# Research Papers — 2026-07 · bundle page 100 of 222 > Full-text markdown of papers #4951–5000 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/100 [← Previous bundle](https://aipod.dev/papers/archive/2026-07/page/99.md) [Next bundle →](https://aipod.dev/papers/archive/2026-07/page/101.md) ### Tractable Query Answering under Epistemic Confidentiality Policies in DL Ontologies (extended version) Authors: Lorenzo Marconi, Daniela Rieti, Riccardo Rosati Published: 2026-07-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.16715v2 We study Controlled Query Evaluation (CQE), a declarative approach to confidentiality-preserving data access, in the context of Description Logic (DL) ontologies, and for confidentiality policies expressed through Epistemic Dependencies (EDs). We first address the problem of answering queries (specifically, Boolean unions of conjunctive queries) under known semantics for CQE (GA- and IGA-entailment). Our results show that if the TBox is expressed in $\text{DL-Lite}_{\mathcal{R}}$, CQE is computationally intractable in general. Moreover, in the presence of EDs, the IGA semantics has recently been proven not to satisfy an important confidentiality preservation property known as indistinguishability. With the goal of defining computationally easier and confidentiality-preserving forms of CQE, we introduce a new semantics for CQE, based on the notion of minimal policy violation (MPV). We show that the new semantics provides a sound approximation of the previous ones, while satisfying the indistinguishability property. We also prove that, in the case of $\text{DL-Lite}_{\mathcal{R}}$ ontologies, query entailment under the MPV semantics can be decided in polynomial time in data complexity. Finally, we present a software implementation of our framework that we used to evaluate the feasibility of this new approach using an existing benchmark for OWL 2 QL. --- ### DS@GT ARC at eRisk 2026: Hybrid Multi-Agent LLM System with Structured Algorithmic Guidance for Conversational Depression Screening Authors: Victor Gong, David Guecha Published: 2026-07-18 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2607.16712v1 We describe DS@GT's submission to the eRisk 2026 Task 1 challenge on conversational depression screening, in which systems interview LLM personas that simulate individuals with varying depression profiles and produce a Beck Depression Inventory II (BDI-II) score plus four key symptoms per persona, without directly asking sensitive mental health questions. Our pipeline evolved through three stages: a monolithic single-model prototype to start off, a baseline multi-agent architecture that separates conversational interviewing from BDI-II scoring under a coordinating orchestration layer, and a final hybrid configuration that replaces the paid GPT-5-nano interviewer with the open-source Gemma 27B. To offset the model's weaker reasoning and instruction-following, the hybrid adds three algorithmic components: a precomputed dialogue tree that standardizes interview openers and follow-ups, a reliability-weighted consensus aggregation inspired by the Weaver framework, and a cluster-based imputation step for unprobed symptoms. We submitted three fully automated runs across all 20 personas, with Run 1 from the paid baseline and Runs 2 and 3 from the hybrid. Hybrid Run 3 achieved an ADODL of 0.9063, ranking 3rd among all complete-submission runs and placing DS@GT 2nd among the 21 teams overall, while outperforming our paid baseline Run 1 (0.8841) at roughly one-quarter of the per-persona API cost. These results support our central hypothesis that with sufficient algorithmic supervision, a weaker open-source model can compete with a stronger proprietary model in the conversational interviewer role. Our source code is available at https://github.com/dsgt-arc/erisk-task1-2026. --- ### OFD-Net: Teacher-Free Reliable Semi-supervised Medical Image Segmentation with Orthogonal Feature Disentanglement Net of Foreground-Background Authors: Shao-feng Jiang, Zhe-yang Jing, Qin Lu, Huan-huan Shi, Zhen Chen, Cong-xuan zhang, Chen Yi Published: 2026-07-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.16705v1 Semi-supervised learning (SSL) is an effective solution for medical image segmentation with limited annotations. Existing SSL methods mainly rely on pseudo-labels generated by teacher-student supervision or cross-network consistency. However, these methods lack an explicit structural reference for judging pseudo-label quality. Low-quality pseudo-labels may lead to unreliable training, error accumulation and confirmation bias when processing unlabeled data with substantial appearance variations. To address this issue, we proposed OFD-Net, a teacher-free single-network framework for reliable semi-supervised medical image segmentation. OFD-Net employs an Orthogonal Feature Disentanglement Module (OFDM) to capture OFD features for reliable SSL by disentangling unlabeled data into background and foreground representations with a reliable structural distribution, thereby effectively reducing error accumulation and alleviating confirmation bias among unlabeled data. Specifically, OFD-Net explicitly employs a Disentanglement Guidance Module (DGM) to inject the resulting structural priors of foreground-background into the decoder by deformable convolution processing, and outputs predictions with clearer foreground representations. Based on DGM and the OFDM, we further develop a reliability-aware pseudo-label learning mechanism that evaluates unlabeled supervision according to the structural consistency between the main prediction and the disentangled foreground-background responses, and then down-weights unreliable regions during training. Extensive experiments on four public medical image segmentation benchmarks, namely ISIC-2016, Kvasir-SEG, Synapse, and ACDC, validate the effectiveness of OFD-Net. These results confirm that orthogonal foreground-background disentanglement enables OFD-Net to establish an efficient and reliable training paradigm within a teacher-free single-network framework. --- ### Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation Authors: Mingqiao Mo, Yunlong Tan, Hao Zhang Published: 2026-07-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.16704v1 Large language models frequently violate fundamental scientific principles when generating technical content, undermining their reliability in scientific applications. We introduce Scientific Feasibility Control SFC, a graph-structured conformal prediction framework that provides statistical guarantees for scientific reasoning validity through progressive absolute-coherent-factuality validation. Our approach decomposes scientific reasoning into atomic absolute-coherent-factuality units requiring both individual correctness against physical laws and logical substantiation from preceding context, addressing the cascade effect where early scientific errors contaminate subsequent reasoning steps. Unlike independence-based methods that treat claims in isolation, SFC models logical dependencies as approximate deducibility graphs and operates through real-time validation with dynamic branching when scientific violations are detected, the system branches to alternative generation paths using verified context as foundation. We demonstrate SFC across established scientific reasoning benchmarks including PhyX multimodal physics, MATH, ScienceQA, and ARC Challenge, achieving 50.1 percent accuracy on PhyX physics reasoning, substantially outperforming recent reasoning models including DeepSeek-R1 49.8 percent and GPT-4 45.8 percent while providing 91.7 percent scientific validity with formal conformal coverage guarantees at alpha equals 0.10 confidence level and reducing scientific law violations by 73 percent across multiple model architectures. --- ### Are Arithmetic Heuristic Neurons Form-Invariant? A Mechanistic Analysis of Symbols, Text, and Code in LLMs Authors: Sharath Naganna, Tanvir Ahmed Sijan, Uddipta Kalita Published: 2026-07-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.16693v1 Large language models often succeed on one formulation of a problem while failing on an equivalent formulation. Whether these failures arise from distinct internal circuits or different activation states of a shared circuit remains unknown. Recent mechanistic interpretability studies suggest that arithmetic in LLMs emerges from a "bag of heuristics," encoded by a sparse set of MLP neurons that represent distinct arithmetic strategies. We investigate whether arithmetic heuristic neurons are form-invariant across symbolic arithmetic, natural language word problems, and Python code in three Llama-3 models. In each format, we identify arithmetic heuristic neurons using a two-stage pipeline combining attribution patching and activation patching. A compact set of neurons is shared across all three formats, and targeted interventions show this shared circuit is both necessary and sufficient for late-layer arithmetic computation. Transferring the shared neurons' activations from a successful execution in one format to a failed execution in another recovers most incorrect predictions, exceeding 97% for addition and subtraction, indicating that cross-format failures arise from activation states rather than distinct circuits. Moreover, shared neurons consistently belong to the same heuristic families across formats, demonstrating that arithmetic computation in LLMs is largely form-invariant at the neuron level. --- ### Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement Authors: Mingqiao Mo, Yangchen Zeng, Zikai Xiao, Xin Xiao, Wenhua Nie, Zhaolu Kang, Guangyuan Dong, Kai Shu, Hao Zhang, Xiaodong Fan Published: 2026-07-18 Categories: cs.SE, cs.CL arXiv: https://arxiv.org/abs/2607.16692v2 The increasing complexity of modern software systems has made automated code generation a fundamental task in software engineering. However, existing approaches often fail to adequately capture the intricate, multi-level dependencies among code entities, leading to generated code that is logically incomplete or difficult to integrate into real-world systems. To address this limitation, we propose a dependency-aware code generation framework that explicitly models interactions among code entities through a graph-based representation. We decompose dependencies into two complementary components: a quantized matrix that captures strong, explicit relations, and a sparse low-rank factorization that models weaker, implicit interactions. The decomposition is efficiently learned via an alternating optimization procedure. During code generation, the learned dependency structure is incorporated as a constraint, ensuring both semantic coherence and structural consistency of the generated code. Furthermore, we introduce a sparse triplet representation for strong dependencies, significantly improving storage efficiency and computational scalability. Extensive experiments demonstrate that our approach consistently produces code with superior semantic alignment and structural fidelity compared to existing methods. --- ### Semi-Supervised Conditional Diffusion via Label Augmentation Authors: Jin Su, Yuan Gao, Yong Zhou, Jian Huang Published: 2026-07-18 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.16685v1 Conditional diffusion models have become a powerful and flexible framework for learning complex conditional distributions from labeled data. In practice, however, acquiring high-quality labels is costly and time-consuming, leaving large volumes of unlabeled data unused. To address this, we introduce label-augmented conditional diffusion (LACD), a simple and effective approach that incorporates unlabeled examples by assigning them a designated trivial label and performing joint denoising score matching over the augmented dataset. We provide sufficient conditions guaranteeing population-level identifiability of the target conditional distribution under this scheme. Moreover, we establish rigorous statistical guarantees: when sufficiently many unlabeled samples are available, the sampling distribution produced by LACD converges strictly faster than the purely supervised estimator in total variation distance, and at least as fast in Wasserstein-1 distance. Extensive experiments on synthetic, image, and tabular benchmarks corroborate our theory and show substantial gains in sample efficiency and generative performance compared with the purely supervised estimator. --- ### Building a Neural Network from Scratch: Implementation, Evaluation, and Optimization Authors: Yuanzhe Jia Published: 2026-07-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.16682v2 The widespread adoption of high-level deep learning libraries, while accelerating model development, has increasingly abstracted away the internal mechanics of neural networks, creating a gap between practical usage and fundamental understanding. To address this, the paper presents a self-contained neural network framework implemented entirely from scratch without relying on automatic differentiation or pre-built deep learning modules. The implementation encompasses all essential components, including multi-layer architectures, diverse activation functions, regularization techniques, and state-of-the-art optimizers. Beyond serving as a pedagogical instrument that demystifies forward/backward propagation, gradient dynamics, and optimization landscapes, the framework demonstrates robust performance when applied to a multi-class classification task, successfully validating its correctness, numerical stability, and generalization across varied configurations. The extensible design and clean modularity further position it as a reliable baseline for educational purposes and future research exploration. --- ### Building a Neural Network from Scratch: Implementation, Evaluation, and Optimization Authors: Yuanzhe Jia Published: 2026-07-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.16682v1 The widespread adoption of high-level deep learning libraries, while accelerating model development, has increasingly abstracted away the internal mechanics of neural networks, creating a gap between practical usage and fundamental understanding. To address this, the paper presents a self-contained neural network framework implemented entirely from scratch -- without relying on automatic differentiation or pre-built deep learning modules. The implementation encompasses all essential components, including multi-layer architectures, diverse activation functions, regularization techniques, and state-of-the-art optimizers. Beyond serving as a pedagogical instrument that demystifies forward/backward propagation, gradient dynamics, and optimization landscapes, the framework demonstrates robust performance when applied to a multi-class classification task, successfully validating its correctness, numerical stability, and generalization across varied configurations. The extensible design and clean modularity further position it as a reliable baseline for educational purposes and future research exploration. --- ### A Framework for Early Sepsis Prediction via Self-Supervised (JEPA) and Federated Representation Learning Authors: Umair bin Mansoor, Munaf Rashid, Roomi Naqvi Published: 2026-07-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.16681v1 Early sepsis prediction from electronic health records is challenged by irregular sampling, high missingness, and class imbalance. We systematically compare four modeling paradigms -- self-supervised Joint Embedding Predictive Architecture (JEPA) via masked latent prediction, self-supervised VICReg (variance-invariance-covariance regularization) with two-view augmentation, semi-supervised fine-tuning of a VICReg-pretrained encoder, and supervised Temporal Convolutional Network (TCN) -- alongside raw-feature baselines. All models share a common preprocessing pipeline of hourly binning with forward-fill imputation applied to 7 biomarkers selected via sparsity analysis from the MIMIC-III dataset. Our best model (JEPA + XGBoost + mean pooling) achieves AUPRC 0.636 at the time of onset (H0), approaching the SupMix benchmark (0.667) while using 83\% fewer biomarkers. The Tier 1 pipeline -- VICReg pretraining followed by semi-supervised fine-tuning and XGBoost -- achieves AUPRC 0.510 at H0, a 3.1$\times$ improvement over the raw-feature baseline (0.165) and a 7.6\% improvement over the end-to-end supervised TCN (0.474). Crucially, the fine-tuned VICReg encoder exhibits the most temporally persistent representations, degrading only 16.8\% from H0 to H10 compared to 47.5\% for supervised TCN and 65.3\% for JEPA, demonstrating that self-supervised pretraining with task-aware fine-tuning yields features that are both sharp near onset and robust across prediction horizons. --- ### The Value of Depth in Message Passing on Sparse Graphs: A Kesten-Stigum Dichotomy Authors: Aseem Raj Baranwal Published: 2026-07-18 Categories: math.ST, cs.LG, math.PR, stat.ML arXiv: https://arxiv.org/abs/2607.16676v2 How deep does a graph neural network need to be on a sparse graph? We study its purest statistical form: node classification on the sparse contextual stochastic block model (CSBM) with average degree $Δ=O(1)$, whose local weak limit is a broadcast-labelled Poisson Galton-Watson tree. Prior work derived a message-passing classifier $h_\ell$ that aggregates from each vertex at distance $k\le\ell$ the attenuated evidence $2\operatorname{artanh}(γ^k t(X_v))$, with $γ$ the edge signal and $t$ a bounded likelihood-ratio transform of the feature. We prove that the value of depth is governed by a single number, the Kesten-Stigum ratio $κ=γ^2Δ$. Below the threshold ($κ<1$), the error sequence is Cauchy at a geometric rate, $|\mathcal{E}(\ell)-\mathcal{E}(\ell')|\le Cκ^{(\ell+1)/3}$ for all $\ell'>\ell$, so all layers beyond depth $O(\log(1/ε))$ change the error by less than $ε$; conversely, under mild regularity each sufficiently deep layer still flips the decision with probability at least $cκ^{\ell/2}$, the empirically sharp exponent. Above the threshold ($κ>1$), depth is geometrically productive: $\mathcal{E}(\ell)$ is driven to a branching-process floor of order at most $1/(κ-1)$ at any geometric rate $κ^{-s\ell}$, $s<1$ (this bound has content only for $κ>17$). No local classifier of any depth beats the universal floor $e^{-Δ}Φ(-ζ)$ set by isolated roots ($ζ$ the feature signal-to-noise ratio), while the first layer provably helps by an explicit total-variation amount. Simulations with an exact belief-propagation baseline on the same trees show that the pairwise rule's error curve is mildly non-monotone in $\ell$, so an optimal finite depth exists (an exact instance is certified in the appendix), while BP saturates strictly faster, at an effective per-layer ratio below $κ$ that we identify. --- ### The Value of Depth in Message Passing on Sparse Graphs: A Kesten-Stigum Dichotomy Authors: Aseem Raj Baranwal Published: 2026-07-18 Categories: math.ST, cs.LG, math.PR, stat.ML arXiv: https://arxiv.org/abs/2607.16676v1 How deep does a graph neural network need to be on a sparse graph? We study its purest statistical form: node classification on the sparse contextual stochastic block model (CSBM) with average degree $Δ=O(1)$, whose local weak limit is a broadcast-labelled Poisson Galton-Watson tree. Prior work derived a message-passing classifier $h_\ell$ that aggregates from each vertex at distance $k\le\ell$ the attenuated evidence $2\operatorname{artanh}(γ^k t(X_v))$, with $γ$ the edge signal and $t$ a bounded likelihood-ratio transform of the feature. We prove that the value of depth is governed by a single number, the Kesten-Stigum ratio $κ=γ^2Δ$. Below the threshold ($κ<1$), the error sequence is Cauchy at a geometric rate, $|\mathcal{E}(\ell)-\mathcal{E}(\ell')|\le Cκ^{(\ell+1)/3}$ for all $\ell'>\ell$, so all layers beyond depth $O(\log(1/ε))$ change the error by less than $ε$; conversely, under mild regularity each sufficiently deep layer still flips the decision with probability at least $cκ^{\ell/2}$, the empirically sharp exponent. Above the threshold ($κ>1$), depth is geometrically productive: $\mathcal{E}(\ell)$ is driven to a branching-process floor of order at most $1/(κ-1)$ at any geometric rate $κ^{-s\ell}$, $s<1$ (this bound has content only for $κ>17$). No local classifier of any depth beats the universal floor $e^{-Δ}Φ(-ζ)$ set by isolated roots ($ζ$ the feature signal-to-noise ratio), while the first layer provably helps by an explicit total-variation amount. Simulations with an exact belief-propagation baseline on the same trees show that the pairwise rule's error curve is mildly non-monotone in $\ell$, so an optimal finite depth exists (an exact instance is certified in the appendix), while BP saturates strictly faster, at an effective per-layer ratio below $κ$ that we identify. --- ### Isotonic Conformal Prediction Authors: Daniel Bensimon, Sean Xiang Yu, Eric D. Kolaczyk, Archer Y. Yang Published: 2026-07-18 Categories: stat.ML, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2607.16675v1 A point prediction that is well calibrated on average can still be systematically biased conditional on its own value, undermining its use in downstream decision-making. We consider two objectives for reliable uncertainty quantification: self-calibration, requiring a point prediction to be unbiased conditional on its own value, and prediction-conditional validity, requiring a prediction interval to attain nominal coverage conditional on the prediction. Self-Calibrating Conformal Prediction (SC-CP) attains both objectives exactly in finite samples, but requires refitting its calibrator for every candidate outcome, which is computationally prohibitive for continuous outcomes. We propose Isotonic Conformal Prediction (ICP), a framework that decouples calibration from prediction-set construction by fitting a single isotonic recalibration map and constructing prediction intervals within strata of similar recalibrated predictions. Within this framework we develop two procedures. Split Isotonic Conformal Prediction (SICP) attains prediction-conditional validity in finite samples and self-calibration asymptotically, at the computational cost of split conformal prediction. Transductive Isotonic Conformal Prediction (TICP) attains both objectives exactly in finite samples through a per-test-point inner loop that avoids refitting the isotonic calibrator. On synthetic heteroscedastic regression problems and a real-world healthcare-utilization dataset, both procedures match the coverage of SC-CP at substantially lower computational cost. --- ### CLDRoute: Conditional Latent Diffusion for Routability Map Generation in Physical Design Authors: Kiran Thorat, Nicole Meng, Caiwen Ding, Yingjie Lao, Zhijie Jerry Shi Published: 2026-07-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.16674v1 Accurate routability estimation during physical design is important for reducing costly post-routing iterations. Prior learning-based methods treat this task as deterministic prediction, mapping placement-stage features to a single congestion or DRC outcome. We instead formulate routability estimation as a conditional generation problem, where both routing congestion and DRC violations are modeled as spatially structured routability fields. Our framework, Conditional Latent Diffusion for Routeability estimation (CLDRoute), uses physics-aware conditioning and task-specific latent modeling to handle the different characteristics of congestion and DRC maps. This allows our method to supports sample-based inference, producing both a mean prediction and a spatial uncertainty estimate for the same input design. On CircuitNet 2.0 (N28), our method achieves, for DRC violation generation, an SSIM of 0.9678, an MAE of 0.0028, and a TopK@1% of 0.3494; for congestion generation, it achieves an SSIM of 0.9031, an MAE of 0.0286, and an NZ-Pearson of 0.3692. Overall, our framework provides a more practical view of routability at placement by generating both the expected outcome and its uncertainty. --- ### SpecLA: Efficient Speculative Decoding for Linear-Attention Models Authors: Zhibin Wang, Xuying Han, Zhaohua Yang, Fuliang Liu, Xue Li, Rong Gu, Sheng Zhong, Chen Tian Published: 2026-07-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.16673v1 Linear-attention models replace the growing KV cache with recurrent states, but autoregressive decoding still reads, updates, and writes these states one token at a time. Speculative decoding can reduce this cost by verifying several draft tokens in one target pass, yet existing speculative systems are designed for Transformer KV caches. For stateful linear-attention targets, verification must follow recurrent dependencies across chains and branches, acceptance must update only the accepted state trajectory, and the drafter must avoid submitting candidates that waste stateful verification work. This paper presents SpecLA, a speculative decoding runtime for stateful linear-attention models. SpecLA verifies chains and trees with topology-aware kernels, stores compact factors produced during verification to recover accepted states, and uses confidence pruning plus a target-aligned EAGLE-style drafter to feed useful candidates to the verifier. On an NVIDIA H100 with a public GDN-1.3B target, SpecLA achieves up to 1.70x end-to-end speedup over autoregressive decoding. --- ### Foundation-Assisted Active Learning for Object Detection Annotation Authors: Jinchang Zhang, Arnold Zumbrun, Jing Lin, Guoyu Lu Published: 2026-07-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16671v1 The annotation cost for remote sensing object detection is high, while existing active learning methods still face several challenges in object detection scenarios, including the coupling of localization and classification uncertainty, severe localization noise in the cold-start stage, and pseudo-diversity caused by high-recall candidate proposals. To address these issues, we propose a foundation-model-collaborative active learning and semi-automatic annotation framework for efficient construction of remote sensing object detection datasets. We build a dual-source mechanism consisting of a reference localization source (SA-source) based on UPN+SAM2 and a detector prediction source (OD-source), and further propose a Foundation-model-enhanced Dual-Source Uncertainty estimation to improve sample selection quality in the cold-start stage by jointly modeling localization consistency and classification confidence. Furthermore, we propose Object-Centric Diversity Sampling, which constructs object-level representations using DINOv2 features and SAM2 masks to improve sample coverage while suppressing pseudo-diversity. To address geometric noise in the semi-automatic annotation stage, we design Dual-Source Box Switching, which replaces noisy detector boxes with matched refined boxes from the SA-source, thereby reducing the manual burden of box refinement. Experiments on DIOR, HRSC2016, DOTAv2, and FAIR1M show that our method achieves superior or comparable results under most annotation budgets, with notably stronger cold-start sample efficiency in the low-budget regime. --- ### OpenLanguageModel: Readable and Composable Small-Language-Model Pretraining for Education and Research Authors: Tavish Mankash, Vardhaman Kalloli, Keshava Prasad, Deepan Muthirayan Published: 2026-07-18 Categories: cs.CL, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2607.16669v1 OpenLanguageModel (OLM) is an open-source PyTorch library for building and pretraining small language models while keeping their machinery visible. In OLM, model code reads like the architecture: components are ordinary modules, while Block, Residual, Repeat, and Parallel describe how they are wired. The resulting model can move unchanged from a teaching notebook to a complete pretraining run or a research ablation. OLM connects this readable model layer to tokenizers, local and streaming datasets, optimization, mixed precision, callbacks, checkpoints, and hardware-aware CPU, single-GPU, and single-node multi-GPU execution. We demonstrate the full path by tracing GPT-2 from diagram to code, launching a FineWeb-Edu training script, replacing one attention component, and letting AutoTrainer configure the available machine. The package includes 27 presets across nine familiar model families and documentation that progresses from LM fundamentals to architecture research. Validation shows close agreement with independent reference implementations, 90.6% four-GPU weak-scaling efficiency for a 348M-parameter workload, compact architecture edits, and positive early usability results. OLM is MIT-licensed and available through PyPI, GitHub, and its documentation site. --- ### Amortized Inference for Sampling Distributions Where the Bootstrap Fails Authors: Akash Deep Published: 2026-07-18 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2607.16666v1 Efron's bootstrap is the default tool for estimating the sampling distribution of a statistic, yet it is provably inconsistent for maxima of bounded-support distributions, means under infinite variance, extreme quantiles, and tail-index estimators. The classical remedies, the m-out-of-n bootstrap and subsampling, require rate corrections that depend on unknown parameters and behave erratically at realistic sample sizes. We propose an amortized alternative: a neural network is trained on simulated datasets drawn from a prior over a distribution family, using single independent draws of the root T_n - T(F) scored by the pinball loss, a proper scoring rule whose population minimizer is the posterior-predictive law of the root. At test time, a single forward pass maps one dataset of n = 200 observations to its full sampling-distribution estimate, from which confidence intervals follow directly. On four canonical bootstrap-failure problems (bounded-support maximum, alpha-stable mean, Pareto tail index, and 99% value-at-risk under tempered stable returns), the method attains nominal 95% coverage, beats every feasible classical method in Wasserstein distance to the true sampling distribution, and captures over 97% of the achievable improvement where the exact Bayes-optimal answer is computable. For the value-at-risk problem no distribution-free method can reach nominal coverage at all; the learned method attains 94.7%. A single universal network with a statistic token matches all four specialists, and on real daily market returns the unchanged model averages 0.87 coverage against 0.73 for the bootstrap, as predicted by our out-of-family analysis. --- ### Multimodal Attention-based Deep Learning for Emergency Triage with Electronic Health Records Authors: Hazqeel Afyq Athaillah Kamarul Aryffin, Kamarul Aryffin Baharuddin, Mohd Halim Mohd Noor Published: 2026-07-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2607.16662v1 Accurate emergency triage decision is critical to avoid clinical deterioration, morbidity, and mortality. Machine learning-based triage system involves acquiring the main presenting complaint in text form and assessing vital signs in numerical data, enabling an automated and efficient analysis of patient information for timely and accurate prioritization of medical attention. However, modelling the intricacies of both data types requires a comprehensive understanding of the temporal structure and dependencies within the data. Thus, the aim of this study is to propose a multimodal deep learning architecture that can effectively handle both tabular and textual data. Furthermore, the proposed model exploits self-attention to to capture both local and global relationships between the features. A dataset consisting of 11,102 triage data collected from emergency department of Hospital Universiti Sains Malaysia is used for model development and validation. The proposed model demonstrated an increase of 1.95% in accuracy, 2.49% in F1-score, and 1.41% in ROC AUC compared to the baseline model. The experimental results demonstrated the potential of the proposed model in predicting triage decisions. --- ### From Adoption to Deployment: A Qualitative Study on AI Integration in Software Development Practice Authors: Mahzabin Tamanna, Elizabeth Lin, Sparsha Gowda, Laurie Williams, Dominik Wermke Published: 2026-07-18 Categories: cs.SE, cs.AI, cs.CR, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.16660v2 The increasing adoption of Large Language Models (LLMs) as AI components in modern software systems introduces distinct security risks to the software supply chain. While many considerations and safety mechanisms are in place for components of the traditional software supply chain, the recent rapid adoption of AI components and platforms has overlooked these hard learned lessons. Selecting and integrating AI models without clear guidance on how these choices affect system security may leave applications vulnerable to threats, such as malicious components, data leakage, and unintended behavior. The goal of this study is to understand practitioners' decision making process and security considerations in selecting and integrating AI components through an exploratory semi-structured interview study. Toward this goal, we conducted semistructured interviews with 22 software developers, architects, and AI practitioners across diverse organizations about how they integrate AI components into their software. Our analysis finds that practitioners' model selection is predominantly driven by functional criteria, including performance, accuracy, cost, and specific features, e.g., tool calling or multimodal support, while security is rarely considered as an evaluation criterion. We observe a consistent lack of security concern throughout the AI component integration process, with established software supply chain lessons overlooked or ignored. The industry is repeating the historically costly mistakes of early software dependency management, prioritizing rapid reuse and availability over security and provenance. We distill our findings into actionable recommendations for AI adopters, model providers, and researchers, advocating for a proactive, security-by-design approach that integrates security evaluation into component selection and sustains it throughout the software development lifecycle. --- ### How Do You Choose Your AI Component? An Interview Study of Secure AI Integration in Practice Authors: Mahzabin Tamanna, Elizabeth Lin, Sparsha Gowda, Laurie Williams, Dominik Wermke Published: 2026-07-18 Categories: cs.SE, cs.AI, cs.CR, cs.IR, cs.LG arXiv: https://arxiv.org/abs/2607.16660v1 The increasing adoption of Large Language Models (LLMs) as AI components in modern software systems introduces distinct security risks to the software supply chain. While many considerations and safety mechanisms are in place for components of the traditional software supply chain, the recent rapid adoption of AI components and platforms has overlooked these hard learned lessons. Selecting and integrating AI models without clear guidance on how these choices affect system security may leave applications vulnerable to threats, such as malicious components, data leakage, and unintended behavior. The goal of this study is to understand practitioners' decision making process and security considerations in selecting and integrating AI components through an exploratory semi-structured interview study. Toward this goal, we conducted semistructured interviews with 22 software developers, architects, and AI practitioners across diverse organizations about how they integrate AI components into their software. Our analysis finds that practitioners' model selection is predominantly driven by functional criteria, including performance, accuracy, cost, and specific features, e.g., tool calling or multimodal support, while security is rarely considered as an evaluation criterion. We observe a consistent lack of security concern throughout the AI component integration process, with established software supply chain lessons overlooked or ignored. The industry is repeating the historically costly mistakes of early software dependency management, prioritizing rapid reuse and availability over security and provenance. We distill our findings into actionable recommendations for AI adopters, model providers, and researchers, advocating for a proactive, security-by-design approach that integrates security evaluation into component selection and sustains it throughout the software development lifecycle. --- ### DORS: Dynamic Attention Routing for Diffusion-based Object Removal in Dense Scenes Authors: Haitong Tang, Haipeng Liu, Yang Wang Published: 2026-07-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16656v1 Object removal aims to eliminate target objects specified by a mask while preserving visual consistency with the surrounding regions. Existing methods typically rely on contextual information from surrounding regions. However, in dense scenes where the surrounding regions contain instances visually similar to the removal target, such reliance often leads to semantic interference, resulting in incomplete removal. This problem arises from erroneous information propagation in the attention space, where masked queries tend to align with such instances due to global similarity matching in self-attention. To address this challenge, we propose a Diffusion-based Object Removal framework for dense Scenes, dubbed DORS, built upon a Dynamic Attention Routing mechanism comprising two complementary components: Instance-Filtered Attention (IFA), which suppresses misleading semantic information from similar instances through dynamically constructed mask-guided attention constraints, and Context-Guided Routing (CGR), which dynamically routes complementary scene information to maintain visual consistency. We further introduce DOR-Bench, a benchmark tailored for object removal in dense scenes. Extensive experiments demonstrate that DORS outperforms state-of-the-art methods, particularly in reducing incomplete removal and duplicate artifacts. The code will be available at https://github.com/httang1224/DORS. --- ### Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model Authors: Kabilan Elangovan, Daniel Ting Published: 2026-07-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.16652v1 This position paper argues that claims about explanation stability are scientifically invalid without cross method validation. Just as statistical significance requires the test statistic to be specified, stability should either be evaluated across multiple attribution paradigms or explicitly scoped to the computational objective of a single method. In controlled chest X ray experiments, DenseNet201, ResNet50V2, and InceptionV3 achieved AUC values above 99%, yet their stability rankings reversed across attribution methods. LayerCAM ranked InceptionV3 as the most stable model, with an IoU of 0.777, whereas GradCAM++ favored DenseNet201 and reduced InceptionV3 stability score by 17.3%. These findings demonstrate that explanation stability is an emergent property of the model method pair rather than an intrinsic characteristic of the model alone. We therefore argue that explanation based claims should be validated across multiple attribution methods and that regulatory submissions should explicitly specify the attribution operators used to avoid creating illusory safety assurances. --- ### DRIFT: Difficulty-aware Rectified Flows for Through-plane MRI Super-Resolution Authors: Yoonseok Choi, Eun-Gyu Ha, Daniel Kim, Mohammed A. Al-masni, Ming-Hsuan Yang, Dong-Hyun Kim Published: 2026-07-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16649v1 Magnetic Resonance Imaging (MRI) is often acquired with anisotropic resolution to reduce scan time, producing stair-step artifacts along the through-plane direction. In through-plane MRI super-resolution, an efficiency-fidelity trade-off arises: feed-forward regressors are fast but oversmooth at large slice-thicknesses, while sampling-based methods improve fidelity at high inference cost. We propose DRIFT, a two-stage thickness-conditioned rectified flow framework for through-plane MRI super-resolution with continuous input slice-thickness. Stage 1 employs an Anatomical Projection Network (APN) to map low-resolution patches to a coarse high-resolution manifold, providing a deterministic anatomical initialization that shortens the residual transport of Stage 2 and stabilizes slice-wise refinement. Stage 2 refines details via rectified flow and introduces a Physics-Aware Difficulty (PAD) metric derived from slice-thickness induced through-plane bandwidth deficit to guide an Adaptive Integration Scheduler (AIS), allocating ODE steps by thickness. A Consistent Endpoint Trajectory Alignment (CETA) loss enforces thickness-consistent reconstructions. Experiments show that DRIFT outperforms super-resolution baselines while reducing inference cost. Code, models, and interactive demos are available at https://yoonseokchoi-ai.github.io/drift-eccv2026/. --- ### Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits Authors: Haifeng Li, Mo Hai Published: 2026-07-18 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.16646v2 Large language models now translate natural-language descriptions of decision problems into solver-ready optimization models, and they fail silently. A generated model often runs and still encodes the wrong problem, while standard evaluation compares optimal values against labeled answers that deployment does not provide. How to certify such a model without any reference is the question this paper addresses. We develop falsification-based verification. Every numeric quantity in a problem description plays a role that the text itself states, such as a capacity, a requirement, or a unit cost, and any correct model must respond to changes in these quantities as the stated roles dictate. From duality and sensitivity analysis we derive a battery of solver-based tests that are individually sound, so a violation certifies a faulty model and the false-positive rate is zero by design. We characterize the errors that no test of this kind can see, give conditions under which each canonical error class is detected with certainty, and prove that perturbation testers with tuned thresholds cannot be simultaneously sound and nontrivial. Across 326 ground-truth models, a synthetic family, and four public benchmarks with two generators, the battery flags 0.0% of faithful models while a threshold tester flags 54.9%; it detects 56.1% of core formulation errors, 70.0% under certified preconditions, and 40.4% of the errors that value-based scoring provably cannot see, and it reproduces the predicted detectability pattern including its blind spots. Every flag carries a machine-checkable certificate that localizes the defect, and a full audit costs about 25 millisecond-scale solver calls per model. Classical sensitivity analysis and duality thus offer a rigorous, label-free audit that complements existing evaluation of AI-generated optimization models. --- ### Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits Authors: Haifeng Li, Mo Hai Published: 2026-07-18 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.16646v1 Large language models now translate natural-language descriptions of decision problems into solver-ready optimization models, but they fail silently. A generated model often runs and still formulates the wrong problem. This paper develops a theory of falsification-based verification for this setting. Every numeric quantity in the description is a typed slot, and a candidate model is tested only through solver calls on slot-transformed instances; no reference model or label is consulted. From duality, comparative statics, and polyhedral limit arguments we derive a battery of test classes covering directions, curvature, crush probes, prohibitive limits, annihilation, and exchange. Every test is sound, so a violation certifies unfaithfulness and the false-positive rate is zero by design. We characterize what such verification can never see, give conditions under which the canonical error classes are detected with certainty, and prove that no fixed-threshold perturbation tester is simultaneously sound and nontrivial. Experiments on 326 ground-truth models from NL4OPT and four benchmark families confirm the theory. The battery attains a 0.0% false-positive rate against 54.9% for a threshold tester, detects 70.0% of certified conditional-class mutants, convicts 40.4% of the mutants invisible to execution-accuracy scoring, and reproduces the predicted detectability pattern including its zeros. --- ### DARA: Degradation-Aware Low-Rank Residual Adaptation with Original-to-Corrupted Distillation for Corruption-Robust Animal Re-Identification Authors: Cynthia Xie, Talia Xu Published: 2026-07-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16644v1 Animal re-identification (Re-ID) relies on fine-grained identity cues that can be disrupted by blur, noise, compression, and other visual degradations. Existing robustness strategies based on degradation-augmented training or pixel-level restoration improve robustness indirectly, but do not explicitly repair shifts in the identity retrieval space. We study corruption-robust animal Re-ID as input-conditioned feature-space repair and introduce DARA, a lightweight retrofit for compact Re-ID models. DARA freezes the fine-tuned backbone and learns routed low-rank residual experts to adapt degraded-input embeddings without corruption-type annotations. To stabilize this adaptive repair, original-to-corrupted distillation uses an original-image teacher to preserve individual embeddings and retrieval relations. Experiments on ATRW, FriesianCattle2017, MPDD, and SeaStarReID2023 show that DARA improves corrupted-query retrieval over standard and augmentation-based fine-tuning, generalizes to unseen corruptions and cross-domain evaluation, and recovers 77.0% of the corrupted-query mAP gap to full corrupted fine-tuning while adding only 0.49% parameters and 0.05% FLOPs. --- ### Diversity-Oriented Fine-Tuning for Uncertainty-Based Hallucination Detection Authors: Qiuyuan Li, Hongliang Dai, Piji Li Published: 2026-07-18 Categories: cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.16643v1 Existing hallucination detection methods are typically conducted at the inference stage, without making any modifications to the model itself. In this paper, we are interested in exploring fine-tuning strategies that enhance the detectability of hallucinations in the resulting model. Focusing on semantic-entropy-based detection, we observe that many erroneous outputs remain undetected because the model produces nearly identical incorrect answers across multiple runs. To address this, we propose diversity-oriented fine-tuning to encourage more varied generations. We introduce two specific strategies: one based on Supervised Fine-Tuning (SFT) and the other on Direct Preference Optimization (DPO). Extensive experiments are conducted to evaluate our approach and analyze the behavior of the models before and after fine-tuning. We find that after adopting our fine-tuning methods, the models become less likely to produce low semantic entropy responses for hallucinated answers, thereby improving the effectiveness of hallucination detection, eventually yielding results better than or comparable with state of the art methods. The code will be publicly released. --- ### De-floored Principal Component Regression: When Rank Selection Alone Is Insufficient for Prediction Authors: Peng Zhao Published: 2026-07-18 Categories: math.ST, cs.LG, stat.ME arXiv: https://arxiv.org/abs/2607.16638v1 Principal component regression (PCR) regularizes high-dimensional prediction by choosing a spectral cutoff, but rank selection cannot correct systematic inflation of the retained empirical eigenvalues. We study clean Gaussian random designs in which the aggregate covariance tail creates a nearly scalar sample-space floor comparable to the predictive head scale. De-floored principal component regression (dPCR) retains the cutoff and subtracts an estimated floor from the retained denominators. We prove an ordinary-PCR prediction-risk lower bound uniform over all ranks and a high-probability dPCR upper bound. When the floor is sharp and inexpensive to remove in population prediction risk, the conditional risk of dPCR is asymptotically negligible relative to that of the best ordinary PCR rank. An exact risk decomposition explains the separation: denominator inflation is governed by first spectral mass, whereas the clean prediction cost of correction is governed by squared spectral mass. A same-sample trimmed-mean floor estimate attains the oracle dPCR upper-bound rate at a prespecified rank, and the separation persists under approximate predictive alignment when the tail prediction-energy fraction vanishes. Separate pointwise fixed-aspect formulas show that the risk-optimal positive scalar correction improves rank-$1$ PCR, whereas mean-floor subtraction is generally not optimal for a broad Marchenko--Pastur bulk. --- ### TopoTuner: Topological Finetuning of Large Language Models Authors: Abdulkadir Erol, Yash Mahajan, Vepaul Hariprashad, Baha Rababah, Santu Karmaker, Cuneyt G. Akcora, Mubarak Shah Published: 2026-07-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.16637v2 Full fine-tuning remains a strong way to adapt pretrained LLMs, but it updates all weights and can be expensive. LoRA reduces the number of trainable parameters, but it does not directly answer which pretrained components should be trained and which can be frozen during adaptation. We introduce TopoTuner, a topology-guided fine-tuning framework for selective freezing of attention projection matrices. \method treats each projection matrix as a row cloud and uses Wasserstein distances between persistence diagrams to measure how its topology changes during fine-tuning. TopoTuner learns a reusable freezing profile from a source dataset and transfers it to efficiently fine-tune models on out-of-domain datasets, evaluating whether task-specific topological drift generalizes across question answering and sentiment analysis tasks. Across LLaMA-3.1-8B, Mistral-7B-v0.3, and Qwen3-8B-Base, TopoTuner is competitive with full fine-tuning while training only 1-2\% of the model parameters, and outperforms LoRA in 7 out of 9 model-dataset settings, which can change up to 39.57\% of the projection parameters. Along with minimized updates, TopoTuner reduces training time by 20.4\% relative to full fine-tuning and 5.5\% relative to LoRA on average. TopoTuner opens a new direction for reusable freezing profiles, where fine-tuning behavior learned on one dataset can be shared across multiple tasks. --- ### TellTale: Blending Multi-Instance LoRA Text Encoders and a Zero-Shot LLM Judge for Ambivalence/Hesitancy Recognition in Videos Authors: Abdel-Karim Al-Tamimi, Ali Rodan Published: 2026-07-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2607.16635v1 We present TellTale, a text-only approach to ambivalence/hesitancy (A/H) recognition in interview videos, evaluated on the BAH dataset as part of the 3rd A/H Video Recognition Challenge (11th ABAW Workshop, ECCV 2026). Although the dataset provides video, audio, facial crops, and transcripts, TellTale relies on the transcript alone and combines three probability streams. Two text encoders, multilingual-e5-large and mDeBERTa-v3-base, are fine-tuned with parameter-efficient LoRA adapters under a multiple-instance learning (MIL) objective, in which transcript chunks are scored individually and pooled with a smooth maximum so that only the video-level label is needed for supervision. The third stream requires no training: a quantized 14B instruction LLM is prompted, zero-shot, to rate each transcript for A/H. The three probabilities are combined by a weighted average and a single decision threshold, both selected on participant-grouped cross-validated predictions. On the organizer-scored private test set of 152 videos from unseen participants, TellTale achieves a Macro-F1 of 0.7364 and an average precision of 0.7940, compared with 0.2827 Macro-F1 for the official vision-based baseline. --- ### CLOSER-Bench: Evaluating Budgeted Cross-Stage Design Closure for Hardware Agents Authors: Peilong Zhou, Zhirong Chen, Cangyuan Li, Haoyu Gao, Kaiyan Chang, Ziming Qu, Ying Wang Published: 2026-07-18 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.16632v1 Hardware engineering exposes coding agents to a form of long-horizon work that is difficult to capture with pass-at-k: progress is continuous, tool feedback is delayed and heterogeneous, and a backend failure may require revising RTL rather than tuning another physical-design parameter. Existing benchmarks measure RTL generation, repository repair, verification, PPA evolution, or physical implementation, but their different designs and oracles make it hard to determine where an agent succeeds or fails across abstraction boundaries. We introduce CLOSER-Bench, a controlled evaluation protocol for budgeted cross-stage design closure. For one design and one hidden objective, it pairs spec-to-RTL, RTL-to-GDS, and spec-to-GDS tasks, records every simulator, synthesis, STA, and place-and-route invocation, and measures final quality, anytime progress, tool cost, and cross-stage recovery. The benchmark is built on open-source Verilator, Yosys, OpenROAD, KLayout, Sky130, and the Harbor agent harness. A ten-task pilot spanning RTL repair, mutation-based verification, coverage, PPA optimization, design-space exploration, cross-model debugging, and security establishes the executable harness and exposes a sharp completion--closure gap: three agents solve a localized AXI repair task, while the matched verification-closure task separates a frontier agent from two otherwise successful baselines. We further validate a full RTL-to-GDS flow and construct a macro-based AXI/DMA streaming accelerator for the stage-paired evaluation. These results motivate treating hardware closure as a budgeted sequential decision problem rather than a collection of independent code generation tasks. --- ### A Research Prototype for Closed-Loop Generative Design of Customized Foot Orthoses via Semantic-Physics Alignment Authors: Rui Wang, Byungwon Min, Suxing Liu Published: 2026-07-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.16631v1 Translating unstructured clinical prescriptions into patient-specific foot orthoses (FOs) is hindered by a semantic-physical misalignment: high-level clinical intent is not mapped deterministically onto the 3D geometric parameters of the orthosis, and existing design workflows remain dependent on manual expertise with no instantaneous biomechanical validation. We present TANS-FO, a research prototype-a modular pipeline with closed-loop feedback for computational design automation of customized FOs, not a clinically validated therapeutic device. A Text-Aligned Neural Surrogate (TANS) uses cross-attention to project clinical-text embeddings onto a continuous lattice-density field, while a Graph Neural Network (GNN) surrogate predicts plantar stress in real time as a substitute for Finite Element Analysis (FEA). The framework is anchored on the open-access PicoFoot-5K anthropometric database (5,230 subjects; 30+ anatomical parameters). Under standardized quasi-static loading, the GNN surrogate agrees with an Abaqus reference solver (R^2 = 0.94), and the full pipeline synthesizes manufacturing-ready lattice insoles within minutes. On the Male 18-40 cohort, the proposed system attains a surrogate-predicted peak-pressure reduction of 34.7% over parametric CAD, with a fit error of 0.42 mm. Separately, an exploratory feasibility observation (n = 12; 2-week follow-up; no control group) using VAS pain reporting indicates short-term comfort improvement (VAS 6.4 -> 2.1), but this data is explicitly classified as preliminary observational evidence only-not evidence of clinical efficacy. --- ### SPARE-GS: Structural Parsimony and Resource Efficiency for 3D Gaussian Splatting Authors: Zhang Chen, Shuai Wan, Fuzheng Yang, Jiazhi Xia, Weiyao Lin, Junhui Hou Published: 2026-07-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16624v1 3D Gaussian Splatting (3DGS) achieves high-fidelity novel view synthesis in real-time; however its training efficiency and representation compactness are hindered by excessive primitive proliferation. To address this challenge, we formulate the structural evolution of 3DGS as a global budget-constrained optimization problem and derive an optimality condition, which requires the marginal utility of structural resources to be balanced across spatial regions under a finite primitive budget. Based on this formulation, we propose SPARE-GS, a general plug-and-play framework that dynamically aligns the distribution of 3D Gaussian primitives with regional representational demand. SPARE-GS estimates capacity-normalized regional demand, assigns adaptive target quotas, and uses regional budget deviations to coordinate densification, pruning and adaptive termination toward a more balanced structural allocation. Extensive experiments across standard, accelerated, and structure-enhanced 3DGS pipelines demonstrate that SPARE-GS reduces the Gaussian count and training time by an average of 30.38% and 23.81%, respectively, while improving the average PSNR. Moreover, the resulting compact representations reduce downstream processing time and improve the rate-distortion performance of diverse compression and pruning methods, demonstrating the broad applicability of global structural budget regulation. --- ### How to Build Marcus's Algebraic Mind: From Minsky's Emotion-Machine Viewpoint Authors: Hiroyuki Chuma, Kanji Otsuka, Yoichi Sato Published: 2026-07-18 Categories: cs.NE arXiv: https://arxiv.org/abs/2607.16623v2 This paper reports a step that had already been taken. Marcus's three components of an adequate cognitive architecture -- variables, recursive structure, individuals vs kinds -- left the neural substrate open; a companion paper answers it with VaCoAl, built on XOR-and-shift over GF(2). Those pillars are horizontal: how a mind represents the world. Minsky's Emotion Machine supplies the orthogonal, vertical dimension -- a mind reasoning about its own reasoning. The vertical step needed no new machinery. A representation exactly recoverable becomes introspection when what is recovered is the reasoner's own deliberative trace: Minsky's Reflective layer. Pillar 2 says nothing about whose structure is recovered; point the same unbind inward and Reflection follows. Only the argument changes. Capability: exact reversible binding at O(N), kept exact within a Frontier Size, yields a trace readable constituent by constituent: a self-report faithful by construction, not verbalization. Only exact-algebraic traces, not probabilistic ones, make the reflexive read faithful. Necessity: audit and valuation are one circuit at opposite settings of one parameter. Repair every collision and the trace is exactly auditable but no path outranks another; tolerate them and the CR2 decay that credits the direct route makes the read approximate. Position: we claim neither to have built the Reflective layer nor to surpass large language models; it supplies the auditable trace probabilistic deliberation cannot leave. The same substrate gives panalogy (content-addressable retrieval scored by CR) and credit assignment as counterfactual unbind-rebind, meeting Pearl's causal axis. Not claimed: Reflection's sufficient conditions (meta-control loop, context-tagging) are future work; Reflection is introspection, not evaluation; its reachability is argued, not shown; speed and power unbenchmarked. --- ### How to Build Marcus's Algebraic Mind: From Minsky's Emotion-Machine Viewpoint Authors: Hiroyuki Chuma, Kanji Otsuka, Yoichi Sato Published: 2026-07-18 Categories: cs.NE arXiv: https://arxiv.org/abs/2607.16623v1 In The Algebraic Mind, Marcus identified three cognitive components: operations over variables, recursively structured representations, and an individual/kind distinction. He left the neural substrate open. A companion paper solves this with VaCoAl, an architecture built on GF(2) XOR-and-shift. It offers exact reversible variable binding, compositional bundling, and spatial individual/kind separation. A collision-avoidance scheme ensures exact recovery within a Frontier Size. Its PyVaCoAl implementation demonstrates this algebra scales to millions of records, while the SRAM-CAM version favors hardware speed. Marcus's horizontal framework concerns how a mind represents the world. This paper reads VaCoAl through an orthogonal lens: Minsky's The Emotion Machine, providing the vertical dimension of a mind reasoning about itself. We claim VaCoAl's exact preservation and recovery of structural representations directly enables introspection -- Minsky's Reflective layer. Reflexively unbinding one's own deliberative trace is the operation. We grade deliberation into three tiers by trace faithfulness: probabilistic (LLMs), approximate-algebraic, and exact-algebraic (VaCoAl). Only exact reversibility ensures reflexive recovery is faithful rather than spurious, reaching the Reflective layer. This substrate carries two more Minsky ideas: panalogy (achieved via content-addressable retrieval where match accuracy indicates analogical fit, enabling lifelong learning) and credit assignment (framed as reflexive counterfactual simulation: surgically unbinding a past choice and rebinding a counterfactual to compare). The exact reversibility allowing the companion paper to climb Pearl's causal ladder helps this paper ascend Minsky's introspective stack, finding the intersection. We separate demonstrated trace execution from theoretical Reflection arguments, leaving meta-control loops strictly for future work. --- ### From Memory to Skills: Evidence-Grounded Co-Evolution Governance for Long-Horizon LLM Agents Authors: Bo Tang, Yang Zhang, Guomian Zhuang, Wenqiang Wei, Gaoyang Zheng, Lindong Xie, Yanchao Tan, Feiyu Xiong, Qingyu Yang, Edward Chung, Zhiyu li Published: 2026-07-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.16621v1 Existing memory systems for long-horizon LLM agents often retrieve prior traces as passive context rather than converting them into executable capabilities. In this paper, we propose MSCE, a training-free Memory--Skill Co-Evolution framework that organizes agent experience into grounded step traces, reusable procedural policies, and declarative environmental cognition. MSCE crystallizes evidence-backed L2 policies with positive estimated gain into callable skills that retain evidence links, applicability boundaries, decision guidance, verification rules, and reliability estimates. It further introduces reflection-weighted value backfilling, which propagates sparse terminal feedback through dense local self-reflections to produce evidence-calibrated trace values for governing memory and skill evolution. Experiments on EvoAgentBench and LoCoMo demonstrate that MSCE significantly outperforms state-of-the-art skill-augmented and memory-driven agent baselines, exhibiting strong cross-domain transferability and lifelong-evolution capabilities. --- ### Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machine Learning Authors: Rakshit Naidu Published: 2026-07-18 Categories: cs.LG, cs.AI, cs.CR, cs.CY arXiv: https://arxiv.org/abs/2607.16620v1 Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems. Prior work has shown that DP-SGD can widen accuracy disparities across demographic groups, but this framing treats fairness as a purely outcome-side concern. We argue that privacy cost, the information leakage borne by each group, is itself a form of harm, and adopt a compensatory-fairness framework in which a group that involuntarily bears greater privacy exposure is owed proportionally greater benefit from the system. From this principle we derive the \emph{Privacy-Cost Equity Ratio} (PCER), a group fairness metric defined as a group's positive prediction rate normalized by its per-group overfitting gap. By a standard membership inference bound, this overfitting gap upper-bounds each group's vulnerability to inference attacks, making PCER a conservative measure of benefit relative to exposure. PCER needs only per-group train and test accuracy (no shadow models), making it a practical post-hoc audit tool. We evaluate PCER alongside standard fairness metrics across six benchmark--attribute combinations spanning tabular and NLP domains, under DP-SGD at a range of privacy budgets, and validate the overfitting-gap proxy against a direct threshold membership-inference attack. The results reveal patterns that outcome-based metrics miss. On COMPAS, PCER uncovers a persistent double disadvantage: the protected group bears both greater privacy exposure and worse predictive outcomes, something demographic parity gap masks entirely. Sensitivity analysis shows very strong privacy guarantees collapse both groups' overfitting to a numerical floor, rendering exposure-based audits uninformative in that regime. Together, these findings show that fairness audits of privacy-preserving systems must account for who bears the cost of protection, not only who benefits from its outcomes. --- ### DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines Authors: Runming He, Zhen Hao Wong, Hao Liang, Zimo Meng, Chengyu Shen, Xiaochen Ma, Wentao Zhang Published: 2026-07-18 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2607.16617v2 Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the \textit{NL2Pipeline gap}. To bridge it, we introduce \textsc{DataFlow-Harness}, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines \textsc{DataFlow-Skills} for procedural guidance, a Model Context Protocol (MCP) layer that exposes the live operator registry and current pipeline state, and \textsc{DataFlow-WebUI}, which synchronizes conversational authoring with a visual DAG editor. On a 12-task data-engineering benchmark, \textsc{DataFlow-Harness} achieves a 93.3\% observed end-to-end pass rate. Relative to Vanilla Claude Code, it reduces measured monetary cost by 72.5\% and generation latency by 49.9\%; its observed pass rate is within 0.9 percentage points of the Context-Aware Claude Code baseline while its cost is 42.8\% lower. Per-task analysis indicates that Skills are most useful when construction depends on implicit procedural knowledge. These results show that live platform grounding can produce persistent, editable workflow artifacts with an observed reliability close to script-generation baselines and with lower measured construction cost and latency. --- ### Backpropagation-Free Trunk Training via the Split Forward Gradients Authors: Tian Qin, Wei-Min Huang Published: 2026-07-18 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2607.16612v1 Backpropagation makes training deep networks memory intensive because it must store intermediate activations. Forward-mode methods avoid this cost, but their gradient estimates become increasingly noisy as the number of trained parameters grows. We introduce Split Forward Gradient (Split-FG), which splits a network at an intermediate representation: it computes the output head gradient exactly and estimates only the trunk gradient with a Jacobian--vector product. This reduces estimator variance and requires no backward pass through the trunk, while retaining an Adam-style convergence guarantee. Our experiments reveal an important practical failure mode. On WikiText-103, naive forward-gradient training of the trunk performs worse than leaving a randomly initialized trunk frozen, likely because Adam updates every noisy, under-determined trunk coordinate too aggressively. Simply using a much smaller learning rate for the trunk reverses this result: a $16$M-parameter GPT-2-style model reaches validation perplexity $387$, compared with $668$ for the frozen-trunk control and $2{,}885$ for a matched pure forward-gradient baseline (backpropagation reaches $150$). Split-FG also produces the strongest backprop-free results on our tabular benchmarks and reaches $60.5\%$ on CIFAR-10 and $35.2\%$ on CIFAR-100 with a heavy-head design. It reduces peak memory by up to $35\%$ relative to matched backpropagation, although the performance gap widens as the forward-mode trunk grows. --- ### Just A Rather Very Intelligent Spoken Agent Authors: Chen Chen, Zhehuai Chen Published: 2026-07-18 Categories: cs.AI arXiv: https://arxiv.org/abs/2607.16610v1 Long-horizon AI agents are becoming increasingly capable, yet their interaction with users remains surprisingly thin. In most workflows, users give an initial instruction, receive only selective textual updates, and lose a clear sense of what the agent is doing or when to step in. This leaves a missing part in the current agent ecosystem: an always-on Jarvis-style mediator that keeps the agent continuously reachable to the user. Such a mediator should support real-time spoken interaction with the user, answer questions without interrupting the worker, proactively report progress or confusion, and inject user guidance back into the agent's execution when useful. In this work, we introduce JarvisBench, a benchmark for measuring the dual value of mediation in long-horizon agent workflows. JarvisBench contains two complementary tracks: an agent-collaboration track that measures whether mediation improves downstream task completion, and a user-interaction track that measures whether mediation makes ongoing execution more understandable, responsive, and accessible to users. We instantiate the benchmark with a modular reference Jarvis prototype and evaluate it on 34 text-only WildClaw tasks executed in OpenClaw. Preliminary results with GPT-5.5, Claude Opus 4.7, Gemini-based, and GPT-based worker agents suggest that Jarvis-style mediation can provide trace-grounded responses to user questions and improve task performance when sparse user guidance is injected at appropriate moments. The results also show that effectiveness depends strongly on the mediator's LLM brain, highlighting both the promise of this missing middle layer and the need for broader community effort. Demo page https://cchen1436.github.io/jarvis --- ### Can Multimodal Large Language Models Understand OCT? Authors: Baochen Fu, Wenzhi Deng, Baihao Jin, Yang Li, Zihan Nie, Kailin Jiang, Yuntao Du, Weiye Song Published: 2026-07-18 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2607.16609v1 Optical coherence tomography (OCT) imaging is essential for the diagnosis and treatment of retinal diseases. Although multimodal large language models (MLLMs) have demonstrated considerable potential in medical image analysis, existing benchmarks largely reduce OCT understanding to coarse-grained disease classification or isolated visual question answering, leaving the complete cognitive process from visual perception to clinical reasoning insufficiently evaluated. To address this limitation, we introduce OCT-Bench, a comprehensive benchmark dedicated to OCT image understanding. OCT-Bench comprises 10,076 high-quality multiple-choice questions constructed from 4,137 OCT images across seven public datasets. Following the real-world clinical interpretation workflow, we establish a hierarchical capability taxonomy consisting of 20 fine-grained tasks across three dimensions: Perception, Cognition, and Reasoning. These tasks cover a broad range of capabilities, including imaging attributes, retinal anatomy, lesion characteristics, spatial relationships, disease assessment, therapeutic decision-making, and prognostic management. We systematically evaluate 20 representative MLLMs, including proprietary models, open-source general-purpose models, and medical-domain models. Experimental results demonstrate that current models remain substantially short of reliable OCT understanding. Moreover, neither medical-domain adaptation nor increased model scale consistently improves performance across capability levels. OCT-Bench enables comprehensive and fine-grained evaluation of MLLMs, providing a foundation for identifying capability bottlenecks and advancing clinically grounded OCT understanding. --- ### NOWJ@COLIEE 2026: Adaptive Pipelines for Legal Retrieval and Reasoning Authors: Thuong-Hieu Ngo, Hoang-Trung Nguyen, Huu-Dong Nguyen, Xuan-Bach Le, Le-Dung Nguyen, Quang-Thanh Tran, Ha-Thanh Nguyen, Thi-Hai-Yen Vuong Published: 2026-07-18 Categories: cs.CL arXiv: https://arxiv.org/abs/2607.16603v1 This paper presents the methodologies and results of the NOWJ team's participation across all five tasks of the COLIEE 2026 competition. For Task 1 (Legal Case Retrieval), we propose a four-stage pipeline comprising candidate filtering, dense retrieval with complementary embedding models, cross-encoder reranking via fine-tuned generative rerankers and MLP-based pairwise classification, and adaptive per-query cutoff prediction. For Task 2 (Legal Case Entailment), we combine BM25 filtering, T5-based reranking, and LLM-based entailment verification with consensus ensemble. For Task 3 (Statute Law Retrieval and Entailment), we adopt a retrieval-augmented generation framework with dense retrieval, attention-based reranking, and few-shot-prompted LLM reasoning. For Task 4 (Legal Textual Entailment), we introduce a dynamic routing pipeline that classifies query difficulty and dispatches cases to either a balanced few-shot solver or a structured zero-shot chain-of-thought solver. For the Pilot Task (Legal Judgment Prediction), we combine hierarchical transformers with CRF layers, argument relation mining, and probabilistic argumentation graph reasoning. --- ### PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration Authors: Han Wang, Zijun Wang, Shuoshuo Xue, Rui Cao, Fengjiao Chen, Xiaodan Liang, Roy Ka-Wei Lee Published: 2026-07-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16602v3 Action-conditioned world models are a key component of embodied AI, serving as scalable policy evaluators that reduce reliance on expensive real-world rollouts. To accurately capture diverse action-induced dynamics, such models should satisfy three key objectives-Physical Plausibility (P), Action Adherence (A), and Visual Fidelity (V), collectively referred to as PAV-while remaining robust to both in-distribution (ID) expert demonstrations and out-of-distribution (OOD) actions. However, existing methods primarily rely on ID action-video pairs and pixel-level reconstruction losses, which do not explicitly optimize PAV objectives and generalize poorly beyond expert data. To address this, we propose PAVXploreRL, a reinforcement learning framework built on a pretrained latent world model that explicitly optimizes PAV objectives through reward-driven training. To improve action generalization, our method jointly leverages ID trajectories and noise-driven OOD action exploration, without paired video supervision. Experiments show that PAVXploreRL consistently outperforms pretrained baselines, achieving a 5.6% average gain across benchmarks and producing higher-quality PAV properties. As a policy evaluator, it also yields more reliable performance estimates and reduces the overestimation bias of prior expert-only world models such as Ctrl-World. Code: https://github.com/Social-AI-Studio/PAVXploreRL --- ### PAVXploreRL: Physical-Action-Visual World Model Reinforcement Learning with Action Exploration Authors: Han Wang, Zijun Wang, Shuoshuo Xue, Rui Cao, Fengjiao Cheng, Xiaodan Liang, Roy Ka-Wei Lee Published: 2026-07-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16602v2 Action-conditioned world models are a key component of embodied AI, serving as scalable policy evaluators that reduce reliance on expensive real-world rollouts. To accurately capture diverse action-induced dynamics, such models should satisfy three key objectives-Physical Plausibility (P), Action Adherence (A), and Visual Fidelity (V), collectively referred to as PAV-while remaining robust to both in-distribution (ID) expert demonstrations and out-of-distribution (OOD) actions. However, existing methods primarily rely on ID action-video pairs and pixel-level reconstruction losses, which do not explicitly optimize PAV objectives and generalize poorly beyond expert data. To address this, we propose PAVXploreRL, a reinforcement learning framework built on a pretrained latent world model that explicitly optimizes PAV objectives through reward-driven training. To improve action generalization, our method jointly leverages ID trajectories and noise-driven OOD action exploration, without paired video supervision. Experiments show that PAVXploreRL consistently outperforms pretrained baselines, achieving a 5.6% average gain across benchmarks and producing higher-quality PAV properties. As a policy evaluator, it also yields more reliable performance estimates and reduces the overestimation bias of prior expert-only world models such as Ctrl-World. Code: https://github.com/Social-AI-Studio/PAVXploreRL --- ### FST.ai 2.5: Explainable and Uncertainty-Aware AI for Olympic and Para-Taekwondo Decision Support, Athlete Digital Twins, and Federation-Scale Analytics Authors: Keivan Shariatmadar, Ahmad Osman, Ramin Rey Published: 2026-07-18 Categories: cs.AI, math.OC, math.PR arXiv: https://arxiv.org/abs/2607.16597v1 The rapid digitalisation of elite sport has created new opportunities for integrating artificial intelligence (AI), performance analytics, and decision-support systems into athlete development and competition management. However, existing solutions remain fragmented, typically addressing isolated tasks such as performance analysis, athlete monitoring, or referee support. This paper presents \textbf{FST$\cdot$ai~2.5}, an explainable, uncertainty-aware, and secure AI framework for Olympic and Para-Taekwondo. \textbf{FST$\cdot$ai~2.5} introduces a unified digital ecosystem integrating athlete intelligence, competition analytics, federation-scale data management, AI-assisted decision support, athlete and event digital twins, explainable performance indicators, and adaptive training recommendations. The framework supports World Taekwondo (WT), Member National Associations (MNAs), coaches, referees, analysts, and athletes through transparent, secure, and federation-aware governance. By combining multi-source competition data, athlete-performance information, and contextual evidence, \textbf{FST$\cdot$ai~2.5} provides tactical diagnostics, longitudinal athlete monitoring, performance forecasting, personalised development planning, and federation-wide benchmarking using explainable and uncertainty-aware AI. Prototype deployments demonstrate the feasibility of the proposed framework. Although developed for Olympic and Para-Taekwondo, the methodology is broadly applicable to explainable AI, digital twins, and trustworthy decision support in combat sports and other high-performance sporting environments. --- ### Learning from World Feedback: Why Model Uncertainty Fails as a Risk Signal in Model-Based RL Authors: Zhaohui Wang Published: 2026-07-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2607.16591v1 The RLxF programme argues that learning signals should come from world feedback rather than from internal model proxies. We instantiate this position in safe model-based control and distil it into three concrete design principles. Empirically, across four world-model architectures spanning a 2x MSE range, MPC planning is statistically equivalent (TOST, n=200), and dynamics-based uncertainty penalties increase collision rates from 26% to 34%: the standard MBRL safety proxy is anti-correlated with safety in this regime. Replacing the model-internal proxy with three world-feedback signals (a sensor-derived margin via minimum lidar, a temporal signal via time-to-collision, and an outcome-supervised feedback model g_psi trained on prior collision labels, structurally analogous to outcome-trained reward models in RLHF) reduces collisions to 1-14% without retraining the world model or the planner. The mechanism is structural: model uncertainty has support over state-prediction space, whereas task risk has support over constraint boundaries, with empirical correlation r < 0.15. From this we extract three RLxF principles (ground risk in world outcomes, validate proxies before deployment, and substitute outcome-trained feedback models when direct world signals are unavailable) and argue they apply equally to model-based control and to verifier-based or RLHF approaches in LLM alignment. --- ### Digital measurement of droplet flame diameter in microgravity combustion images using Segment Anything Model 2 with automatic prompt selection Authors: Minghui Xu, Chaoyi Zhou, Aaron P. Cecil, Xi Liu, Siyu Huang, Yuhao Xu Published: 2026-07-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2607.16587v1 Flame diameter is a key measurable parameter in microgravity droplet combustion, but its extraction from self-illuminated frames remains difficult because soot tails, blurred luminous boundaries, chamber reflections, and droplet drift introduce substantial measurement bias and operator dependence. This work presents an AI-enabled digital measurement workflow for automated flame diameter from combustion images. The workflow integrates automatic prompt-point generation into Segment Anything Model 2, employing Random Sample Consensus (RANSAC)-based circle fitting. The automatic prompt strategy removes subjective manual point selection, while the video memory mechanism maintains temporal consistency for drifting droplets, and the RANSAC fitting rejects soot-tail pixels as geometric outliers. The method is validated by 19,537 flame images of n-heptane, n-decane, and n-octane droplets with varying initial diameters. Compared with manual-reference measurements, the proposed workflow achieves a mean relative agreement of 96.9%, a mean absolute percentage error of 3.1%, and substantially outperforms conventional Hough circle detection, which performed worse under the same evaluation conditions. The results also show that the measurement accuracy improves with increasing droplet size. The proposed workflow has a combined standard uncertainty of 8.54% and achieves approximately a 229-fold improvement in efficiency over manual measurement. These results demonstrate that the proposed SAM2-based workflow provides a reproducible, fully automated, and metrologically characterized digital measurement system for extracting flame diameter from challenging combustion images. The approach supports high-throughput combustion diagnostics and illustrates that AI-based segmentation can be integrated into quantitative measurement workflows for digitalized image-based metrology. --- ### Harnessing disorder to decouple extension and shear in kirigami metamaterials Authors: Haomin Yu, Hanxun Jin, Mingxuan Bi, Mohammad Jafari, Feng Helen Long, Michael J Greenberg, Farid Alisafaei, Guy Genin Published: 2026-07-18 Categories: cond-mat.mtrl-sci, cs.LG arXiv: https://arxiv.org/abs/2607.16583v1 Kirigami turns stiff sheets into compliant, shape-morphing structures, but its reliance on periodic cut patterns comes at a cost: correlated panel rotations couple extension to shear, so stretching one axis drives a parasitic shear that cannot be suppressed, and also confine anisotropic stiffness to a narrow, discrete set of responses that cannot be tuned independently. Biological tissues overcome an analogous constraint through controlled disorder, such as graded fiber orientations in skin and hierarchical anisotropy in myocardium, achieving direction-dependent mechanics unavailable to regular architectures. Here, we show that engineered disorder is a design degree of freedom for kirigami, with stochastic kirigami accessing a continuous and far broader region of mechanical response than periodic patterns. This includes programmable anisotropy with near-complete elimination of extension-shear coupling. Because disordered patterns lack a simple parameterization, we navigate this design space with a geometry-aware graph neural network (GNN) that maps cut topology to the full nonlinear, bidirectional stress-strain response, coupled to a genetic algorithm that inverse-designs patterns reproducing target responses along two perpendicular axes. The GNN trains an order of magnitude faster and more accurately than image-based models. Fabricated elastomer samples reproduce the predicted nonlinear, anisotropic responses, closing the loop from design to physical component. By turning disorder into a variable to control directional stiffness, this work develops architected materials that stretch without parasitic shear, from soft actuators to tissue-interfacing devices matched to the anisotropy of living tissue. --- ### Autonomous VR-Based Risk Detection for Situational Awareness in Dangerous Settings Authors: Mohammad Eskandari, Murali Krishna Varma Indukuri, Stephanie M. Lukin, Cynthia Matuszek Published: 2026-07-18 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2607.16582v1 In high-risk environments such as disaster response, situational awareness depends not only on detecting hazards but also on communicating them clearly to human operators. Vision Language Models (VLMs) have shown strong potential for scene understanding in safety-critical settings, yet their value as part of human-facing robotic systems remains underexplored. We present a VR-based Human Robot Interaction framework for studying how VLM-assisted robots can support situational awareness in simulated hazardous environments. In our system, a robot explores a virtual scene and queries a VLM to identify potential hazards and annotate user-facing points of interest. These annotations are presented to a human operator through an immersive VR interface. This framework enables controlled evaluation of both robotic hazard identification and the communication of safety-critical information to users. Results from our study indicate that the annotated VR interface was preferred over the unannotated baseline and that participants reported high clarity, usefulness, and comfort when interacting with the system. These findings suggest that combining VLM-based robotic perception with immersive visualization is a promising approach for supporting situational awareness in hazardous settings. ---