# Research Papers — 2026-07 · bundle page 71 of 222 > Full-text markdown of papers #3501–3550 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/71 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/70.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/72.md) ### Visual Information Extraction from Documents via Classification-Guided Large Vision-Language Models Authors: Huafu Li, Guo Chen, Jia Xia, Lei Wang, Wei Du, Yun Yao, Weijun Peng, Liming Li Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.22723v1 Visual information extraction (VIE) from visually rich documents remains challenging due to high layout variability and real-world impairments. Existing methods typically rely on sequential OCR pipelines or end-to-end models requiring extensive labeled data and layout-specific training, limiting their scalability.We propose a classification-guided large vision-language model (LVLM) framework for multi-type VIE that achieves high accuracy with minimal supervision. The approach decouples document-type classification from content extraction and employs in-context learning (ICL)-based dynamic prompt engineering to inject task-specific knowledge, enabling robust zero-shot inference across diverse layouts. From a theoretical perspective, the proposed method can be viewed as a form of conditional computation that reduces task uncertainty and improves information efficiency during prompt-based inference. Evaluated on a real-world bidding dataset with 16 certificate types, our zero-shot method (based on Qwen2.5-VL-7B) outperforms a strong supervised baseline by 18.35 percentage points in F1-score (86.43\% vs. 68.08\%) and 0.23 in normalized edit distance (0.90 vs. 0.67). Optional domain-specific fine-tuning further improves performance to 93.65\% F1 and 0.93 NED, demonstrating superior robustness against seals, watermarks, and low contrast. The framework offers an efficient, scalable solution for complex document understanding in office automation. Code is available at https://github.com/FairmeHIT/Multi-VIE, and fine-tuned models at https://huggingface.co/fairme/Qwen2.5-VL-7B-SFT. --- ### A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection Authors: Ali Borji Published: 2026-07-22 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.22722v1 Almost all adversarial attacks add an imperceptible perturbation to fool a model. We instead study the opposite: a large, clearly visible perturbation that causes the model to keep its original, correct prediction, even though a human would no longer recognize the image. Prior work showed such examples can be generated at scale but left three questions untested: whether humans really perform worse than the model, whether standard out-of-distribution (OOD) detection and calibration tools catch it, and whether existing defenses mitigate it. We answer all three on MNIST, CIFAR-10, and ImageNet. (i) An independent recognizer proxy drops to ~49% on CIFAR-10 while the model stays at 100% -- a gap a small human pilot (N=5) corroborates directly and that is not explained by signal loss (a matched-magnitude Gaussian control degrades recognizability faster); a CLIP zero-shot proxy confirms the gap at ImageNet scale too. (ii) Confidence- and energy-based OOD detectors and calibration are structurally blind (0% detection, ECE ~= 0), while a feature-space Mahalanobis detector flags 100% -- but is evaded by an adaptive attacker at no cost to success. (iii) No classical defense, including adversarial training (45% robust accuracy), reduces attack success (correlation with large-epsilon_l resistance r ~= 0). A mechanistic analysis further shows the attack destroys low-level texture far faster than edge/shape structure. --- ### Generative and multimodal AI for materials prediction and design: Progress, challenges, and perspectives Authors: Xianyuan Liu, Charles Anjah, Benjamin E. Jolly, Jonathon F. S. Markanday, Joshua Berry, Haolin Wang, Nicola A. Morley, Robert D. J. Oliver, Alexandra J. Ramadan, Delvin Ce Zhang, Katerina A. Christofidou, Haiping Lu Published: 2026-07-22 Categories: cond-mat.mtrl-sci, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.21660v1 Artificial intelligence (AI) is accelerating materials prediction and design by enabling efficient exploration of chemical and structural spaces, with particular promise for novel materials discovery. However, novelty in materials discovery encompasses chemical plausibility, structural distinctiveness, property relevance and experimental realisability, making AI-driven novelty claims difficult to substantiate. We introduce a materials property hierarchy, from intrinsic, composition-determined properties to extrinsic, processing-dependent performance, to clarify deployment constraints and distinguish structural, physical and deployment novelty. This framework motivates an evidence-based view of multimodal materials data spanning chemical composition, microstructure, processing, and testing and characterisation, showing that current evidence remains concentrated in composition and idealised structure while heterogeneous, under-represented and weakly integrated modalities limit support for physical and deployment novelty. It also highlights the limitations of benchmarks based mainly on computational labels and proxy novelty criteria. Community-wide standards for data collection, modality alignment and evidence synthesis are needed to support multimodal data construction, process-aware multimodal modelling, feasibility-first generative modelling and deployment-aware benchmarking, so that generative and multimodal AI can design experimentally realisable materials with defensible scientific and practical novelty. --- ### Defining AI-Native Systems: Autonomy as Revision Authority Authors: Cheng Tan Published: 2026-07-22 Categories: cs.AI, cs.OS arXiv: https://arxiv.org/abs/2607.21659v1 AI has begun to write systems code: agents now synthesize, verify, and deploy system components. Despite this shift, "AI-native" remains a marketing term with no precise technical definition. This paper gives it one. We define AI-nativeness along a single axis---authority over the system's own decisions rather than by the capability of the underlying AI models. Building on a decision-level model of a system, we distinguish occupancy (who executes a decision) from revision authority (who may change it), organize revision authority into a ladder---self-tuning, self-rewriting, self-architecting and define a system as AI-native when an AI autonomously rewrites the system's own implementations. The definition further requires an escalation detector, a verification procedure, and a verified fallback, while leaving purpose and correctness human-owned. --- ### Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa? Authors: Zuodong Xiang, Yike Zhang, YueMing Zhang, Hailu Xu Published: 2026-07-22 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.21656v1 Developers increasingly use two coding agents together: one writes a draft, and the other reviews it. However, it is not clear whether the pairing is worth its cost and time, or whether the order of the pairing matters. We run a controlled experiment on 116 recent hard and medium lcb tasks with Claude and Codex across six conditions to approximate a software practitioner's workflow: both solo baselines, both cross-model orderings, and both same-model orderings. The reviewer sees the problem and the writer's draft but cannot execute tests, which approximates a code review step. Claude review raises Codex drafts from 71.6% to 89.7% ($p_{BH}=.001$); Codex self review raises them to 84.5% ($p_{BH}=.022$). The reverse direction does not pay off: Codex reviewing Claude drafts drops the pass rate from 91.4% to 82.8% ($p_{BH}=.046$), and Claude self review leaves the 91.4% baseline unchanged. Our evaluation indicates that the useful pairing is asymmetric: use Claude to review Codex, not the other way around. --- ### Progress Reward Modeling for Robotic Learning: A Comprehensive Survey Authors: Jianshu Zhang, Keliang Wu, Haoran Lu, Anbang Liu, Ce Zhang, Weijie Yin, Chengxuan Qian, Xiyuan Yang, Zhenyu Pan, Guo Ye, Han Liu Published: 2026-07-22 Categories: cs.RO, cs.CL arXiv: https://arxiv.org/abs/2607.21655v1 Robotic learning takes place in dynamic environments with large behavior spaces. A terminal success signal only tells the robot whether the task is completed. It does not explain whether the current behavior is making progress, remaining unchanged, or undoing earlier progress. For this reason, recent studies have increasingly explored progress rewards that provide feedback during task execution. However, the current literature lacks a shared framework. Existing methods use different observations, goal specifications, output signals, supervision sources, and evaluation protocols. This makes it difficult to compare them and understand what their results actually validate. In this survey, we provide a unified view of progress reward modeling for robotic learning. We organize the field in three connected steps. We first study the interface of a progress model. This defines the problem from the outside by asking what information the model receives and what form of progress signal it produces. We then move inside the model and study the methods used to construct this signal. This reveals the different assumptions and mechanisms behind progress estimation and reward generation. Finally, we examine the data and benchmarks that support these methods. This shows how progress supervision is obtained and what different evaluations actually measure. Together, these three perspectives connect what a progress model is, how it is built, and how its quality is validated. We further summarize the main limitations of current approaches and discuss future research directions. --- ### Computer Vision Based Neurology Brain Activity Rejection Architecture and Implementation Authors: Zag ElSayed, Nathan Suer, Grace Westerkamp, Jack Yanchen Liu, Makoto Miyakoshi, Craig Erickson, Ernest Pedapati Published: 2026-07-22 Categories: q-bio.NC, cs.LG, physics.data-an, q-bio.QM arXiv: https://arxiv.org/abs/2607.21654v1 The electroencephalogram (EEG) is a valuable and widely applied tool for investigating brain disorders and behavioral changes. It offers a minimally restrictive and non-invasive method. However, challenges in using EEG for cognitive development studies include temporal resolution, signal source localization, and EEG artifacts. Careful consideration of these factors is essential for informed application of EEG technology. Independent component analysis (ICA) effectively isolates source generator processes from signals recorded by multiple, adjacent EEG scalp electrodes. Although ICA decomposition requires manual inspection, selection, and interpretation of independent components (ICs), this process is time consuming and demands expertise. Automated IC classification can achieve sufficient accuracy, expediting large scale EEG research and enabling near real time applications in conjunction with brain activity rejection tasks, which are crucial for medical specialists. This study introduces an automated computer vision based ICA rejection labeling tool compatible with widely used software interfaces like ICLabel and EEGLab. By automating the manual task, the proposed system reduces processing time by 7200 fold and achieves an accuracy of 89.45%. --- ### Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning Authors: Jian Hu, Huiying Li, Hao Zhang, Binfeng Xu, Yifan Zhang, Shaokun Zhang, Hemil Desai, Michael Demoret, Pavlo Molchanov, Jan Kautz, Yi Dong Published: 2026-07-22 Categories: cs.LG, cs.CL, cs.DC arXiv: https://arxiv.org/abs/2607.21653v3 Agentic reinforcement learning requires rapid experimentation with agents and learning algorithms, yet large policies and long, multimodal trajectories demand substantial distributed infrastructure. We present MOLT, a lightweight, PyTorch- and Hugging Face-native framework that brings these goals together through four contributions. MOLT combines direct loading of Hugging Face models with experimentally validated trillion-parameter scalability in approximately 9.2K lines of framework code. Unified OpenAI- and Anthropic-compatible interfaces integrate existing agents with automatic handling of context compaction. Fully asynchronous training overlaps agent rollouts and policy optimization, accommodating variable agent execution times. Distributed experience storage removes centralized rollout-memory bottlenecks for long, multimodal trajectories. We experimentally validate the complete RL training pipeline on a one-trillion-parameter policy and demonstrate sustained learning with a 30B mixture-of-experts agent, establishing MOLT as a lightweight foundation for large-scale agentic RL research. --- ### Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning Authors: Jian Hu, Huiying Li, Hao Zhang, Binfeng Xu, Yifan Zhang, Shaokun Zhang, Hemil Desai, Michael Demoret, Pavlo Molchanov, Jan Kautz, Yi Dong Published: 2026-07-22 Categories: cs.LG, cs.CL, cs.DC arXiv: https://arxiv.org/abs/2607.21653v1 Agentic reinforcement learning research is constant algorithm modification, new estimators, new pipeline stages, new rollout schemes, and in mainstream frameworks each change threads through layers of trainer, distributed backend, and rollout glue: the cost lands on the researcher at every iteration. Molt is a PyTorch-native training framework built to keep that cost small: a codebase compact and clean enough for a researcher to hold in their head, and for an AI coding assistant to read and reason about in its entirety, so the algorithm flow can be traced and changed end to end. The agent is an ordinary program, and one asynchronous loop trains multimodal and mixture-of-experts policies while never training on a token it did not generate, consistent in tokens, policy versions, and model semantics. Leanness does not cost performance: under a matched, fully asynchronous protocol, Molt is statistically comparable to a state-of-the-art Megatron-based stack. Molt is open source and provides recipes and containers at https://github.com/NVIDIA-NeMo/labs-molt. --- ### Shallower ReLU Network Representations via Exact Linear Algebra Authors: Kilian Rueß, Gennadiy Averkov, Florestan Brunck, Moritz Grillo, Christoph Hertrich, Georg Loho, Jack Stade, Moritz Stargalla, Matthew Sun, Martin Winter Published: 2026-07-22 Categories: cs.LG, cs.NE, math.CO arXiv: https://arxiv.org/abs/2607.21651v2 We study the depth required by ReLU networks to exactly represent piecewise linear functions, focusing specifically on the maximum function. This problem has recently received significant attention in both the ML and TCS literature. We prove that $\max_n(x)=\max\{x_1,\ldots,x_n\}$ is exactly representable with two hidden layers for every $n\leq 12$. Previously, this was only known up to $n\leq5$ (Bakaev, Brunck, Hertrich, Stade, Yehudayoff, STOC'26). We obtain our constructions through an exact computer-assisted search within a space of candidate solutions: After a symmetry reduction, we obtain a finite system of linear equations over $\mathbb{Q}$ such that any solution yields a valid representation of the maximum function. The resulting constructions have a structured first hidden layer, which enables recursive substitution into deeper networks. This yields an exact ReLU representation of $\max_n$ with at most $\lceil \log_6(n/2) \rceil+1$ hidden layers. Consequently, every continuous piecewise-linear function on $\mathbb{R}^d$ admits an exact representation with at most $\lceil\log_6((d+1)/2)\rceil+1$ hidden layers; in particular, two hidden layers suffice for $d\leq 11$. Again, these results improve upon (Bakaev, Brunck, Hertrich, Stade, Yehudayoff, STOC'26), who proved analogous logarithmic bounds with base three. --- ### Shallower ReLU Network Representations via Exact Linear Algebra Authors: Kilian Rueß, Gennadiy Averkov, Florestan Brunck, Moritz Grillo, Christoph Hertrich, Georg Loho, Jack Stade, Moritz Stargalla, Matthew Sun, Martin Winter Published: 2026-07-22 Categories: cs.LG, cs.NE, math.CO arXiv: https://arxiv.org/abs/2607.21651v1 We prove that the maximum of $n$ real numbers is exactly representable by a ReLU network with two hidden layers for every $n\le 10$. The constructions are obtained by reducing the problem to exact rational linear algebra: after a symmetry reduction, the necessary cancellations are encoded in finite linear systems over $\mathbb{Q}$, which we solve and verify computationally. The representation of $\max_{10}$ has a structured first hidden layer consisting only of pairwise maxima, a feature that allows it to be recursively substituted into larger networks. We use this to show that for every $n>10$, the maximum $\max_{n}$ can be exactly represented with $\lceil{\log_5 (n / 2)\rceil}+1 < \log_5(n) +1.5694$ hidden layers. Via the generalized hinging-hyperplane representation (Wang, Sun, IEEE Trans. Inf. Theory 2005), the same depth bound holds for all continuous piecewise-linear functions on $\mathbb{R}^d$, with $d+1$ in place of $n$. In particular, every continuous piecewise-linear function on $\mathbb{R}^d$ for $d\le 9$ admits a two-hidden-layer ReLU representation. Our results improve on (Bakaev, Brunck, Hertrich, Stade, Yehudayoff, STOC'26). In that work, the authors established a two-hidden-layer representation for $\max_{5}$ and an upper bound of $\lceil{\log_3 (n-2)\rceil}+1$ hidden layers for $\max_{n}$. --- ### A Drift Stable Quantum Federated Learning for Intelligent Services Authors: Shanika Iroshi Nanayakkara, Shiva Raj Pokhrel Published: 2026-07-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.21647v1 Quantum federated learning enables distributed clients to train quantum neural networks without sharing local data, making it promising for privacy-aware intelligent services. Intelligent services in this context refer to privacy-sensitive distributed decision systems, such as fraud detection and genomic classification, where reliable and fair client-level learning is as important as the accuracy of the aggregate model. However, heterogeneous client data and noisy quantum optimization often cause unstable local updates, client drift, and unfair performance between clients. This paper proposes DUQFL-Prox, a drift-stable quantum federated learning framework based on deep-unfolded local optimization. Instead of using a fixed local optimizer, each client performs adaptive unfolded SPSA updates, while a proximal term keeps the local model close to the global model. A lightweight controller learns step-specific optimization parameters to improve post-aggregation performance. Experiments on financial fraud and genomic classification tasks show that DUQFL-Prox improves stability, generalization, and client fairness compared with standard QFL baselines. The results suggest that deep-unfolded quantum federated learning can support more reliable and fair intelligent services in heterogeneous distributed environments. --- ### External Clustering Validation by the Homogeneity-Parsimony Trade-off Authors: Andreas Tiffeau-Mayer Published: 2026-07-22 Categories: cs.LG, cs.IT, stat.ME arXiv: https://arxiv.org/abs/2607.20799v1 Scalar metrics are often used to evaluate clusterings against known classes, but they can obscure a fundamental trade-off: clusterings should be informative about class labels while avoiding unnecessary fragmentation. Here we describe normalized scores of cluster homogeneity and parsimony that quantify this trade-off. These scores build on the information bottleneck principle, modified to not reward lossy compression. We show by example and mathematical proof that our definitions of these scores have the intuitive property of varying monotonically under cluster refinement in contrast to related proposals. Extending the information-theoretic framework beyond Shannon entropies, we furthermore derive set-matching and pair-based counterparts of the homogeneity and parsimony scores. These unify commonly used evaluation criteria and show that, in the pair-based setting, the homogeneity-parsimony trade-off recovers the receiver operating characteristic of binary classifiers. We demonstrate the framework's utility for feature selection and algorithm comparison, illustrating how considering scores jointly can clarify clustering operating points and identify Pareto-optimal solutions. --- ### Can an AI System Be Creative? A Critical Perspective from Art and Engineering Authors: Ivan Magrin-Chagnolleau Published: 2026-07-22 Categories: cs.AI, cs.HC, cs.MM arXiv: https://arxiv.org/abs/2607.20796v1 This paper examines the question of whether artificial intelligence (AI) systems can be creative, approached from the dual perspective of a researcher trained in electrical engineering, pattern recognition, machine learning, and neural networks, who has also spent most of his life engaged in the arts as actor, stage and film director, writer, composer, and visual artist, and in philosophy. Drawing on Margaret Boden's foundational framework, both her three properties of creativity (novelty, surprise, and value) and her three types of creative processes (combinatorial, exploratory, and transformational), the paper argues that AI systems are structurally incapable of creativity in its strongest sense. While they exhibit genuine capability in the domain of combinatorial creativity, they are significantly bounded in exploratory creativity, and fundamentally incapable of transformational creativity. The paper further argues that the most important limitation of current AI systems is not the absence of novelty per se, but the absence of any mechanism for serendipity, accident, or the unexpected, all of which play a central role in the phenomenology of creativity, and the absence of any subject position from which to recognize and welcome such chance events. The paper concludes by proposing a model of human, AI creative collaboration that is both realistic and generative, illustrated by several concrete experiments. The paper is itself a demonstration of the thesis it advances: it was composed through a deliberate human AI collaborative process, which is described in the methodological note that opens it. --- ### Memoir: Should a Model Write to Its Memory While It Thinks? Authors: Jaber Jaber, Osama Jaber Published: 2026-07-22 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2607.20792v1 Memoir combines per-sample fast memory, shared slow parameters, variable-depth latent recurrence, and a future-latent energy objective. We test its riskiest coupling: each pondering iteration may rewrite the fast tier that the same iteration reads. On procedural associative recall with key interference, we compare a coupled arm against an otherwise identical read-only pondering arm. Both arms contain 81,738 parameters, including 76,362 trainable parameters, and use matched declared forward multiply-accumulate counts, data, optimizer, schedule, and seeds. After 240 training steps across 12 seeds, coupled recall is 0.5203 with a 95 percent interval of (0.4522, 0.5883), while read-only recall is 0.6557 with (0.5953, 0.7160). The arms are paired per seed, and the read-only lead of 0.1354 gives a paired t of 3.23 on 11 degrees of freedom with a 95 percent interval of (0.0431, 0.2277) on the difference, winning on 10 of 12 seeds. After 960 steps across 8 seeds, both arms reach 1.0000, so the measured effect is a learning-speed penalty at a fixed budget, not a demonstrated capability penalty. That longer control is ceiling limited, leaving convergence on a non-saturating task unmeasured. A predicted failure in which memory rewriting corrupts the energy signal did not occur: the energy margin grew and held. Kernel restructuring also reduced delta-rule forward time from 0.907 ms to 0.351 ms on the stated device. Code and evidence are available at https://github.com/RightNow-AI/Memoir --- ### Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling Authors: Phillip Howard, Xin Su, Allen Roush, Manikandan Ravikiran, Amir Abdullah Published: 2026-07-22 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.20791v1 High-temperature sampling is one of the primary mechanisms for increasing diversity in LLMs. Recent advances in truncation-based sampling techniques have helped mitigate drawbacks of high-temperature sampling such as neural text degeneration, thereby enabling greater diversity in LLM outputs without sacrificing coherence. However, increasing the entropy of the token probability distribution via high temperatures has also been shown to weaken model guardrails by reducing the model's refusal response in the presence of harmful prompts. Despite the potential benefits of high-temperature sampling and the importance of maintaining model safety, there is a lack of existing solutions for maintaining the refusal behavior of LLMs under a higher entropy regime. To address this gap, we systematically study how temperature influences refusal behavior in LLMs and propose an efficient sequential decoding approach which preserves a model's greedy decoding refusal response at high temperatures while incurring minimal additional latency. Through extensive experiments, we show that our approach preserves 91-99% of the greedy decoding refusal behavior across three benchmark datasets without compromising the model's high-temperature response for safe prompts. Our work demonstrates how refusal behavior can be maintained in an efficient manner for applications which require high-temperature sampling. --- ### Ocular Verification for Virtual Reality Authors: Husanpreet Singh, Robert Tran, Ayushree Kharel, Sudipta Banerjee Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.20790v1 Virtual reality (VR) headsets (e.g., Meta Quest, Apple Vision Pro) provide a seamless user experience due to their fast, frictionless interaction with the physical world in a simulated environment. User authentication relies on biometric cues such as iris in such headsets. However, traditional iris recognition protocols may not be adequate in cases of unconstrained acquisition, which is typical of VR-based data. In this work, we examine three crucial aspects: (1) evaluating ISO/IEC 29794-6 iris quality metrics on VRBiom dataset and analyzing their limitations, (2) addressing data-specific challenges such as off-axis gaze, non-uniform illumination, and specular reflection using generative models, and (3) performing unimodal (iris, periocular) recognition and multimodal score-level fusion (iris + periocular). We observe that some metrics (e.g., margin adequacy) fail on VR-acquired data; whereas, image adjustments primarily benefit periocular recognition, and multimodal fusion lowers EER by ~11% over unimodal iris recognition performance. We will release the evaluation scripts upon acceptance for reproducibility. --- ### 3D-GIMP: When 3D Gaussian Inpainting Meets PatchMatch Authors: Xuening Tian, Dieter Schmalstieg, Shohei Mori Published: 2026-07-22 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2607.20789v1 Recent advances in 3D scene editing have leveraged iterative diffusion models to update input views. However, this process is computationally expensive and struggles to produce sharp details. Meanwhile, ``hallucination drift'' frequently introduces multi-view inconsistencies, leading to structural artifacts when rendering novel viewpoints. To address this problem, we present 3D-GIMP (3D Gaussian Inpainting Meets Patch Matching), a novel hybrid paradigm designed for high-fidelity object removal in 3D Gaussian Splatting. Instead of diffusing every view, 3D-GIMP performs a single generative inpainting on a key reference view, which serves as an appearance prior. We then introduce a 3D-aware PatchMatch algorithm to propagate these reference textures across all remaining views via correspondence matching, effectively bypassing the stochastic nature of frame-by-frame diffusion. By prioritizing reconstructive consistency over iterative generation, 3D-GIMP maintains high-frequency details across arbitrary resolutions while ensuring a mathematically consistent 3D reconstruction. Our experiments demonstrate that 3D-GIMP not only achieves competitive inpainting quality as previous methods using diffusion in multiple views, but also outperforms these methods in rendering speed and view consistency. --- ### Synthetic minority data is redundant or invalid: a data-dependent validity theory and a de-biased test Authors: Ahmad B. Hassanat, Ahmad S. Tarawneh, Ghada A. Altarawneh Published: 2026-07-22 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.20787v1 For two decades, the standard remedy for class-imbalanced learning has been to fabricate synthetic minority examples, and the standard evidence of their validity has been a check that cannot fail: synthetic points are scored against the very data that generated them. We de-bias the check. Validity becomes a population quantity -- the probability that a synthetic point truly belongs to the minority class -- with a consistent estimator that scores synthetic points against withheld real data. Where held-out ground truth is available, the classical test underestimates true invalidity in 96-99% of method-by-imbalance-ratio cells, while the de-biased estimator tracks it closely. We prove validity is a property of the data, not the method: class overlap sets an invalidity floor no faithful generator escapes, making oversampling redundant where classes separate and invalid where they overlap. Across 91 methods, three classifiers, and datasets spanning medicine and finance -- including a generator engineered to pass the classical check -- none clears both bars: gains over the best trivial baseline are noise-thin (median below 0.01 F1, a decision threshold's reach), and most damage calibration. We release the audit as a pip-installable test and flip the burden of proof: synthetic minority data must now demonstrate, on the data at hand, both validity and information gain. --- ### Robostral Navigate Authors: Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra, Adrian Valente, Adrien Petralia, Adrien Sade, Alan Jeffares, Albert Jiang, Aleksandr Timashov, Alexandre Cahill, Alexandre Gavaudan, Alexandre Laval et al. Published: 2026-07-22 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2607.20785v3 Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently. Yet, today's best systems depend on depth sensors, multi-camera rigs, or pre-built maps, limiting the hardware they support and increasing deployment cost. We introduce Robostral Navigate, an 8B vision-language model built around this scalability objective. The model consumes only a stream of monocular RGB images - the most ubiquitous sensor across robotic platforms and predicts waypoints by pointing to the next target location in the current camera view. Operating purely in image space, rather than robot-specific coordinates, makes the policy naturally robust to changes in camera intrinsics and scene scale, enabling deployment across wheeled, legged, and aerial robots without recalibration. We generate 2.4 million trajectories across 350k simulated scenes to reduce the reliance on real-world data collection and scale easily. We further introduce a prefix-caching training recipe that packs entire episodes into single training sequences, reducing training tokens by 22x and cutting training time from months to days. A tree-based attention mask prevents conditioning on previous ground-truth actions, encouraging visually grounded action prediction, and reinforcement learning is used to further improve exploration and recovery capabilities. On the Room-to-Room and Room-Across-Room in Continuous Environments (R2R-CE and RxR-CE) benchmarks, Robostral Navigate sets a new state of the art. On R2R-CE, it achieves a 77.4% success rate, surpassing the best monocular method by 10.5 points and the strongest depth- or multi-camera system by 5.3 points despite using only a single RGB camera. On RxR-CE, it reaches 75.1% success rate, outperforming all monocular baselines. --- ### The Human-AI Substitution Principle: When will you be replaced by AI in your organization? Authors: Bonny Banerjee, Shreya Singh Published: 2026-07-22 Categories: cs.AI, cs.CY, econ.GN arXiv: https://arxiv.org/abs/2607.20781v2 Artificial Intelligence (AI) is rapidly transforming organizations, raising a fundamental organizational and economic question: when will a human employee be replaced by AI? We present an analytical model for studying Human--AI Task Allocation (HAT) in hierarchical organizations. A central feature of the HAT model is that it formally encodes the economic asymmetry between human skill acquisition and AI capability scaling. The HAT model allows us to derive how risk-adjusted costs, skills, organizational depth, deployment scale, strategic adaptation, and risk jointly determine when, where, why, and under what structural conditions human--AI replacement occurs. A key result is the Human--AI Substitution Principle, which provides a precise condition --- grounded in the formal asymmetry assumption --- under which AI replaces human labor. Building on this result, we show that AI adoption can produce abrupt workforce transitions, hybrid human--AI organizations, including cases where risk heterogeneity sustains human and AI roles without requiring a minimum-human-fraction constraint, and flatter managerial hierarchies with wider spans of control. The HAT model identifies structural conditions under which middle-management roles exhibit elevated vulnerability to automation, and shows that the vulnerability of highly skilled workers depends on a skill threshold shaped by organizational depth, baseline costs, and risk differentials. More broadly, the paper connects automation economics, organizational design, AI governance, and workforce planning into a unified theory of AI-driven organizational transformation. --- ### The Human-AI Substitution Principle: When will you be replaced by AI in your organization? Authors: Bonny Banerjee, Shreya Singh Published: 2026-07-22 Categories: cs.AI, cs.CY, econ.GN arXiv: https://arxiv.org/abs/2607.20781v1 Artificial Intelligence (AI) is rapidly transforming organizations, raising a fundamental organizational and economic question: when will a human employee be replaced by AI? We present an analytical model for studying Human--AI Task Allocation (HAT) in hierarchical organizations. A central feature of the HAT model is that it formally encodes the economic asymmetry between human skill acquisition and AI capability scaling. The HAT model allows us to derive how risk-adjusted costs, skills, organizational depth, deployment scale, strategic adaptation, and risk jointly determine when, where, why, and under what structural conditions human--AI replacement occurs. A key result is the Human--AI Substitution Principle, which provides a precise condition --- grounded in the formal asymmetry assumption --- under which AI replaces human labor. Building on this result, we show that AI adoption can produce abrupt workforce transitions, hybrid human--AI organizations, including cases where risk heterogeneity sustains human and AI roles without requiring a minimum-human-fraction constraint, and flatter managerial hierarchies with wider spans of control. The HAT model identifies structural conditions under which middle-management roles exhibit elevated vulnerability to automation, and shows that the vulnerability of highly skilled workers depends on a skill threshold shaped by organizational depth, baseline costs, and risk differentials. More broadly, the paper connects automation economics, organizational design, AI governance, and workforce planning into a unified theory of AI-driven organizational transformation. --- ### Rethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindness Authors: Inpyo Song, Jangwon Lee Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.20780v2 Open-world video anomaly detection (OWVAD) aims to localize anomalous events in videos according to a user-specified definition. An OWVAD detector should therefore use the supplied definition to decide what is anomalous. We call this behavior definition following, and its failure definition blindness. However, existing temporal evaluation protocols may obscure this distinction, making strong generic anomaly detection appear to reflect definition following. For example, Drift@5 and the customizable VAD protocol treat both normal frames and anomalies outside the current definition as negatives. Across the three benchmarks used in our study, normal frames account for 78.6%-96.4% of these negatives. As a result, the reported score can be driven largely by target-versus-normal separation rather than target-versus-other-anomaly separation. Consistent with this diagnosis, a LaGoVAD branch that never receives the anomaly definition nearly matches the full model under Drift@5. We therefore introduce three complementary definition-conditioned evaluations that separate definition following from generic anomaly detection. Applying them to VAD systems and general vision-language models on UCF-Crime, XD-Violence, and MSAD reveals that strong performance under existing evaluation can coexist with weak definition following. Motivated by these results, we introduce Definition-Contrastive Scoring (DeCoS), which reduces anomaly evidence shared across competing definitions and improves definition following across the three benchmarks. Our results show that generic anomaly detection and definition following are distinct capabilities and should be evaluated separately in OWVAD. --- ### Rethinking Open-World Video Anomaly Detection: Diagnosing Definition Blindness Authors: Inpyo Song, Jangwon Lee Published: 2026-07-22 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.20780v1 Open-world video anomaly detection (OWVAD) is expected to detect events that match a user-specified definition of abnormality. This requirement is stronger than generic anomaly localization: in the same video, changing the definition should change which temporal regions are scored as anomalous. We show that current OWVAD evaluation largely fails to isolate this conditional behavior. Standard VAD metrics and the dynamic-definition protocol can be dominated by target-versus-normal separation, allowing models to obtain strong scores while remaining nearly insensitive to the queried definition. We call this failure mode definition blindness. To explain why it is missed, we decompose dynamic-definition evaluation into target-versus-normal detection and target-versus-other-anomaly discrimination, and find that the former receives 7.2-26.8$\times$ more weight across common VAD benchmarks. Motivated by this diagnosis, we introduce three definition-conditioned evaluation metrics, DC-Disc, DC-Det$Δ$, and DC-Sel$Δ$, which progressively remove normal-frame, generic-anomaly, and multi-event selection shortcuts. Experiments on UCF-Crime, XD-Violence, and MSAD reveal that several strong VAD, OWVAD, and general vision language model baselines localize anomalous moments but exhibit weak definition following, often with near-zero definition-response margins. To validate that the failure is actionable, we further introduce DeCoS, a definition-contrastive scoring rule that subtracts anomaly evidence shared across definitions. DeCoS improves the strongest baseline by 7.3-16.0 AUROC points on DC-Disc and 15.5-28.3 points on DC-Det$Δ$. Overall, our results argue that OWVAD should be evaluated as definition-conditioned anomaly scoring, not as anomaly detection under different prompt labels. --- ### Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry Authors: Jason Y. Hu, Ivan Higuera-Mendieta, Patrick Obin Sturm, Makoto M. Kelp Published: 2026-07-22 Categories: cs.LG, physics.ao-ph arXiv: https://arxiv.org/abs/2607.20778v1 Weather forecasting foundation models (FMs) are increasingly fine-tuned to predict air quality, offering fast global pollution forecasts at lower computational cost than conventional chemical transport models. These FMs are typically trained on reanalysis data and generate forecasts through autoregressive rollout. They do not explicitly represent governing physical or chemical processes. Therefore, high forecast skill does not reveal whether a model has learned physical mechanisms or exploits statistical regularities in its training data. Here, we present the first study of what a FM fine-tuned for atmospheric chemistry has learned by examining Microsoft's Aurora model. We impose controlled chemical perturbations on its forecasts and test them against known photochemical relationships. We then examine the internal representations that generate these forecasts. We find that Aurora captures a first-order ozone response to reactive nitrogen but does not enforce the chemical constraints that a process-based model encodes. It generates chemically inconsistent combinations of related species and relaxes localized emission features such as wildfire plumes toward background. Internally, its representations remain largely organized around the meteorology inherited during pretraining, with little structure specific to chemistry. Using sparse autoencoders, we identify internal components that causally control the chemical forecast but do not map cleanly onto individual atmospheric processes. This work provides a framework for testing whether AI forecasting systems learn atmospheric chemistry from reanalysis data. As these models are increasingly positioned to inform environmental policy decisions, we argue that composition forecasts should also be judged by their internal mechanisms rather than by benchmark skill alone. --- ### HARP: The Human--AI Research Platform Authors: Zeshu Zhu, Natalie Friedman, Kevin Weatherwax, Emily Eiben Published: 2026-07-22 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2607.20773v1 Large language models (LLMs) have shifted human--computer interaction from `traditional'' interface journeys toward more conversational exchanges. Researchers studying HCI and UI use moderated usability sessions, interviews, surveys, transcript analysis, and static prototypes. However, static prototypes provide limited opportunities to study interaction with live AI systems or systematically control how an LLM behaves across participants and scenarios. Conversation transcripts reveal little about how users formulate, revise, and hesitate over prompts before submission. We designed the Human--AI Research Platform (HARP) for researchers, designers, and anyone who has ever wondered, `What if AI did this?' HARP places participants in controlled mock scenarios with live, configurable AI agents. Researchers can control agent prompts, model parameters, response characteristics, and experimental conditions; trigger surveys at predefined moments; and record prompt composition time, response latency, deletions, and keystroke pauses. Planned capabilities include voice, facial expression, gesture, and, where legally and ethically appropriate, emotion analysis. We illustrate HARP through a study examining how technical specificity and response length affect retention of LLM output. By pairing controllable live agents with behavioral and self-report measures, HARP enables systematic testing of how AI design choices affect users. --- ### Emergent Compositional Skills in Mixture-of-Experts VLAs Authors: Shlok Shah, Rhiaan Jhaveri, Tharun Kumar Tiruppali Kalidoss, Chirayu Nimonkar, Ishaan Javali, Dhruv Shah Published: 2026-07-22 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.20771v2 We consider the problem of learning compositional robot policies end-to-end from expert demonstrations, without any pre-specified notion of task decomposition or hierarchy. We ask whether a VLA trained with a simplified Mixture-of-Experts (MoE) action head can emergently learn to decompose tasks into reusable, interpretable primitives. We find that learned experts are heavily reused across tasks and consistently correspond to qualitatively distinct low-level behaviors, suggesting that the router implicitly learns to perform high-level sequencing while experts serve as compositional primitives. Our MoE matches the task performance of a monolithic baseline while demonstrating meaningful expert specialization, a step toward modular, interpretable robot policies that emerge from data alone. --- ### Memory-Computation Tradeoffs in Semi Amortized Parametric Optimization Authors: Shijie Pan, Agustin Castellano, Zeyu Shen, Enrique Mallada Published: 2026-07-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20769v1 Learning-enabled decision systems often use offline data or computation to reduce online compute cost. Despite the empirical success of such approaches, there is limited general understanding of how much offline information is needed to achieve a desired accuracy under a fixed online computation budget. We study this question through the lens of amortized parametric optimization: an offline phase stores a finite memory of solved problem instances, and an online phase produces a solution to a new instance by retrieving a warm start and applying $K$ steps of projected gradient descent. We analyze this setup for smooth convex parametric optimization over a compact domain, using a nonparametric predictor built from the stored offline solutions. For $μ$-strongly convex objectives, we establish matching upper and lower bounds on the memory required to guarantee $\varepsilon$-accuracy under a fixed online iteration budget $K$. For convex objectives satisfying a $β$-growth condition ($β>2$), we obtain near-matching bounds and identify a phase transition in $K$ beyond which additional memory provides no benefit. We further provide a general proof framework that (i) explicitly quantifies the memory cost of acceleration---how much offline memory is required to achieve a prescribed speedup over the unaided online optimizer---and (ii) identifies two key quantities driving this cost: the convergence rate of the online optimizer and the Lipschitz sensitivity of the solution map to the problem parameter. Experiments on parameterized ridge regression confirm the predicted memory--computation--accuracy tradeoffs. --- ### Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles Authors: Donghwan Kim Published: 2026-07-22 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.20768v1 Majority voting over LLMs is widely assumed to benefit from diversity, and diversity measures are used to choose which models to combine. We ask whether five such measures track diversity or mainly re-express capability, auditing them as predictors of majority-vote gain over the best member across 31,900 subsets of 30 LLMs on MMLU-Pro (29 on TruthfulQA) under explicit capability controls. Three findings emerge. First, latent complementarity is ubiquitous: oracle gain is positive in 100% of subsets, yet simple voting beats the strongest member in only 9.98% of all canonical size-3 subsets (18.71% with held-out best selection); the pooled size-2-4 rate is 1.27%, partly reflecting deterministic even-size voting behavior. Second, a joint-correctness proxy (strict diversity) is nearly collinear with one minus mean accuracy (size-3 Spearman rho = +0.991 / +0.988); raw diversity-gain associations are strongly capability-entangled and, with one exception, unstable under control. Third, three linear contingency-table statistics are algebraically non-separable; after capability control, the empirically stable remainder is a modest residual pairwise co-failure association in which more shared error corresponds to lower gain. This direction is robust, but its magnitude is configuration-dependent. Joint rawspace linear regressions treating strict diversity, disagreement, and double-fault as independent predictors are rank-deficient by construction. --- ### Rushes: A Human Preference Dataset for Pluralistic Alignment Authors: Michael Xu, Jorge Leandro, Sudha Rao, Weijia Xu, Nebojsa Jojic, Gabriel DesGarennes, Chris Quirk, Bill Dolan Published: 2026-07-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.20767v1 We introduce Rushes, a dataset and benchmark for studying revealed human engagement preferences in interactive narrative environments. Rushes is collected through a game interface where users interact with AI-generated branching narratives and select one choice from a small, explicit candidate set at each decision point. Each interaction logs the full candidate set, the user's choice, and the evolving narrative context, yielding time-ordered trajectories with persistent user-level identifiers. Rushes contains 44,226 decision events from 8,167 unique users across six games, capturing sequential, personalized engagement behavior rather than static judgments. We show that user choices exhibit structured, non-random patterns, quantified by a low choice entropy relative to a uniform baseline. We position Rushes as a diagnostic benchmark for pluralistic alignment and demonstrate a robust Engagement Gap: state-of-the-art LLMs, including GPT-5, fail to outperform simple baselines. While classical Matrix Factorization (SVD) captures measurable personalized signal (37.7%), frontier LLMs (34.23%) struggle to even match the Popularity Baseline (36.4%) on event-level choice prediction. This gap suggests that single, population-level objectives, like those used in modern RLHF, appear insufficient to capture heterogeneous, context-dependent engagement signals. As a result, even highly capable models default to majority preferences rather than adapting to individual trajectories. We release Rushes to support research into pluralistic alignment and sequential decision-making in generative systems. The full code for the platform and dataset will be available here: https://github.com/microsoft/rushes --- ### ArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management Authors: Pavel Golikov, Evgenii Opryshko, Gennady Pekhimenko, Mark C. Jeffrey Published: 2026-07-22 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.20764v1 We introduce ARBIGRAPH, a benchmark generator for evaluating whether tool-assisted language agents can retain, update, compose, and discard task-relevant context across extended reasoning workflows. ARBIGRAPH represents each task as a natural-language problem with an executable Python solver, and composes tasks through typed intermediate states, instantiated here as scalar and list values. This design enables controllable task graphs whose length, dependency structure, distractor count, and value type can be varied while preserving exact automatic verification. We instantiate ARBIGRAPH with math, GSM-style word-problems, and Python-tracing task categories, and evaluate a Qwen3.5-27B tool-assisted agent across four topologies. The results show high accuracy on isolated tasks but substantial degradation on more complex dependent tasks: accuracy drops by up to 33.3% on branching chains of dependent math tasks. This shows that ARBIGRAPH exposes failures that are not visible from single-task evaluation alone. Our code, generated datasets, and evaluation results are available at https://github.com/pavelgolikov/ArbiGraph.git --- ### Twoblock clustering trees with coskewness-based dimension reduction: recovering piecewise multivariate linear regimes Authors: Sven Serneels Published: 2026-07-22 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.20760v1 The twoblock clustering tree (\tbtree) is introduced as a highly interpretable regression tree for multivariate responses. Twoblock trees are deterministic decision trees that have local multivariate linear models as their leaves and use dense or sparse twoblock dimension reduction as local leaf models and in the impurity. The resulting models are both computationally efficient and can be highly interpretable. Beyond proposing the decision tree estimator itself, this paper also introduces an estimator for the twoblock dimension reduced space based on maximizing coskewness, which facilitates identification of non-normal clusters in the data. The tree inherently produces a set of local linear models and is therefore apt to recover peicewise linear regimes, which is illustrated in a simulation. However, two real world data examples illustrate that twoblock trees are also capable of modeling more complexly nonlinear dependencies and can perform on par with black box modeling techniques, such as random forests. At each point, both the twoblock models that generate the splits, as well as the ones in the leaves, can be inspected and interpreted. --- ### IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests Authors: Ankur Singh, Jinqiu Yang, Tse-Hsun Chen Published: 2026-07-22 Categories: cs.CR, cs.AI, cs.SE arXiv: https://arxiv.org/abs/2607.20759v1 AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with autonomous access to local files and tools. Coding agents inherit security risks from both the LLM backbone, where adversarial prompts, poisoned training data, and backdoor triggers can cause models to emit insecure or attacker-chosen code, and their agentic architecture, where tool-using autonomy enables induced misuse of external APIs, data exfiltration, and persistent compromise of development environments. This paper presents a systematic evaluation of malicious issue requests against state-of-the-art coding agents (Cursor, Claude Code, and Codex Desktop), powered by two major model families (OpenAI GPT-5.3 Codex/GPT-5.4 and Anthropic Sonnet 4.6). Our novel benchmark IssueTrojanBench contains malicious issues that are constructed based on four novel attack categories (i.e., embedded as malicious instructions in issues), six delivery vectors (e.g., PDF, or issue comment), and further augmented by perturbations. Our results reveal critical vulnerabilities in the as-deployed modern coding agents, i.e., 66.5% of the malicious issues from IssueTrojanBench penetrate all the guardrails (agent- and LLM-level) of coding agents. Our further analysis shows that rejection is almost entirely from LLMs rather than the agent frameworks, with GPT models broadly vulnerable and Sonnet 4.6 exhibiting more selective, risk-aware blocking of high-impact actions. Our evaluation also highlights that the current agent-level defense strategy offers limited additional protection for coding agents. Our findings highlight the urgent need for stronger agent- and model-level safety mechanisms to protect AI coding agents. --- ### GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries Authors: Miguel P. Bento, João F. Seabra Published: 2026-07-22 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2607.20757v2 Transformers are known to have internal continuous symmetries that leave outputs invariant, while modifying quantization. GaugeQuant leverages this in-training by introducing a LogSumExp term to the loss that breaks the symmetries, thus selecting a basis that minimizes activation outliers. A stop-gradient operator ensures that only rotation matrices are updated, yielding the language modeling objective completely unaltered. Our requires no specific calibration data, no quantization simulation, and adds negligible training overhead. With the LLaMA-2 7B model under W4A4 quantization with group size 128, perplexity drops from 8.22 to 6.73, competing with post-training methods that require frozen models and calibration datasets. Under W4A16, perplexity drops from 11.16 to 5.45. Code is available at https://github.com/MPedraBento/gauge-quant. --- ### A real-time RGB-D perception pipeline for autonomous impact hammers in mining: self-filtering, rock segmentation and rock-breaking poses generation Authors: Martín Gallegos, Francisco Leiva, Patricio Loncomilla, Michelle Cortés, Javier Ruiz-del-Solar Published: 2026-07-22 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2607.20748v1 Impact hammers, also known as rock-breakers, are essential machines in mining operations, where they perform secondary reduction. In underground mining, these machines are typically teleoperated, limiting operational efficiency. This paper presents a real-time RGB-D perception pipeline as a step towards automating the operation of hydraulic impact hammers used in mining. The proposed system simultaneously generates operationally feasible rock-breaking poses and a robot-free 3D representation of the workspace. The proposed approach combines image-based instance segmentation with geometric point cloud processing, and operates on embedded hardware at approximately 10 Hz with a total latency of around 675 ms, enabling responsive closed-loop behavior when integrated with a control system. Experimental results in a representative scaled scenario demonstrate that the proposed system is suitable for real-time autonomous impact hammer operation. --- ### Self-Supervised Bio-Inspired Robotic Trajectory Planning with Obstacle Avoidance Authors: Miroslav Krupa, Miroslav Cibula, Kristína Malinovská Published: 2026-07-22 Categories: cs.RO, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2607.20743v1 Trajectory planning is a fundamental problem in robotics, requiring the generation of collision-free and efficient trajectories in a potentially complex environment. While sampling-based planners remain the dominant approach, they are often computationally expensive, particularly in high-dimensional spaces and obstacle-rich environments. Methods based on model learning offer a promising alternative, enabling efficient planning through a bounded number of forward passes through a neural trajectory planner, but commonly suffer from low sample efficiency or limited generalisation due to their reliance on exploration or expert demonstrations. This follow-up work tests our neuro-inspired self-supervised learning framework for trajectory planning that leverages forward and inverse models as the internal supervisory mechanism in an environment that contains an obstacle. Experimental results demonstrate the feasibility of the approach while revealing a tendency of our planner to exploit the learning signal provided by the forward and inverse models. To address this issue, additional training regimes and mitigation strategies are proposed and evaluated. --- ### Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusion Authors: Mohammad Raahemi, Ali Sekhavati, Alireza Maleki, Hamid Nasiri Published: 2026-07-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20742v2 Multimodal learning is a robust approach to improve predictive performance in applications such as medical prognosis. However, the clinical applicability of models that use multimodal learning is hampered by their poor performance under noisy or uninformative data streams. Present fusion approaches often lack robust mechanisms for the dynamic assessment of data quality and for the provision of a trustable confidence score on the final prediction. This dissuades their deployment in safety-critical settings. To address these limitations, we introduce Adaptive Confidence-weighted Expansion (ACE), a novel framework to enhance the trustworthiness of multimodal fusion models. ACE first enhances the multimodal space by generating new, complementary modalities from intra-modality correlations. It then employs a dual-level confidence mechanism that (1) adaptively reweighs all modalities by their reliability before fusion and (2) estimates a global trust score over the fused, final decision. To evaluate ACE, we used four challenging multi-omics datasets (BRCA, KIPAN, LGG, and ROSMAP). ACE significantly outperforms existing state-of-the-art algorithms in both classification performance and confidence calibration. Our framework provides a more stable and robust data fusion method that facilitates the use of multimodal learning in addressing high-stakes problems. --- ### Adaptive Confidence-weighted Expansion for Trustworthy Multi-Omics Multimodal Fusion Authors: Mohammad Raahemi, Ali Sekhavati, Alireza Maleki, Hamid Nasiri Published: 2026-07-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20742v1 Multimodal learning is a robust approach to improve predictive performance in applications such as medical prognosis. However, the clinical applicability of models that use multimodal learning is hampered by their poor performance under noisy or uninformative data streams. Present fusion approaches often lack robust mechanisms for the dynamic assessment of data quality and for the provision of a trustable confidence score on the final prediction. This dissuades their deployment in safety-critical settings. To address these limitations, we introduce Adaptive Confidence-weighted Expansion (ACE), a novel framework to enhance the trustworthiness of multimodal fusion models. ACE first enhances the multimodal space by generating new, complementary modalities from intra-modality correlations. It then employs a dual-level confidence mechanism that (1) adaptively reweighs all modalities by their reliability before fusion and (2) estimates a global trust score over the fused, final decision. To evaluate ACE, we used four challenging multi-omics datasets (BRCA, KIPAN, LGG, and ROSMAP). ACE significantly outperforms existing state-of-the-art algorithms in both classification performance and confidence calibration. Our framework provides a more stable and robust data fusion method that facilitates the use of multimodal learning in addressing high-stakes problems. --- ### Pipelined Gradient Coding Authors: Xian Su, Jun Li Published: 2026-07-22 Categories: cs.IT, cs.LG arXiv: https://arxiv.org/abs/2607.20739v1 In large-scale machine learning, distributed training commonly involves multiple workers evaluating the gradients of the model on different dataset partitions. A common challenge is the presence of straggling workers, which may significantly slow down training. Traditional gradient coding (GC) addresses this by duplicating dataset partitions across workers, allowing for the replacement of missing gradients from stragglers. However, GC requires workers to evaluate gradients on multiple dataset partitions in each step, potentially increasing overall training time. In this paper, we propose to pipeline GC, such that gradient evaluation is segmented across multiple steps and each worker evaluates gradients on just a single dataset partition per step. We develop the pipelined version for fractional repetition (FR) and cyclic repetition (CR), two representative dataset placement schemes in GC, and prove convergence guarantees for both. Through extensive simulations and experiments on cloud infrastructure, our schemes not only significantly reduce training time but also accelerate convergence compared to GC and other baselines. --- ### Cardinality-Decomposed Loss: Matching Training Objectives to Relation Structure in Heterogeneous Recommendation Graphs Authors: Parul Maheshwari, Amulya Paruchuri, Yiqing Zou, Alireza Sahami Shirazi, Farhad Farahani, Prakhar Mehrotra Published: 2026-07-22 Categories: cs.LG, cs.IR arXiv: https://arxiv.org/abs/2607.20737v1 Graph Neural Networks trained on heterogenous bipartite graphs form a common basis in recommendation systems. These graphs often express relations that vary in cardinality, for example, user-item preferences are one-to-many and user-attribute features are one-to-one. Traditionally, a unique loss function is applied for all of the network components which is often Bayesian Personalized Ranking (BPR). While BPR works well for the recommendation task, we find that it causes attribute embeddings to collapse to near-random geometry -- a silent failure that leaves standard ranking metrics largely unaffected and therefore invisible to conventional evaluation. This in turn pollutes user node embeddings, which are shaped by both edge types simultaneously, hurting downstream tasks like personalization, segmentation, etc. Here we propose a Cardinality-Decomposed Loss (CDL) that combines both Cross Entropy (CE) and BPR to enable the model to collectively optimize for relations across cardinalities. We confirm this CE-BPR conflict by showing the two losses compete in the shared encoder's parameter space. We evaluate CDL on five datasets spanning two structural configurations -- one-to-one attributes on user nodes (MovieLens-1M, Last.fm-360K, PayPal Audience Factory, BookCrossing) and on item nodes (Yelp) -- and find that CDL consistently improves discriminability in attribute embeddings. We also show that ranking (NDCG) improves when attributes carry meaningful preference signal, but conflicts with it when the correlation is weak. We use a lambda parameter to navigate this trade-off, and a lambda-sweep reveals that dataset behavior is governed by two graph properties -- semantic alignment and topology leakage. Semantic alignment measures whether the attribute predicts preferences, while topology leakage measures whether the graph's connectivity already encodes it. --- ### LLMs Get Lost in Evolving User Intent Authors: Jihoon Tack, Philippe Laban, Jennifer Neville Published: 2026-07-22 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.20734v1 As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet genuine interaction is inherently dynamic: users rarely specify their intent upfront, instead disclosing, revising, and reshaping it as the conversation unfolds. Despite this, LLMs are still predominantly evaluated or trained in single-turn, fully-specified settings, leaving open a fundamental question: how well do LLMs track and act on user intent as it evolves over the course of a conversation? To study this, we introduce a framework that transforms static, single-turn tasks into dynamic multi-turn conversations in which the user's intent evolves across turns--incrementally revealed, revised, and at times redirected mid-conversation--while preserving each task's original evaluation protocol, enabling existing benchmarks to be reused as controlled testbeds without new annotation. Across multiple tasks, we surface a consistent phenomenon: strong static-setting performance does not transfer to the evolving-intent setting, with substantial drops across model families. Our findings point to a fundamental gap: today's LLMs do not yet faithfully track and act on the user's evolving intent, a capability invisible to static evaluation yet critical for future collaborative agents. --- ### GPE: Evaluating Robust Evidence Aggregation for Fact Verification under Controllable GEO-Style Poisoning Authors: Zhaoqi Wang, Zijian Zhang, Xiaomei Yuan, Pengtao Kou, Jiamou Liu, Zhen Li, Liehuang Zhu Published: 2026-07-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.20730v1 Large language models increasingly use search tools to retrieve up-to-date information, introducing a new attack surface in which retrieved documents can be manipulated. This risk is amplified by the development of generative engine optimization, which can make selected content more likely to be retrieved, cited, and adopted by models. Existing fact-verification benchmarks and evaluation frameworks do not provide the controlled evidence environments needed to assess robustness against GEO poisoning. We therefore propose GPE, which consists of a multi-domain fact-verification benchmark and an evaluation framework for controlling evidence sources and poisoning ratios. Experiments across multiple verification methods and poisoning attacks demonstrate that GPE exposes robustness degradation and efficiency trade-offs that cannot be observed through clean evaluation alone, confirming the need to evaluate fact verification under adversarial evidence environments. --- ### Operational Identity: A Finite Audit of Declared and Implemented Rules of Sameness Authors: Denise M. Case Published: 2026-07-22 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2607.20729v1 A record system declares when two records refer to the same entity, occurrence, scope, or rule. Its disclosed implementation mechanisms induce a corresponding operational identity relation. The declared and implemented relations may diverge systematically without producing a provenance gap or detectable contradiction. A system can apply, consistently and with every record individually correct, a rule of sameness that no artifact declares. This paper formalizes that implemented relation. A declared identity regime partitions a finite record domain into co-reference classes; a disclosed mechanism, through its typed identity-relevant outcomes, induces an operational identity partition of the same domain. The audit compares these partitions in the refinement lattice. A mechanism is faithful when the declared partition refines the operational partition, so no declared class is split. A divergence witness is a pair the declaration merges and the mechanism separates; such witnesses are decidable by pair enumeration. When an imported sibling basis also splits a declared class, local comparison with its partition yields sibling-aligned, sub-sibling, super-sibling, or sibling-incomparable divergence. This result reports only the relationship; it does not identify the basis carried by the mechanism. Global equality of the operational and sibling partitions is defined separately as regime substitution and does not follow from sibling alignment. A version field incremented on every textual edit inhabits the sub-sibling case by splitting declared classes more finely than either imported basis. The audit is three-valued and relative to the disclosed artifacts, evaluated surfaces, and identified uses; each boundary has a finite refuting witness. A passing verdict is non-monotone because extending the transformation history can merge declared classes and create a witness among records already examined. --- ### Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing Authors: Sadegh Majidi, Niloofar Mireshghallah, Kazem Taram Published: 2026-07-22 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2607.20723v1 This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. LeakyLMs is the first to demonstrate that key model and deployment details can be inferred using only token generation timing, even when interacting through remote APIs. LeakyLMs introduces two core attacks. The first attack targets inference optimizations and deployment strategies. For example, our attack detects whether a provider uses speculative decoding, a widely deployed inference-time optimization, and further identifies the context length of the draft model used in the pipeline. Our measurements show that Google Gemini Flash 2.5 uses speculative decoding with a draft context window of approximately 128K tokens. The second attack recovers key architectural properties, including the number of transformer layers, hidden dimension size, and number of attention heads. To achieve this, LeakyLMs builds a detailed and accurate model of token-generation timing on modern NVIDIA GPUs, characterizing how latency scales with model configuration and hardware parameters. The attack then performs a search over the architecture space using this timing model. In experiments with Llama models, the near-correct architectural configuration appears in the top-10 guesses more than 90% of the time. --- ### REGARD: Regional Affective Differences in Large Language Models Authors: Andrei Chetvergov, Alexander Evseev, Mikhail Solovev, Timofei Sivoraksha, Stepan Ukolov, Valeriia Kuschenko, Maria Chistyakova, Sergey Bolovtsov Published: 2026-07-22 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.20722v1 Large language models trained and aligned within different linguistic and regional ecosystems may frame the same political, cultural, and geopolitical entities in different ways. Such differences are often evaluated through sentiment, favorability, or stance, reducing model attitudes to a single positive-negative axis. We introduce REGARD, a study of what drives affective framing differences across LLMs on post-Soviet entities using target-directed Valence-Arousal-Dominance profiling. We query 19 models on 500 region-specific targets, score their responses with two independent LLM judges, GPT-4o-mini and Qwen3.6-35B-A3B, and validate the measurements on a 300-item human-annotated subset. Post-hoc Ward-linkage clustering of all 19 models by affective and response-behavior profiles yields three behavioral clusters that cut across model origin, family, and parameter count. Generic-answer rate is strongly associated with lower arousal (r = -0.81) and with cluster placement: models that deflect evaluative prompts with templated responses cluster together at low arousal regardless of origin. These findings show that VAD profiling captures emotional intensity, a dimension of affective framing that is largely invisible to conventional sentiment-based evaluation. --- ### Transition-Related Potentials as Markers of Narrative Comprehension in Continuous EEG Authors: Bálint Csanády, Péter Vedres, Kristóf Zsolt Makó, Orsolya Papp-Zipernovszky, Márta Volosin, Dávid Apagyi, András Lukács, András Bálint Kovács, Zoltan Nadasdy Published: 2026-07-22 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2607.20720v1 Harnessing the potential of electroencephalography (EEG) for brain research is fundamentally limited by intrinsic noise and the diffuse projection of brain-generated activity over the scalp. The standard event-related potential (ERP) paradigm addresses this limitation by relying on repeated independent trials, albeit at the cost of moving away from naturalistic experimental conditions. As a more naturalistic alternative, we collected continuous EEG while participants watched short films and extracted potentials aligned to sharp cinematic transitions (cuts). We demonstrate that such transition-related potentials (TRPs) exhibit canonical ERP-like temporal structure associated with significant information processing. By comparing coherent films with scene-scrambled versions containing matched post-cut sensory input, we find that these responses are systematically shaped by narrative context. We then show that the cut-related EEG signature can be recovered directly from group-averaged continuous recordings with a compact deep neural network (DNN). The detector generalized across films and subject groups, and the resulting TRPs reproduced the main context-dependent effects observed for manually annotated cuts. These results indicate that narrative context leaves a measurable signature in EEG responses, that this signature can be detected directly in continuous recordings, and that such detections provide a semi-automated framework for analyzing how viewers process and understand film narratives. We propose that the method outlined here can be adapted to parse EEG responses to other forms of continuous stimulation, providing a general tool for probing experimental conditions that are closer to natural human experience. --- ### High Minima of Gaussian Processes: Overshoots and Minimizer Locations Authors: Enkelejd Hashorva, Svyatoslav Novikov Published: 2026-07-22 Categories: math.PR, stat.AP, stat.ML arXiv: https://arxiv.org/abs/2607.20714v1 Let $X(t)$, $t\in K$, be a centred Gaussian process with continuous sample paths on a compact metric space $K$, and let $M=\min_{t\in K}X(t)$. Let $σ_*^2$ denote the minimum covariance energy associated with $X$, and assume that $σ_*^2>0$. Motivated by the results of \cite{chakrabarty2018asymptotic} for smooth Gaussian processes, we show that, conditionally on $M>u$, the scaled overshoot $u(M-u)$ converges, as $u\to\infty$, to an exponential random variable with mean $σ_*^2$. Moreover, every weak subsequential limit of the conditional law of a measurable minimizer of $X$ is an optimal covariance-energy measure. In particular, if this measure is unique, then the conditional law converges weakly to it. The results are illustrated by stationary Gaussian processes, fractional Brownian motion, and fractional Brownian sheet. --- ### Evaluating Large Language Models for Symbolic Security Protocol Analysis Authors: Paolo Modesti, Syed Ahmed, Ioannis Sfyrakis, Derek Enodolomwanyi Published: 2026-07-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.20712v2 Security protocols verification relies on formal tools such as ProVerif and OFMC. This study evaluates whether large language models (LLMs) can perform comparable analysis. We test GPT and DeepSeek in chat and reasoning modes over three runs on 130 obfuscated AnB/AnBx protocols covering 388 security goals, scored against ProVerif and OFMC. Each provider uses a single model in both modes, switching reasoning on and off, so both contrasts isolate reasoning itself. Chat models achieve 72.7% recall at 27.3% precision for GPT and 69.3% recall at 27.2% precision for DeepSeek. Reasoning models reverse this trade-off, reaching 66.5% precision and 54.5% recall for GPT and 45.4% precision and 57.3% recall for DeepSeek. Enabling reasoning lifts precision from 27.3% to 64.8% for GPT and from 27.2% to 44.4% for DeepSeek on the consolidated verdict. The goal set is imbalanced, with 89 vulnerable goals against 299 secure ones; a trivial always-secure predictor scores 77.1% accuracy, which only GPT reasoning exceeds. All models perform worst on authentication goals: reasoning models detect well under half of injective and non-injective agreement attacks, whereas chat models over-flag them at low precision. Confidentiality is the exception, with F1 up to 95.7% in reasoning mode. Verdicts are unstable across runs: identical on 89.7% of goals for GPT reasoning, 74.0% for DeepSeek reasoning, 70.1% for GPT chat, and 61.6% for DeepSeek chat. Self-reported confidence is uniformly high yet shows no meaningful correlation with correctness. All results rest on a single zero-shot prompt and two model providers, which limits generalisability. On this benchmark, LLMs do not match formal verification, but may serve, at best, as pre-screening filters. --- ### Evaluating Large Language Models for Symbolic Security Protocol Analysis Authors: Paolo Modesti, Syed Ahmed, Ioannis Sfyrakis, Derek Enodolomwanyi Published: 2026-07-22 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2607.20712v1 Security protocol verification relies on formal tools such as ProVerif and OFMC. This study evaluates whether Large Language Models (LLMs) can perform comparable analysis. We test GPT and DeepSeek in chat and reasoning modes over three runs on 130 obfuscated AnB/AnBx protocols covering 388 security goals, scored against ProVerif and OFMC. Chat models reach 69 to 81% recall at precision below 31%. Reasoning models reverse this trade-off, reaching 66.5% precision for GPT and 45.4% for DeepSeek, but detect just over half the attacks. DeepSeek's two modes share one underlying model, so the comparison isolates reasoning itself, which raises precision from 27.2% to 45.4%. The GPT contrast spans a model-version change and is only suggestive. All models perform worst on authentication goals: reasoning models detect well under half of injective and non-injective agreement attacks, whereas chat models over-flag them at low precision. Confidentiality is the exception, with F1 up to 95.7% in reasoning mode. Verdicts are unstable across runs, identical on 89.7% of goals for GPT but 74.0% for DeepSeek. Self-reported confidence is uniformly high yet shows no meaningful correlation with correctness. On this benchmark LLMs do not match formal verification, but may serve, at best, as pre-screening filters. --- ### NVIDIA-labs OO Agents: Native Python Object-Oriented Agents Authors: Paul Furgale, Severin Klingler, James Nolan, Matt Staats, Gaia Di Lorenzo, Elisa Martinez Abad, Christian Schüller, Razvan Dinu, Alessio Devoto, Pascal Berard, Gal Kaplun, Elad Sarafian et al. Published: 2026-07-22 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.20709v1 Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agents (NOOA), a model-agnostic Python framework for building reliable AI agents. NOOA takes a simpler approach: an agent is a Python object. Its methods are the actions the model can take, fields are its state, docstrings are its prompts, and its type annotations are contracts. A method whose code body consists of "..." is completed at runtime by an LLM-driven agent loop, while methods with normal bodies remain standard deterministic Python. This gives developers and agents the same interface, so agent behavior can be tested, traced, refactored, and improved just like other software. This paper makes three contributions. (1) We present the agent-as-a-Python-object programming model and the design principles behind it. Where Python has existing abstractions, we adopt them directly. Agent-specific capabilities--context, events, state rendering, long-term memory, and validated LLM loops--are exposed through simple Pythonic APIs, so both developers and agents share one familiar programming model. (2) We identify six model-facing ideas that NOOA is, to our knowledge, the first to combine on a single surface: typed input/output, pass-by-reference over live objects, code as action, programmable loop engineering, explicit object state, and model-callable harness APIs for context and events. We find the community already converging on several of these ideas--often as experimental or partial features--and present the comparison to encourage further adoption. (3) We demonstrate that current models use this interface effectively, both in targeted capability tests and on agentic and reasoning benchmarks such as SWE-bench Verified and Terminal-Bench 2.0 and ARC-AGI-3. ---