in which lower and upper limits are set on the number of assets in the portfolio. For this purpose, new mating strategies along with the aforesaid package are implemented in well-known multi-objective evolutionary algorithms to solve the problem. The customized algorithms are subsequently tested against traditional ones using well-known market indices as benchmarks. Results indicate that the proposed strategy not only provides better approximations but also converges faster as well at no loss of performance with an increasing number of assets in the market. --- ### TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models Authors: Tianyou Jiang, Ziyu Zhou Published: 2026-07-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.09562v1 Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretraining. Existing few-shot adaptation methods typically introduce additional trainable components, which can be unstable in extremely low-data regimes (e.g., 1-shot), and lack robustness on different medical data. We present TCLA, a purely training-free few-shot adaptation method for Medical VLMs, which is fast and model-agnostic. TCLA corrects inference logits based on a small set of support samples, boosting pretrained VLMs performance by improving inter-class deconfusion and reducing domain shift. Extensive experiments on nine datasets across multiple medical imaging modalities including X-ray, Ultrasound, MRI, CT, Histopathology, demonstrate that TCLA consistently improves OOD performance of Medical VLMs and, in most of cases, outperforms existing training-based adaptation methods. --- ### Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI Authors: Yuan Cao, Haiqian Yang Published: 2026-07-10 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.09560v1 Modern AI systems are increasingly being evaluated for their ability to reason, code, prove theorems, use tools, and long-horizon research tasks. These are powerful capabilities, but they share a structural limitation: the representational frame within which the model operates, including its conceptual vocabulary, the space of admissible solutions it can search, and the criteria by which success is evaluated, is typically fixed and supplied in advance. This paper argues that building stronger intelligent systems capable of open-ended innovation requires additional classes of operations: the creation, stabilization, and reuse of new representational primitives, which alter the space being searched rather than simply searching within it. We characterize the distance between current AI systems and genuinely open-ended intelligence through two gaps. The first is the vocabulary gap, the difficulty of inventing and stabilizing new representational primitives rather than merely recombining existing ones. The second is the verifier gap, the difficulty of judging the value of a new primitive when its full payoff may be visible only after future reuse. We interpret both gaps through a unified framework of intelligence as cognitive discrepancy reduction. By viewing intelligent behaviors as a sequence of cognitive transformations, we distinguish intra-space transformations which operate within a fixed representational frame, from generative transformations which may modify the frame itself. On this basis, we propose a ladder of innovation autonomy and outline several directions for advancing open-ended AI, including objectives that reward useful representational change, persistent memory architectures for invented primitives, and adaptive verification mechanisms capable of evolving alongside the representations they evaluate. --- ### High-Dimensional Interpolators Can Be Fragile: Heavy Tails and High-Dimensional Large Deviations Authors: Youheng Zhu, Yiping Lu Published: 2026-07-10 Categories: math.ST, math.PR, stat.ML arXiv: https://arxiv.org/abs/2607.09547v1 High-dimensional interpolation is common in modern machine learning, but its tail risk is less understood than its expected prediction risk. Existing theory shows that interpolating models can perform well in expectation, yet such guarantees do not determine the probability of rare, severe errors. In operations research and stochastic decision-making applications, rare estimation errors can have disproportionate downstream effects, so tail behavior matters alongside average performance. We study the fragility of high-dimensional linear interpolators using large-deviation methods. We focus on ridgeless regression and compare it with ridge-regularized estimators. We first show that the risk of ridgeless regression can exhibit heavy-tailed behavior: although its expected risk may remain well controlled, its upper tail can decay much more slowly than that of regularized alternatives. We then quantify this phenomenon at the level of large-deviation rates. In the regime we study, ridge regularization suppresses fixed right-tail deviations at the $n^2$ scale, whereas ridgeless regression has only $n\log n$-scale decay, where $n$ is the sample size. This gap shows that interpolation can be statistically fragile even when it is accurate on average. Thus regularization affects the frequency of rare, high-impact risk events in addition to the usual bias-variance tradeoff. --- ### Graph-Regularized Low-Rank Matrix Completion by Variable Projection Authors: Benoît Loucheur, P. -A. Absil, Michel Journée Published: 2026-07-10 Categories: cs.LG, math.NA, math.OC arXiv: https://arxiv.org/abs/2607.09546v1 We address the low-rank matrix completion problem by incorporating graph regularization into the existing Riemannian Trust-Region Matrix Completion (RTRMC) framework. The latter uses the geometry of the low-rank constraint to remodel the problem as an unconstrained optimization problem on a single Grassmann manifold. Our approach, named Graph-Regularized RTRMC (GR-RTRMC), exploits the inherent relationships between rows and columns of the matrix. By using these relationships, we aim to improve the accuracy and robustness of matrix completion, particularly in scenarios where the underlying data exhibits strong correlations between rows or columns. --- ### The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs Authors: Ahmed Oumar El-Shangiti, Abzal Nurgazy, Hilal AlQuabeh, Nikolai Rozanov, Kentaro Inui Published: 2026-07-10 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2607.09544v1 Despite strong performance on many multimodal tasks, vision-language models (VLMs) still struggle with basic object counting. We investigate whether this reflects missing internal knowledge or a gap between internal representations and verbalized outputs. Training simple probes on activations from four VLMs across five counting datasets reveals that nonlinear probes can reliably detect counting errors, suggesting that VLMs often encode the correct count even when they output the wrong answer. SVCCA analysis shows that probes trained on ground-truth counts and probes trained on model outputs occupy a partially shared activation subspace but read out along misaligned directions. We further validate our findings using a causal steering intervention, proving that strengthening the direction of count-identified probes does improve model counting performance. Motivated by this result, we propose a detector-guided self-correction method that selectively re-prompts the model only when an internal error detector predicts failure. This simple inference-time intervention improves counting accuracy by up to 15.6 absolute percentage points, without any parameter updates. Our results establish activation-based error probing as both a practical tool for improving VLM counting and a mechanistic lens on the gap between internal knowledge and model outputs. --- ### CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding Authors: Gabriel Mahuas, Victoria Shevchenko, Ugo Tanielian, Yassir Bendou, Richard Gao Published: 2026-07-10 Categories: cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2607.09543v1 Self-supervised pretrained foundation models (FM) have shown early promise for non-invasive electroencephalogram (EEG) decoding applications. Many recent large-scale models converged on the approach of tokenizing raw EEG followed by masked reconstruction pretraining. However, this recipe has been shown to be suboptimal for data, like EEG, with high noise amplitude and information confined to limited dimensions such as narrow frequency bands. Building on this insight, we develop a novel contrastive-pretrained EEG model with multiscale temporal convolution input layers and Transformer encoder blocks (CoCoT). CoCoT matches or beats state-of-the-art reconstruction-pretrained EEG models on extensive benchmark decoding tasks with heterogeneous electrode configurations. Furthermore, CoCoT trained from scratch outperforms previous single-task decoding models and even rivals pretrained models, showcasing the architecture's flexibility and data efficiency. Through systematic ablations, including model architecture and pretraining objective, we demonstrate the viability of contrastive learning for building EEG FMs while suggesting key architectural design considerations, prompting further investigations in alternative large-scale pretraining strategies. --- ### GatedLinear: Adaptive Routing of Complementary Linear Bases for Time Series Forecasting Authors: Qitai Tan, Ruiwen Gu, Yilin Su, Mo Li, Xu Lin, Xiao-Ping Zhang Published: 2026-07-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.09537v1 Time series forecasting requires models to capture diverse, often mutually exclusive, temporal dynamics, from smooth trend continuation to nonstationary drift and strict phase-aligned recurrence. While recent deep learning models have improved accuracy, they typically force these diverse patterns through a single computational backbone governed by fixed algorithmic inductive biases (e.g., self-attention or spectral filtering). This single-mechanism approach often struggles with the profound heterogeneity of real-world series, where different variables and forecast horizons necessitate fundamentally different predictive treatments. To address this, we propose GatedLinear: a lightweight framework that frames forecasting as the adaptive routing of complementary linear bases. GatedLinear leverages a pool of three specialized mechanisms: a global trend-seasonal basis for smooth projection, a difference-based incremental basis for nonstationary drift, and a phase-aligned recurrence basis for explicit cyclic reuse. To dynamically orchestrate these distinct behaviors, we introduce a Tri-Factorized Fusion Gate that disentangles routing decisions into channel-specific preferences, horizon-aware offsets, and phase-indexed biases derived from known future time marks. This design allows the model to perform highly granular, point-wise soft routing across different predictive regimes without stacking computationally heavy neural modules. Experiments on standard benchmarks show that our method achieves state-of-the-art or highly competitive accuracy against recent complex foundational models, while offering explicitly interpretable routing patterns and operating with a substantially smaller parameter footprint. --- ### Statistically Undetectable Backdoors in Deep Neural Networks Authors: Andrej Bogdanov, Alon Rosen, Neekon Vafa Published: 2026-07-10 Categories: cs.LG, cs.CR, stat.ML arXiv: https://arxiv.org/abs/2607.09532v1 We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box setting, meaning that the backdoored and honestly trained models are close in total variation distance, even given the full descriptions of the models (e.g., all of the weights). The backdoor provides access to invariance-based adversarial examples for every input, mapping distant inputs to unusually close outputs. However, without the backdoor, it is provably impossible (under standard cryptographic assumptions) to generate any such adversarial examples in polynomial time. Our theoretical and preliminary empirical findings demonstrate a fundamental power asymmetry between model trainers and model users. --- ### FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech Synthesis Authors: Ahmet Erdem Pamuk, Ömer Yentür, Ahmet Tunga Bayrak, Yavuz Alp Sencer Öztürk, Mustafa Yavuz Published: 2026-07-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.09530v2 We introduce Freya-TTS, a compact, tokenizer-free, Turkish-first text-to-speech model designed for highly reliable and efficient conversational synthesis. Freya-TTS is a 183.2M-parameter non-autoregressive conditional flow-matching Diffusion Transformer (DiT) that operates in the continuous latent space of the frozen AudioVAE2 (16 kHz encode, 48 kHz decode), allowing the model to focus its capacity on text-to-latent mapping while inheriting high-quality 48 kHz reconstruction. We advance the framework along three key dimensions: (1) rule-free end-to-end modeling from a 92-symbol Turkish character vocabulary without a phonemizer, grapheme-to-phoneme frontend, or discrete speech tokenizer, with digit strings expanded to their spoken form at the text frontend; (2) non-autoregressive parallel denoising, which predicts the entire latent sequence simultaneously over a predicted duration; and (3) a production-oriented two-stage post-training recipe consisting of single-speaker voice locking and short-utterance coverage, improving speaker consistency and robustness on short inputs. On the Freya-TR-Eval benchmark, Freya-TTS achieves a band-matched word error rate (WER) of 8.0% and character error rate (CER) of 3.0%, lower error than both larger open systems in its field, XTTS-v2 and F5-TTS, at 40-55% of their parameter count, together with the highest naturalness (MOS) among the compact systems. The model achieves a real-time factor of 0.11 on a consumer GPU (RTX 4090; ~0.14 mean on an H100) and synthesizes in real time on a laptop CPU, making it well suited for resource-constrained edge deployment. We release the model weights, training and inference code, and evaluation benchmark under the Apache-2.0 license. --- ### TSAI-MetaFraud: A Benchmark Dataset for Financial Fraud Transaction and Behavioral Risk Detection in Metaverse Ecosystems Authors: Refat Ishrak Hemel, Ehsan Hallaji, Roozbeh Razavi-Far Published: 2026-07-10 Categories: cs.LG, cs.CR, cs.DB, cs.SI arXiv: https://arxiv.org/abs/2607.09528v1 The emergence of metaverse platforms has created virtual economies that introduce new challenges related to fraud, bot activity, and illicit financial behavior. Despite growing interest in trustworthy metaverse analytics, existing datasets typically focus on user behavior, authentication, or financial transactions in isolation, limiting the development and reproducible evaluation of multimodal fraud detection methods. To address this gap, we present TSAI-MetaFraud, a multimodal, multi-task benchmark dataset for fraud analytics in virtual economies. TSAI-MetaFraud integrates behavioral, transactional, and graph-structured information while incorporating realistic fraud and automated bot scenarios. We define benchmark tasks including transaction fraud detection, cross-modal node classification, temporal link prediction, and weakly supervised fraud detection, and provide baseline evaluations using machine learning models and graph neural networks. By jointly capturing behavioral activity, financial interactions, and relational structure within a unified virtual economy, TSAI-MetaFraud provides a benchmark for advancing multimodal learning, graph mining, fraud analytics, and trustworthy AI in emerging metaverse ecosystems. --- ### ALICE: Learning a General-Purpose Pathology Foundation Model from Vision, Vision-Language, and Slide-Level Experts Authors: Jiawen Li, Tian Guan, Huijuan Shi, Xitong Ling, Mingxi Fu, Anjia Han, Chao He, Yonghong He Published: 2026-07-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.09526v1 Foundation models are reshaping computational pathology, yet their capabilities remain shaped by pretraining objectives, data sources, and spatial scales, fragmenting complementary expertise across separate backbones. Here we present ALICE, a unified foundation model trained through multi-stage agglomerative distillation that sequentially distills eight vision-only, vision-language, and slide-level teacher models into dedicated modules of a single backbone. ALICE is pretrained on 24,985,184 tile-level pathology images and 155,604 high-resolution images, and evaluated across 21 task scenarios, 96 downstream tasks, and 48 data sources, spanning region-of-interest tissue analysis, vision-language multimodal evaluation, and whole-slide clinical assessment. In all three evaluation settings, ALICE achieved the best average rank among task-matched pathology foundation models. These results demonstrate that agglomerative distillation can consolidate complementary capabilities from specialized models into a unified backbone for broad computational pathology applications. The model is available at https://github.com/WonderLandxD/ALICE. --- ### SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction Authors: Chongyu Qu, Can Cui, Zhengyi Lu, Junchao Zhu, Tianyuan Yao, Junlin Guo, Juming Xiong, Yanfan Zhu, Yuechen Yang, Bennett A. Landman, Yuankai Huo Published: 2026-07-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.09521v1 Does every cancer patient truly need a complete diagnostic workup for accurate survival prediction? In multimodal clinical oncology, diagnostic modalities follow a clinically mandated order of escalating burden -- from demographics collected at intake to genomic profiling requiring specialized tissue analysis. Current multimodal survival methods either assume all modalities are available or passively handle missing data, but none actively reason about whether acquiring the next modality is justified for a given patient along this ordered workflow. We formulate this as a sequential decision problem and propose SAGEAgent (Sequential Acquisition Guided by Experience), a self-evolving LLM-based clinical agent that decides which diagnostic modalities to acquire for each patient, balancing predictive accuracy against clinical invasiveness. SAGEAgent reasons about each patient's evolving diagnostic state through clinical tools that translate numerical predictions into text, an episodic memory that retrieves similar past cases, and a semantic memory that accumulates reusable decision patterns from experience. Experiments on a glioma cohort combining TCGA-LGG, TCGA-GBM, and BraTS with four diagnostic modalities demonstrate that SAGEAgent achieves competitive survival prediction accuracy while reducing average acquisition burden by 55%. --- ### Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference Authors: Junfei Zhan, Haoxun Shen, Mingang Guo, Zixuan Huang, Tengjiao He Published: 2026-07-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.09520v2 Vision-Language Models (VLMs) are the perceptual backbone of embodied AI, but their energy footprint on edge hardware remains poorly understood. Existing efficiency efforts focus predominantly on reducing visual tokens, implicitly treating visual processing as the dominant energy cost. We overturn this implicit assumption through the first systematic energy profiling of on-device VLM inference, spanning five models across three architecture families, four input resolutions, and two hardware platforms (NVIDIA RTX 3070 and Jetson Orin NX). Our analysis yields three findings. First, average inference power is a model-intrinsic constant, invariant to input resolution, image complexity, and prompt type, with less than 5% variation across all conditions. This means that all energy variation across inputs must arise from variation in inference time, not from variation in power draw. Second, each output token costs 11 to 39x more wall-clock time than each input token due to the compute-bound and memory-bound asymmetry between prefill and decode, making output token count the dominant driver of both latency and energy. Third, image complexity, measured by the number of objects in an image, induces up to 4.1x energy differences at identical resolution. This variation arises not from increased visual processing cost, but from differences in output length. These findings expose a fundamental limitation of visual token pruning: even removing all visual tokens saves at most 10% of total energy for fixed-token models. Across models spanning 1 billion to 8 billion parameters, controlling output length saves up to 97% of total energy, with the energy dominance of decoding growing stronger at larger model scale. In short, the true energy bottleneck in edge VLM inference is not what the model sees, but how much it says. Code is available at https://github.com/Junfei-Z/seeing-is-free. --- ### Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference Authors: Junfei Zhan, Haoxun Shen, Mingang Guo, Zixuan Huang, Tengjiao He Published: 2026-07-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.09520v1 Vision-Language Models (VLMs) are the perceptual backbone of embodied AI, but their energy footprint on edge hardware remains poorly understood. Existing efficiency efforts focus predominantly on reducing visual tokens, implicitly treating visual processing as the dominant energy cost. We overturn this implicit assumption through the first systematic energy profiling of on-device VLM inference, spanning five models across three architecture families, four input resolutions, and two hardware platforms (NVIDIA RTX 3070 and Jetson Orin NX). Our analysis yields three findings. First, average inference power is a model-intrinsic constant, invariant to input resolution, image complexity, and prompt type, with less than 5% variation across all conditions. This means that all energy variation across inputs must arise from variation in inference time, not from variation in power draw. Second, each output token costs 11 to 39x more wall-clock time than each input token due to the compute-bound and memory-bound asymmetry between prefill and decode, making output token count the dominant driver of both latency and energy. Third, image complexity, measured by the number of objects in an image, induces up to 4.1x energy differences at identical resolution. This variation arises not from increased visual processing cost, but from differences in output length. These findings expose a fundamental limitation of visual token pruning: even removing all visual tokens saves at most 10% of total energy for fixed-token models. Across models spanning 1 billion to 8 billion parameters, controlling output length saves up to 97% of total energy, with the energy dominance of decoding growing stronger at larger model scale. In short, the true energy bottleneck in edge VLM inference is not what the model sees, but how much it says. --- ### Failure as a Process: An Anatomy of CLI Coding Agent Trajectories Authors: Xiangxin Zhao, Han Li, Shuaiting Li, Tianyi Zhao, Earl T. Barr, Federica Sarro, He Ye Published: 2026-07-10 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.09510v1 Large language model (LLM) coding agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a growing concern. Existing empirical studies investigate why coding agents fail, yet they largely treat failure as a final outcome rather than a temporal process, providing limited insight into how failures emerge, evolve, and become unrecoverable. We present the first large-scale empirical study of CLI coding-agent failure trajectories, introducing a process-oriented framework that analyzes failure through its onset, evolution, and recovery across execution trajectories. We first collect 3,843 execution trajectories generated by seven frontier models across three coding-agent scaffolds (OpenHands, MiniSWE, and Terminus2) on Terminal-Bench, then carefully filter them to obtain 1,794 complete and valid trajectories for manual annotation (over 63,000 execution steps), from which we derive 14 findings spanning failure occurrence, root causes, recovery, and cross-system consistency. Our findings show that coding-agent failures are predominantly driven by epistemic errors, typically begin within the first few execution steps, and often remain hidden until recovery is no longer possible, suggesting that improving coding-agent reliability requires earlier validation and intervention rather than relying solely on final-outcome evaluation. --- ### DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion Authors: Sithu Aung, Viktor Kocur, Yaqing Ding, Torsten Sattler, Zuzana Kukelova Published: 2026-07-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.09507v1 Global Structure-from-Motion (SfM) is an efficient paradigm for recovering camera poses and sparse 3D structure from unordered images. However, its reliance on scale-ambiguous epipolar geometry makes global positioning sensitive to noisy baseline estimates and weak view-graph constraints, while false edges from visually ambiguous pairs can further degrade reconstruction. We propose DGSfM, a depth-aware global SfM pipeline that uses monocular depth maps as a scalable prior while preserving explicit multi-view optimization. For each image pair, we use a depth-aware relative pose solver to convert scale-ambiguous epipolar constraints into scale-aware relative pose constraints. We further improve robustness through view-graph filtering and depth-consistency-based correspondence pruning, which suppress false edges and matches that remain plausible under epipolar geometry alone. Finally, global scale averaging and depth-guided pose-point initialization align monocular depth maps into a common reconstruction scale and provide stable initialization for global positioning and bundle adjustment. Experiments on ETH3D and IMC2021 show that DGSfM consistently improves over strong global SfM baselines across sparse and dense matching front-ends, achieving substantial gains in pose accuracy. Code is available at https://github.com/sithu31296/DGSfM. --- ### What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility Authors: Filippo Ziliotto, Luciano Serafini, Lamberto Ballan, Tommaso Campari Published: 2026-07-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.09503v1 A fundamental challenge in 3D reconstruction and robotic localization is co-visibility: determining which image pairs share overlapping visible surfaces, particularly in scenarios with minimal overlap. We demonstrate that VGGT implicitly encodes co-visibility as an emergent behavior: without any supervision for this task, its internal representations exhibit a clear hierarchical structure mirroring that of large language models, i.e. early layers build a 3D-aware scene representation, while late layers act as dedicated co-visibility reasoners. In particular, we identify layer L17 as a negative anchor that consistently routes non-co-visible pairs for this backbone, regardless of the evaluation setting, providing task-grounded evidence of layer specialization in a geometry-grounded foundation model. Building on this, we introduce Co-VGGT, which freezes VGGT and trains only a lightweight layer-wise mixture-of-experts head (less than 7.5M parameters) to classify co-visibility from RGB alone, treating each layer as a specialized expert whose geometric abstraction is adaptively weighted per input pair. On the Co-VisiON benchmark, Co-VGGT surpasses the human annotation baseline and improves over prior work by more than 25% pairwise and 10% multiview. Pairwise predictions are well-calibrated (ECE=0.030), enabling direct use as edge weights in visibility graphs for downstream SfM and SLAM pipelines without post-hoc correction. Code and data are available. --- ### All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models Authors: Pan Li Published: 2026-07-10 Categories: cs.LG, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2607.09502v1 Explaining machine-learning models is increasingly important for decision-making and consumer trust, yet it is widely believed to come at a cost: existing Explainable AI (XAI) methods suffer from a persistent accuracy-explainability trade-off. We argue that this trade-off is not fundamental, but an artifact of treating explanation and prediction as separate objectives; when properly coupled, they become complementary, so that equipping a model to explain itself improves, rather than degrades, its accuracy. We introduce the Rashomon Explanation paradigm, which builds a set of faithful, prediction-guiding explanations rather than a single one, and prove that this set is generally non-empty and that explanation fidelity bounds the performance of the models it guides. To explore this set, we propose RashomonLLM, an Explanation-Prediction-Reflection agentic workflow that generates explanations in natural language by iteratively aligning them with predictions, and we prove it converges and recovers the full set. Across customer-churn classification, clinical survival regression, and industrial click-through prediction on large-scale live-streaming logs, RashomonLLM significantly outperforms state-of-the-art prediction and XAI baselines on both accuracy and explanation quality, with gains driven by explanation fidelity and robust to distribution shifts, temporal splits, and seeds. Our framework thus advances business performance while laying the groundwork for consumer trust. --- ### Normalisation-Based Likelihood Ratio Estimation for Forensic Authorship Verification Authors: Sadie Barlow, Andrea Nini, Edoardo Manino Published: 2026-07-10 Categories: cs.CL, stat.AP arXiv: https://arxiv.org/abs/2607.09501v1 Authorship verification (AV) is the task of determining whether two texts were written by the same author. In a forensic context, the strength of AV evidence can be quantified using likelihood ratios. Most AV methods are score-based and deriving well-calibrated likelihood ratios from these scores requires a separate calibration model. This, in turn, requires additional amounts of case-relevant data, which is often time-consuming to obtain and prepare. This study proposes two novel normalisation techniques, the Square Root Correction and the Hapax Correction, for deriving likelihood ratios from the AV method LambdaG without the need of a calibration model (Nini et al. 2026). These corrections are designed to mitigate the overestimation of evidential strength that may result from long or highly repetitive texts. Performance is evaluated against logistic regression calibration across fifteen corpora and a range of text lengths (100-9,500 tokens), using the log-likelihood ratio cost (Cllr). The proposed methods achieve performance comparable to logistic regression calibration, with the Hapax Correction outperforming it in approximately 45% of tests (weighted by corpora). Furthermore, performance was more frequently close (within 5%) when the Hapax Correction was outperformed by logistic regression calibration, compared with the reverse comparison. Eliminating the need to train a calibration model reduces data-requirements, time and complexity, thereby increasing the accessibility and transparency of forensic text comparison. This combination of empirical performance and practical advantages supports the adoption of the proposed methods in forensic settings. --- ### Shared Selective Persistent Memory for Agentic LLM Systems Authors: Sanjana Pedada, Aditya Dhavala, Neelraj Patil Published: 2026-07-10 Categories: cs.AI, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2607.09493v2 Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the domain constraints, data schemas, tool configurations, and output preferences that made previous sessions productive. We introduce shared selective persistent memory, an architecture that retains four categories of reusable context - task specifications, data schemas, tool configurations, and output constraints - while discarding session-specific reasoning traces, and that packages them into workspaces transferable across users under role-based access control. The resulting cost curve is non-monotonic. In a controlled replication on four public datasets, where a formatting specification is established once and then withheld, no memory completes 0/12 trials at 3.8K input tokens, selective memory completes 12/12 at 3.9K, and full conversation history completes 8/12 at 7.7K. What is kept matters more than how much is kept: the winning configuration costs essentially what the failing one does, and twice as much context does not improve on it. Both differences from no memory survive Bonferroni-corrected exact McNemar tests (p = 0.0005, p = 0.008); the two memory conditions separate on price rather than completion. We implement this in a deployed platform where agents produce git-versioned artifacts from CSV, SQL, REST, and MCP sources. A complementary zero-token data refresh contract decouples generated programs from runtime data, firing on 12/12 trials at a median 0.08s with no model call, while summary-driven data representation costs 97-431x fewer tokens than raw injection. Across 24 recurring enterprise tasks selective memory completes 23/24 against 19/24 and 17/24, though at that sample no pairwise difference reaches significance. --- ### Shared Selective Persistent Memory for Agentic LLM Systems Authors: Sanjana Pedada, Aditya Dhavala, Neelraj Patil Published: 2026-07-10 Categories: cs.AI, cs.MA, cs.SE arXiv: https://arxiv.org/abs/2607.09493v1 Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is token-inefficient and counterproductive: irrelevant context degrades generation quality. We introduce shared selective persistent memory, an architecture that identifies and retains four categories of reusable context (task specifications, data schemas, tool configurations, and output constraints) while discarding session-specific reasoning traces. Crucially, this memory is shared: workspaces encapsulating selective memory can be transferred across users with role-based access control, enabling collaborative reuse without redundant specification. We implement it in a deployed collaborative workspace platform where LLM agents produce, edit, and maintain git-versioned artifacts (dashboards, reports, and data-driven documents) from heterogeneous sources (CSV, SQL, REST APIs, and MCP servers). A complementary zero-token data refresh mechanism decouples generated programs from runtime data, enabling artifact reuse without re-invocation. Across three enterprise scenarios, shared selective persistent memory achieves 96% task completion (vs. 79% without memory and 71% with full history). Zero-token refresh eliminates LLM re-invocation for recurring updates (14x task-time reduction), while summary-driven generation cuts per-invocation token cost by 97x versus raw data injection. A replication on four public datasets confirms generalizability, with zero-token refresh succeeding in 12/12 trials. Notably, naive full-history persistence actively degrades completion by biasing the agent with stale traces, while selective memory outperforms both extremes. --- ### Multimodal Reward Hacking in Reinforcement Learning Authors: Jiayu Yao, Yiwei Wang, Anmeng Zhang, Zhe Sun, Songsong Wang, Lingrui Mei, Yuyao Ge, Shenghua Liu Published: 2026-07-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.09492v1 Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance. This risk is amplified when visual evidence is evaluated by text-only or weakly grounded rewards. We study reward hacking in MLLM RL across safety VQA, chart VQA, and stress-test settings, varying reward design, data ambiguity, model scale (2B-32B), and RL algorithm (GRPO, RLOO, DAPO). We introduce Newly Rewarded Failure Rate (NRFR), which measures failures among samples whose proxy reward improves over the SFT baseline. Outcome-only rewards cause severe hacking, reaching 48.1% Reward Hacking Rate (RHR), while NRFR exceeding RHR shows that RL creates new failures rather than merely inheriting them. Scaling reduces but does not eliminate hacking: even the 32B model retains a 54.9% worse rate under outcome-only rewards, whereas answer-aware rewards improve the oracle trend at every scale. Robustness is also algorithm- and scale-dependent: GRPO is consistently most resistant, RLOO remains vulnerable, and DAPO improves substantially from 2B to 8B. Visual-evidence rewards help only with reliable verification: keyword-based checks increase hacking, while VLM-as-judge semantic verification reduces it. Overall, multimodal reward hacking is a systematic result of optimizing imperfect rewards, and robust alignment requires rewards and verifiers that remain reliable under optimization pressure. --- ### Terminal Dimension Reduction for Time Series with Applications Authors: Alexander Munteanu, Matteo Russo, David Saulpic, Chris Schwiegelshohn Published: 2026-07-10 Categories: cs.DS, cs.CG, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2607.09490v1 Terminal embeddings have emerged as a powerful tool for dimension reduction. Given a set of points $P\subset \mathbb{R}^d$, a terminal embedding is a mapping $f:\mathbb{R}^d\rightarrow \mathbb{R}^t$ that preserves the pairwise distance between any pair of points $p\in P$ and $q\in \mathbb{R}^d$ up to small distortion under this mapping. Terminal embeddings have been particularly fruitful for constructing $k$-means and $k$-median coresets, where the objective is to find a typically weighted subset $Ω$ of $P$ such that for any candidate solution, the cost of the clustering objective on $Ω$ approximates the cost of the clustering objective on $P$ up to small distortion. Unfortunately, these techniques have not been extended to more complicated structures such as clustering time-series data under common straight-line interpolation between measurements. The main issue is that terminal embeddings, arguably the central technique in this line of research, cannot be linear and are thus not immediately suitable to preserve linear structures. In this work, we develop a generalization of terminal embeddings to affine line-segments that overcomes this issue. We showcase their applicability by using our lines-preserving terminal embeddings to obtain the first dimension-free coresets for clustering time-series under the Fréchet distance. The underlying dimension reduction uses Johnson-Lindenstrauss (JL) embeddings, and our experiments indicate that terminal embeddings perform similarly to JL and favorably against PCA for synthetic and real-world time-series, while only terminal embeddings extend pairwise distance preservation to the full ambient space. --- ### Ceci n'est pas une pipe: AI systems as semantic abstractions Authors: Jade Alglave, Patrick Cousot Published: 2026-07-10 Categories: cs.AI, cs.PL arXiv: https://arxiv.org/abs/2607.09489v2 An AI system's output is not the fact or world state it appears to describe, but rather an engineered representation. We propose a semantic framework to describe AI systems, to be able to examine the correctness of such representations. To do so, we distinguish what is justified by accepted domain knowledge, what reference sources say, and what the system can currently use. This allows us to give precise definitions to common failures: extrapolation, refuted or unsupported assertion, sources versus knowledge mismatch, stale or refuted source, added hypotheses, unsupported use... We hope our framework gives a useful vocabulary for specifying and checking AI systems whose outputs, citations, tool calls, and world-changing actions must be justified by reliable claims and explicit authority rather than apparent fluency. ---