arXiv:2607.01677v1 Announce Type: new Abstract: Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-frame accuracy but suffer from temporal drift due to limited context windows, while generative methods improve consistency and generalization at the cost of extensive training data (10M+ samples) and lack of geometric precision. In response to these issues, we introduce \textbf{ICDepth}, a framework that adapts pre-trained text-to-video diffusion transformers for video depth estimation via In-Context Conditioning (ICC), leveraging their rich spatial-temporal priors. To address key challenges in transferring ICC from generation to dense prediction, we propose: (1)~\textbf{SAND-Attention}, which ensures precise spatial-temporal alignment via shared RoPE and enforces unidirectional attention to prevent noise contamination; (2)~\textbf{SRFM}, which injects DINOv2 semantic and resolution priors to enhance geometric precision. ICDepth achieves state-of-the-art results on multiple benchmarks with remarkable data efficiency, trained on only 0.8M frames ($6$--$13\times$ less than competing generative methods), while demonstrating strong zero-shot generalization to diverse domains.
Science Journals
arXiv:2607.02089v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, yet they remain vulnerable to unreliable reasoning. Existing self-correction methods mitigate these issues but typically rely on post-training or carefully engineered feedback, incurring high computational cost. In this work, we revisit this challenge through the lens of emotional cues, asking whether they can activate latent self-correction behaviors in VLMs without additional training. \textbf{We find that emotional signals serve as an effective trigger for self-correction, encouraging more cautious and reflective reasoning}. Motivated by this finding, we propose \escabstract (\textbf{\underline{E}}motional \textbf{\underline{S}}elf-\textbf{\underline{C}}orrection), a training-free self-correction framework. ESC introduces an external verifier that detects potentially incorrect initial responses and injects emotional feedback to encourage model to reflect, and produce a better revised response without additional training. Extensive experiments across safety, hallucination, vision-centric perception, and multimodal reasoning benchmarks show that ESC consistently improves reliability while preserving overall model utility. These results suggest that emotion can function not only as an ability to be recognized, but also as a practical control signal for scalable self-correction in VLMs. \textbf{We therefore believe that ESC provides a strong foundation for a new reliable human-like, emotion-integrated research direction.} Our project is publicly available at \textcolor{red}{https://genai4e.github.io/ESC/}.
arXiv:2607.01729v1 Announce Type: new Abstract: Deep learning models for speech classification are vulnerable to backdoor attacks, where malicious triggers cause misclassification at inference time. While sample-specific attacks can bypass many defenses, they often rely on poisoned label attack, making them detectable via manual data defense. In this paper, we propose DRL-CLBA, a novel clean label backdoor attack for speech classification that leverages Deep Deterministic Policy Gradient (DDPG) reinforcement learning. We also utilize deep audio steganography to embed sample-specific triggers into source audio, creating feature-space anchors. The proposed reinforcement learning framework effectively optimizes target samples toward trigger-bearing anchor points in the model's deep latent space, enabling label-migration-free poisoning of target samples. Experimental results across three datasets and four different DNNs demonstrate that DRL-CLBA achieves a high attack success rate, effectively bypassing some backdoor defenses. The attack demonstrates strong resistance against fine-tuning, pruning, and spectral signature defenses, exposing critical vulnerabilities in speech-controlled systems.
arXiv:2607.01715v1 Announce Type: new Abstract: Existing robust preference optimization for language-model alignment mainly studies pairwise supervision and places robustness at the dataset, prompt, or preference-pair level. We instead study listwise preference optimization under ranking-label uncertainty: given a prompt and a candidate list, the observed ranking over that list may be ambiguous due to annotator inconsistency, near-ties, lossy rankwise feedback, or reward-model noise. We propose a pointwise total-variation robust Plackett--Luce objective that directly robustifies the ranking label conditional on the candidate list. The robust loss admits an exact decomposition into the nominal PL loss plus a worst-case PL correction, and the worst-case ranking is obtained by sorting current implicit scores in ascending order, reducing the inner maximization from $K!$ enumeration to $O(K\log K)$. This tractable structure yields strong offline and online optimization guarantees. In the offline fixed-list setting, the robust objective is convex and projected stochastic subgradient reaches global $\epsilon$-suboptimality with $O(\epsilon^{-2})$ sample complexity. In the online policy-induced setting, where candidate lists are generated by the current policy, we establish weak convexity and $\widetilde O(\epsilon^{-2})$ Moreau-envelope stationarity. Experiments in offline LLM alignment show that the proposed robust correction largely preserves performance under clean labels and improves robustness under noise. In online alignment, it makes reward-model-ranked candidate expansion more reliable and improves both reward-model and external GPT-4 judge metrics.
arXiv:2606.03305v2 Announce Type: replace Abstract: Benchmark contamination, where evaluation examples appear in a model's training data, threatens the validity of LLM assessment. Statistical tools for detecting training-data membership exist, but have been validated almost exclusively in controlled academic regimes: large, homogeneous pre-training corpora and transparent, single-stage training pipelines. Whether these methods remain reliable in realistic auditing scenarios remains unclear. We identify two under-studied failure modes: distribution shift, which arises when suspect and validation sets violate the IID assumption, and scale constraints, which arise because benchmarks are orders of magnitude smaller than pre-training corpora. We systematically evaluate three leading paradigms, LLM Dataset Inference, Post-Hoc Dataset Inference, and CoDeC, across 25 models from multiple families (including Pythia, OLMo 2, and specialised cultural and medical LLMs) and scales (up to 27B). We then further extend our analysis to frontier industry models. Across 335 evaluations, only 201 yield correct outcomes. LLM Dataset Inference results in false positives under distribution shift, Post-Hoc Dataset Inference is underpowered at benchmark scale, and CoDeC provides only coarse provenance signals that are insufficient to verify individual benchmark splits. Our results reveal a systematic reliability gap between controlled validation and practical benchmark auditing, and show that statistical detection cannot yet replace transparent data provenance. We open-source our benchmark for further research.
arXiv:2512.02657v2 Announce Type: replace Abstract: Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations arise over time. Existing unlearning methods, however, are designed for single-step deletion and collapse after only 3-5 sequential applications. We trace this instability to two compounding factors: (i) coarse mapping targets that cause degradation to accumulate unnecessarily across steps, and (ii) the absence of local protection for semantically neighboring concepts, whose shared internal representations make them the first to suffer collateral damage. Because this damage is strongest in the local semantic neighborhood of the forget concept, global replay alone cannot prevent it. Building on this analysis, we propose Locality-Aware Continual Unlearning (LACU), a framework with two complementary mechanisms. Locality-Aware Target Selection chooses, for each forget prompt, the context-preserving mapping prompt that the diffusion model itself treats as most similar to the original prompt, measured by score-prediction distance (how differently the model denoises the same noisy image under two text conditions), ensuring each update is as small and targeted as possible. Locality-Aware Replay uses the same metric to identify the retain concepts closest to the forget concept in the model's own representation and replays them as a local functional regularizer, directly shielding the most vulnerable neighborhood. Combined with teacher-student distillation and lightweight $\ell_2$ parameter regularization, LACU maintains stable unlearning over 10 sequential steps, preserving significantly higher related retention ($RR_{\text{acc}}$) and general retention ($GR_{\text{acc}}$) than recent baselines.
arXiv:1807.05630v3 Announce Type: replace-cross Abstract: Smooth entropies are a tool for quantifying resource trade-offs in (quantum) information theory and cryptography. In typical bi- and multi-partite problems, however, some of the sub-systems are often left unchanged and this is not reflected by the standard smoothing of information measures over a ball of close states. We propose to smooth instead only over a ball of close states which also have some of the reduced states on the relevant sub-systems fixed. This partial smoothing of information measures naturally allows to give more refined characterizations of various information-theoretic problems in the one-shot setting. In particular, we immediately get asymptotic second-order characterizations for tasks such as privacy amplification against classical side information or classical state splitting. For quantum problems like state merging the general resource trade-off is tightly characterized by partially smoothed information measures as well.
arXiv:2606.31363v2 Announce Type: replace Abstract: Single image super-resolution aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. Training SR models typically requires paired HR-LR data, which is difficult to obtain in reality. As a result, most methods synthesize LR images by artificially degrading HR images with handcrafted kernels or camera ISP adjustments. However, these synthetic degradations fail to capture the complexity of real LR images, leading to poor generalization in practice. To address this, we observe that even within a single high-quality image, regions at different depths exhibit varying resolutions, where distant regions act as LR patches and closer ones as HR patches. This allows the extraction of real, degradation-induced LR patches from real images. Since these LR patches lack paired HR counterparts, we propose LA-SR (Language Assistant for SR), a novel framework for unpaired SR. The key idea of LA-SR is to redefine unpaired SR in the language space, using vision-language models to bridge the LR-HR gap. LA-SR projects images into a semantically rich space representing both content and quality, and applies two language-guided losses: linguistic content loss to preserve semantic fidelity, and linguistic quality loss to enhance perceptual realism. With this alignment, LA-SR effectively super-resolves real LR inputs, producing realistic outputs that overcome the limitations of synthetic-data-trained methods.
arXiv:2606.31763v2 Announce Type: replace Abstract: Autonomous wet-lab experimentation requires more than plausible protocol text: biological intent, quantitative procedures, device constraints and experimental feedback must remain aligned from protocol and SOP design to code and physical execution. We developed ProtoPilot, a self-evolving multi-agent system, together with an expert-grounded benchmark and evaluation framework for testing this conversion as an experimental automation problem. The framework spans 294 synthetic-biology and molecular-biology tasks derived from 98 gold-standard protocols, wet-lab expert rubrics, device-level validity gates and real experimental tests. ProtoPilot incorporates layer-wise verifiability, multi-agent orchestration and a runtime-updated skill library to generate protocols, expand SOPs, synthesize SDK-compliant code and revise workflows from wet-lab feedback. It achieved a Top@3 expert-preference rate of 90.2%, an overall protocol-to-code gate pass rate of 89.5% and an Opentrons pass rate of 88.24%, compared with 32.35% for OpenTrons-AI. Wet-lab validation produced interpretable readouts, Sanger-confirmed products and feedback-corrected PCA-assembled DNA targets, establishing a verifiable route to autonomous experimentation. Together, these results show that the evaluation framework captures execution-relevant requirements for autonomous wet-lab automation, and that ProtoPilot can meet them by converting protocol and code generation into validated execution and feedback-guided revision.
arXiv:2601.14534v2 Announce Type: replace Abstract: The United States labor market has entered a period in which high job vacancy rates and prolonged unemployment persist together. Classical theory attributes such conditions to skills mismatch or geographic immobility, but neither fully explains a pattern now widely reported: qualified candidates are rejected at the earliest, automated stage of hiring, before any human sees their application. This paper introduces Artificial Frictional Unemployment (AFU), a framework describing how deterministic automated screening rejects qualified candidates through semantic misinterpretation rather than genuine skill gaps. We situate the phenomenon within labor economics and information asymmetry theory and formalize the mechanism by which legacy Applicant Tracking Systems (ATS) turn hiring into a high-precision classification problem that inflates false negatives. The contribution is primarily conceptual. To make the mechanism concrete, we report a controlled proof-of-concept simulation comparing keyword-based screening with vector-space semantic matching under identical conditions. The simulation shows how lexical variance alone can produce false negatives; it is not a measurement of how much real-world friction is artificial, which we leave to future field studies. Building on the framework, we outline JobOS, a candidate-side architecture that illustrates how semantic competency mapping could operate alongside existing hiring infrastructure. Framing automated recruitment as labor market infrastructure, rather than a firm-level convenience, exposes a correctable source of matching inefficiency with consequences for workforce participation and the use of human capital.
arXiv:2606.17793v2 Announce Type: replace Abstract: We introduce AIriskEval-gaming, an open platform and dataset to evaluate social engineering risks in LLM-mediated multimodal interaction through controlled games. It supports human-human, human-AI and AI-AI settings, combining configurable game templates, role-conditioned LLM agents, psychology-informed participant profiling, structured interaction trees, and synchronized behavioral and biometric acquisition, filtering, and deep-learning-based feature extraction. The dataset (AIriskEval-gaming-db) was collected from 15 participants who interacted with a role-conditioned GPT-5.4 agent in two concatenated games: an adapted Prisoner's Dilemma and an Ultimatum Game. It comprises 340 GB of raw and processed multimodal data across six streams: interaction logs, video, screen recordings, gaze logs, smartwatch signals, and game/questionnaire metadata. These data include interaction paths, written justifications, psychological profiles, subjective feedback, perceived counterpart identity, game outcomes, and derived behavioral, facial, and gaze features. Alongside the dataset, we provide descriptive analyses characterizing the resulting multimodal data. Rigorous risk evaluation is essential for the deployment of secure AI systems, as it enables the identification and mitigation of vulnerabilities, ensures the protection of sensitive data, and supports compliance with evolving regulatory and ethical standards in society. The dataset and related code are available on GitHub.
arXiv:2607.00483v2 Announce Type: replace Abstract: Designing effective reward functions remains a major challenge in reinforcement learning (RL), particularly in open-ended environments where task goals are abstract and difficult to quantify. In this work, we present VLM-AR3L, a framework that leverages Vision-Language Models (VLMs) to provide both absolute and relative rewards for RL. VLM-AR3L interprets an agent's visual observations in the context of a natural language task goal, and learns both absolute and relative rewards from VLM-generated preference labels. The absolute reward model predicts scalar evaluations for individual states, while the relative reward model compares consecutive observations to infer progress or regression toward the task goal. Their integration combines the stability of state-based evaluation with the robustness of comparative supervision. We evaluate VLM-AR3L across benchmarks spanning classic control, manipulation, and open-world embodied tasks, with a particular focus on Minecraft given its visual complexity and long-horizon decision-making requirements. Experimental results show that VLM-AR3L consistently outperforms prior VLM-based reward learning methods.
arXiv:2607.01461v1 Announce Type: new Abstract: Peridynamics is a fast growing field of continuum mechanics, especially developed for the modeling and simulation of fracture problems, initiated a quarter century ago. In this study, we analyze the evolution of the peridynamics community since its inception in terms of publication co-authorship. For this purpose, we construct a peridynamics co-authorship network for each year from 2000 to 2024 and perform network analysis based on selected metrics. Nodes represent scientists, and links connect co-authoring scientists with link weights representing the number of co-authorships (based on the total number of co-authors per publication). Network-level metrics are used to quantify the evolution of the field, and node-level metrics are used to identify trends in the most collaborative scientists in peridynamics. We noticed a deviation in network trends that occurred in the years since 2019, and we subsequently performed a country-based analysis with insights about the impact of the COVID-19 pandemic on the evolution of the peridynamics co-authorship network.
arXiv:2607.01487v1 Announce Type: new Abstract: We propose a scaling law that takes into account model size and training data while explicitly splitting the latter into training steps and batch size (called three-term law). Fitting the proposed law on a large set of training runs, we find that it correctly recovers the scaling of the optimal batch size. Moreover, because it makes use of training runs with suboptimal batch size, our proposed law can be robustly fit with a significantly smaller amount of training runs. We further show that the three-term law can be used to derive scaling laws for suboptimal batch sizes, and that it matches previous empirical findings related to the critical batch size.
arXiv:2607.01554v1 Announce Type: new Abstract: This study proposes a reconfigurable rocker-bogie mechanism that achieves efficient turning motion with a small number of actuators while maintaining high step-climbing capability. By installing motors at the bogie joints and actively swinging up and down bogies, the system enables switching between four-wheel and six-wheel configurations. Omnidirectional wheels are mounted on the rear ends of the rockers, allowing smooth turning in the four-wheel configuration based on a differential-drive model. Experimental evaluation using a prototype robot demonstrated that the proposed mechanism achieves zero-radius turning at a speed more than five times that of a conventional rocker-bogie mechanism equipped with six non-steerable grip wheels, while requiring only approximately 17% of the total average wheel torque. In addition, the robot successfully climbed a 40 cm step with an average climbing time of 6.4 s, confirming its high turning and step-climbing performance.
arXiv:2607.01792v1 Announce Type: new Abstract: While decoder-only LLMs excel at a vast array of natural language tasks, it suffers from an asymmetric information flow induced by causal attention: later tokens are richer in contextual grounding than earlier ones. A simple and effective remedy is prompt repetition -- just appending a second copy of prompt before generation can redistribute grounding across positions and improve reasoning performance. However, full repetition of the original prompt doubles the KV cache footprint and quadruples attention cost during prefill, making it impractical for long-context settings. We propose PartRep, a selective augmentation method that appends only the most informative tokens -- rather than the entire prompt. We use token-wise negative log-likelihood (NLL) as a selection signal, motivated by the hypothesis that less predictable tokens are less recoverable from surrounding context and therefore benefit more from late-position repetition. To avoid the heavy cost of a full forward pass for scoring, we train a lightweight gate that predicts high-NLL tokens from early-layer hidden states, enabling token selection during mid-prefill via early exit. Across eight benchmarks (including MMLU, GSM8K, and RULER) and three model families (Qwen2.5, Llama3.2, Gemma4), PartRep retains most of the gains of full repetition while using only 59.4\% of its KV cache and 79.0\% of its prefill FLOPs.
arXiv:2412.08907v3 Announce Type: replace Abstract: Global geolocation, which seeks to predict the geographical location of images captured anywhere in the world, is one of the most challenging tasks in the field of computer vision. In this paper, we introduce an innovative interactive global geolocation assistant named GaGA, built upon the flourishing large vision-language models (LVLMs). GaGA uncovers geographical clues within images and combines them with the extensive world knowledge embedded in LVLMs to determine the geolocations while also providing justifications and explanations for the prediction results. We further designed a novel interactive geolocation method that surpasses traditional static inference approaches. It allows users to intervene, correct, or provide clues for the predictions, making the model more flexible and practical. The development of GaGA relies on the newly proposed Multi-modal Global Geolocation (MG-Geo) dataset, a comprehensive collection of 5 million high-quality image-text pairs. GaGA achieves state-of-the-art performance on the GWS15k dataset, improving accuracy by 4.57% at the country level and 2.92% at the city level, setting a new benchmark. These advancements represent a significant leap forward in developing highly accurate, interactive geolocation systems with global applicability.
arXiv:2504.03711v2 Announce Type: replace Abstract: Artificial intelligence (AI)-driven electronic design automation (EDA) techniques have been extensively explored for VLSI circuit design applications. Most recently, foundation AI models for circuits have emerged as a new technology trend. Unlike traditional task-specific AI solutions, these new AI models are developed through two stages: 1) self-supervised pre-training on a large amount of unlabeled data to learn intrinsic circuit properties; and 2) efficient fine-tuning for specific downstream applications, such as early-stage design quality evaluation, circuit-related context generation, and functional verification. This new paradigm brings many advantages: model generalization, less reliance on labeled circuit data, efficient adaptation to new tasks, and unprecedented generative capability. In this paper, we propose referring to AI models developed with this new paradigm as circuit foundation models (CFMs). This paper provides a comprehensive survey of the latest progress in circuit foundation models, unprecedentedly covering over 130 relevant works. Over 90% of our introduced works were published in or after 2022, indicating that this emerging research trend has attracted wide attention in a short period. In this survey, we propose to categorize all existing circuit foundation models into two primary types: 1) encoder-based methods performing general circuit representation learning for predictive tasks; and 2) decoder-based methods leveraging large language models (LLMs) for generative tasks. For our introduced works, we cover their input modalities, model architecture, pre-training strategies, domain adaptation techniques, and downstream design applications. In addition, this paper discussed the unique properties of circuits from the data perspective. These circuit properties have motivated many works in this domain and differentiated them from general AI techniques.
arXiv:2607.01854v1 Announce Type: new Abstract: Can a platform tell, before deployment, whether an open-weight checkpoint has had its refusal mechanism stripped? Runtime guards cannot: they score generations, not the artifact. We combine two cheap internal signals, a reference-anchored activation refusal-gap and a weight-recovery energy of the base-to-candidate weight difference, into a threshold-free checkpoint audit. The two are negatively correlated and label-complementary: the gap supplies refusal-specificity and the weight energy supplies recall. On a 273-checkpoint registry spanning Qwen, DeepSeek-distilled Qwen, Llama, and Gemma, their z-sum separates 57 public abliterations from 37 benign fine-tunes, merges, and instruction-tunes at AUROC 0.95, significantly above either signal alone (0.84, 0.90), and a Youden-calibrated threshold transfers to held-out families at balanced accuracy 0.89 (FPR 0.11), missing only 4 of 57. We then map two failures, in order of severity: a spoofed reference evades both axes with no training ({\Delta}W=0, \r{ho}=1 by construction), and a white-box owner trains a checkpoint past the threshold while it stays guard-unsafe and coherent. The audit is effective triage, not tamper-proofing: it presumes an attested reference, and its claims are bounded by the registry we evaluate it on.
arXiv:2607.01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training. To study this phenomenon, we introduce STEER (Safety Targeted Embedding Exploit via Refinement), a gradient-guided attack that identifies words contributing most strongly to the model's refusal behavior and iteratively translates them into low-resource languages to suppress refusal while preserving harmful intent. Across six open-source 8B-parameter models, STEER achieves attack success rates of up to 93.0% on JailbreakBench and 96.7% on AdvBench, outperforming random code-switching and Greedy Coordinate Gradient (GCG). The resulting prompts also transfer to GPT-4o-mini, achieving a 35.5% attack success rate without requiring access to the target model, suggesting that the underlying weakness is not specific to a single architecture. These findings demonstrate that safety mechanisms aligned primarily on English cannot be assumed to generalize across multilingual inputs. We argue that improving multilingual safety requires broader coverage during alignment and mechanisms that explicitly detect and abstain on out-of-distribution inputs.
arXiv:2607.01704v1 Announce Type: new Abstract: Unordered trees appear in applications where the order among child vertices is insignificant, such as abstract syntax trees and chemical structures. To describe patterns in such trees, we propose unordered term tree patterns, which employ height-constrained variables that restrict trunk length and subtree height. We formalize the pattern matching problem between an unordered term tree pattern and an unordered tree, and present an $O(N \cdot \max\{nD^{3/2}, \mathcal{S}\})$-time algorithm, where $n$ and $N$ are the numbers of vertices in the pattern and tree, $D$ is the maximum vertex degree, and $\mathcal{S}$ is the sum of trunk constraints. Computational results show that the algorithm runs efficiently in practice.
arXiv:2607.01734v1 Announce Type: new Abstract: We present a case study in reformalization, a variant of autoformalization in which the input proof is not natural language but a formal development in a different proof assistant. Concretely, we report three reformalizations of the Jordan Curve Theorem: from Mizar to Lean, from HOL Light to Lean, and from HOL Light to Agda. We analyse the results and identify pipeline design choices that matter for practical reformalization tasks.
arXiv:2607.01871v1 Announce Type: new Abstract: Current road safety systems primarily focus on minimizing post-collision damage. However, advances in algorithmic perception are shifting focus toward early collision prediction, especially in lowvisibility conditions like nighttime or fog, where thermal infrared sensing outperforms both human vision and RGB imaging. While available RGB-infrared datasets such as FLIR ADAS and LLVIP are good benchmarks, they mostly consist of clear weather and overly simple scenarios. In this article, we introduce the LYNRED-MDS: Multimodal Detection Subset, a subset of the LYNRED Mobility Dataset, comprised of 4000 RGB-infrared image pairs captured under diverse weather, lighting, and road conditions around Grenoble, France. Our dataset spans varied driving contexts (urban, rural, mountainous, etc.) and a vehicle fleet compliant with Western European standards. Thermal cross-dataset evaluation using a YOLOv8n baseline suggests that our dataset offers strong generalization potential for pedestrian detection in driving scenarios. By covering critical edge cases, our dataset supports the development of more reliable and deployable vision systems for advanced driver-assistance systems.
arXiv:2607.01794v1 Announce Type: new Abstract: With the rapid development of autonomous aerial systems, Unmanned Aerial Vehicles (UAVs) are increasingly deployed in applications such as inspection, environmental monitoring, and rescue, creating growing demand for reliable autonomous navigation. However, autonomous UAV navigation in dense environments remains challenging under sparse perception and dynamic constraints. Most reinforcement learning (RL) methods lack explicit safety mechanisms, leading to unsafe exploration, unstable training, and risky behaviors, especially during high-speed flight. Even in safe RL approaches, safety is often enforced by projecting policy outputs onto a safe action set, which may introduce instability. Meanwhile, many learning-based methods rely on dense inputs or large networks, increasing computational burden and limiting lightweight onboard deployment. Facing the above challenges, we propose a safety-constrained perception-control integrated framework for UAV navigation. A lightweight network encodes sparse observations into collision-risk-aware features using asymmetric and depthwise separable convolutions. We formulate the task as a constrained Markov decision process within a hierarchical control architecture and solve it using a Lagrangian-based safe PPO algorithm. Curriculum learning further improves training stability. Experiments with varying obstacle densities and flight speeds demonstrate higher success rates, improved safety, and better efficiency than existing reinforcement learning baselines.
arXiv:2607.01891v1 Announce Type: new Abstract: Information Systems research increasingly relies on machine learning (ML) to predict outcomes in complex sociotechnical systems, yet predictive models are not designed to identify causal effects. This limitation is particularly critical in building retrofits, where unbiased estimates of energy savings are essential for climate policy and investment decisions. Because retrofit adoption is shaped by household and building characteristics that also affect energy consumption, predictive ML can yield biased effect estimates. This paper systematically benchmarks leading causal ML estimators, including metalearners (S-, T- and X-Learners) and DoubleML across multiple retrofit interventions. To enable this comparison, we construct a physically grounded simulation in which true treatment effects and realistic adoption biases are known. Results show that DoubleML achieves the lowest estimation errors, particularly for complex envelope retrofits. These findings demonstrate that orthogonalising the treatment assignment improves causal effect estimation and provides a methodological foundation for large-scale energy retrofit and policy evaluation.