Search

Topics

Environment198 papers Environmental Uncertainty27 papers Urban Environments182 papers Unknown Environments112 papers Real-World Environments69 papers 3D Environments28 papers Indoor Environments28 papers Railway Environments17 papers Harbor Environments14 papers Agentic Control87 papers Sea-Surface Temperature Data45 papers Ocean43 papers

Papers 6,901–6,930 of 6,967

Date pendingcs.CV

EVIS: Real-Time Event Camera Simulation with Multimodal Supervision in NVIDIA Isaac Sim

Event cameras are increasingly adopted in embodied perception for their microsecond temporal resolution, high dynamic range, and resilience to motion blur. However, training event-based models for robotics requires large-scale, action-conditioned data with dense physical annotations that are difficult to collect in the real world. We introduce EVIS, an open-source physics-grounded event simulator integrated into NVIDIA Isaac Sim that generates events from linear-HDR radiance from a closed-loop robot training episode. Rather than relying on learning-based video interpolation or expensive dense rendering, EVIS exploits renderer-provided motion vectors and depth maps through bi-directional warping and depth-based splatting. This enables high throughput, real-time, and high-fidelity event generation. We evaluate EVIS across runtime efficiency, sim-to-real transfer, and zero-shot model compatibility. A rotation-speed estimator trained solely on EVIS events achieves 2.75 rad/s MAE on real sensor data. Pretrained models for reconstruction, matching, and tracking perform competitively on EVIS events without any fine-tuning. EVIS sustains real-time generation across GPU-parallel environments on a single GPU. Code repository: https://github.com/spikelab-jhu/isaac-sim-event-camera-plugin.

Linli Shi, Ruijun Zhang, Ziyun Wang

Johns Hopkins University

Nvidia Isaac Sim Ego-Motion Robotics Plug-And-Play

Date pendingcs.RO

Learning Traversability for Long Horizon Off-Road Navigation

Autonomous navigation across large off-road environments remains a challenging problem. Onboard sensors perceive only the immediate surroundings, yet safe and efficient routes depend on terrain features that extend well beyond the sensor horizon. Geo-spatial data sources such as satellite imagery, aerial LiDAR, and vector maps can close this gap, but learning traversability from them is difficult: dense labels are unavailable at scale, and existing methods rely on short-range sensing. We propose an efficient formulation that learns a continuous traversability map from overhead data, supervised directly by human-driven GPS trajectories and shaped by supervised geometric priors from LiDAR. Alongside the model, we release a dataset, curated from public sources, consisting of 299 scenes spanning

\sim\!1{,}244\,\mathrm{km}^{2}

of diverse terrain, paired with

1{,}130\,\mathrm{km}

of human driving. In field trials on a Clearpath Warthog across seven routes at two sites,our method achieves trajectories within

5.5\%

of human path length and reduces operator interventions by

\sim\!85\%

compared to local-planner-only autonomy.

Kasi Viswanath, Jason M. Gregory, Shaunak Kolhe +1

Department of Mechanical Engineering, Texas A&M University, College Station, TX 77840, USA · DEVCOM Army Research laboratory, Adelphi, MD, USA

Traversability Autonomous Navigation Navigation Long-Horizon

Date pendingcs.AI

A Density-Matrix Framework for Electronic-Structure Analysis of Electrolytes for Lithium Batteries

Electrolyte reactivity in lithium batteries is shaped by molecular functional groups, Li

^{+}

solvation and salt-anion participation. Conventional quantum chemistry is too computationally expensive for systematic analysis of diverse electrolyte molecules and their local solvation environments. Here we present EMolStudio, a density-matrix-centered AI platform for electronic-structure prediction and analysis. Its workflow integrates molecular functionalization, explicit Li

^{+}

first-shell assembly, density-matrix prediction, and electronic-structure parsing. Applied to 163,655 functionalized molecules and 22,500 first-shell clusters across four lithium salts, we find that 1) functionalization separates CO

_{2}

Me, CN, F/CF

_{3}

, and sulfonyl groups by distinct shifts in frontier levels, electrostatic potential, and Li

^{+}

-donor contact; 2) anion identity reshapes frontier-orbital localization, with LiTDI anchoring the highest occupied orbital on the anion across the library. By carrying a unified density-matrix representation from molecular functionalization to salt-resolved solvation shells, EMolStudio provides a general platform for understanding and designing battery electrolytes.

Mingkang Liu, Huize Yu, Lei Shen

Department of Mechanical Engineering, National University of Singapore, 9 Engineering Drive 1, Singapore 117575, Singapore · National University of Singapore (Chongqing) Research Institute, Chongqing 401120, China · National University of Singapore Guangzhou Research Translation and Innovation Institute, Guangzhou, Guangdong 510700, China

Large-Scale Electronic Structure Calculations Previous Machine-Learning-Based Implicit Solvent Lithium-Ion Batteries

Date pendingcs.AI

Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents

We study proactive exploration in LLM agents, i.e., the ability to explore an environment to acquire information that improves future decision-making. In this regard, we first identify two fundamental bottlenecks that hinder this capability and then propose \ours, a novel method designed to instill and refine proactive exploration. Specifically, \ours\ consists of two components: (1) Exploratory Data Construction, which synthesizes exploration-rich trajectories to mitigate the hindsight bias of standard demonstrations; and (2) RL Optimization with Contrastive Signal Guidance, which leverages contrastive trajectory pairs to distinguish productive exploration from redundant wandering. Extensive experiments demonstrate the effectiveness of \ours\ and provide insights into the characteristics of proactive exploration. Our code is available at: https://github.com/GuanZhizhao/SAFARI.

Zhizhao Guan, Chen Huang, Ziming Liu +5

Sichuan University · Engineering Research Center of Machine Learning and Industry Intelligence · National University of Singapore +1

Large Language Model Agents Autonomous Exploration Strategies Interaction Trajectories

Date pendingcs.CR

Chameleon: An Adaptive AI-Driven Honeypot Architecture Using Threat-Calibrated Particle Swarm Optimization and Semantic Deception Rapidly-Exploring Random Trees

Traditional honeypots share an invariant behavioral profile: a skilled adversary can confirm the presence of a deception environment within a few diagnostic commands, limiting their intelligence value. Commercial deception products (USD 100,000-150,000/year) similarly lack real-time model-driven feedback. Chameleon, an openly distributed adaptive honeypot, addresses both shortcomings. It integrates: a BiLSTM classifier achieving 99.61% accuracy across seven threat categories at ~2 ms CPU latency; a locally deployed Qwen3.5-0.8B model delivering 90% generation accuracy at 4.5 ms latency; and two meta-heuristic engines. Threat-Calibrated PSO (TC-PSO) reshapes swarm inertia and objective amplification in proportion to the classifier's anomaly output, adjusting connection-holding delays in real time. Semantic Deception RRT (S-RRT) evolves deception schemas via exponentially scaled pheromone updates from a language-model severity assessment, with a depth-decay multiplier enforcing a finite memory footprint. A controlled 30-seed benchmark (42-71, identical trajectories and budgets) shows threat-calibrated inertia alone does not improve search over standard PSO on static or dynamic landscapes (p = 0.18); population-diversity mechanisms (GA/ACO) significantly outperform PSO-family optimizers on threat-regime shifts (p < 0.0001, d <= -37). S-RRT's depth-decay delivers a significant memory reduction versus standard RRT (53.1 vs. 119.2 units, p < 0.0001, d = -10.0); its severity-weighted pheromone does not improve raw fitness. Operating cost is ~USD 17/month, a ~490-fold reduction versus commercial alternatives.

Rohit Swami, Tushar Singh, Akash Warde +1

Dept. of AI and Data Science, SIES Graduate School of Technology, Mumbai, India

Honeypots Threat Models Artificial Intelligence Detection Deception Particle Swarm Optimization Olfactory Perception

Date pendingcs.CV

A2DINOv3: Rethinking Multi-Modal Object Detection via Socialized Collaboration

Multi-modal object detection is essential for robust scene understanding in challenging conditions, including low-light and adverse environments. Recent vision foundation models (e.g., DINOv3) have exhibited strong representation capabilities, yet adapting them to multi-modal scenarios remains challenging. Existing dense cross-modal fusion strategies often force heterogeneous modalities to interact indiscriminately, which may introduce redundant information and disrupt the valuable pre-trained representations. To address this issue, we revisit multi-modal fusion from the perspective of socialized learning and propose adapter to DINOv3 (A2DINOv3), a multi-expert collaboration framework with a Socialized Collaboration Protocol (SCP). Specifically, RGB and infrared branches are modeled as heterogeneous experts that independently preserve their specialized knowledge while exchanging complementary information through selective and constrained interactions. This design mitigates harmful cross-modal interference and prevents degradation of pre-trained priors during adaptation. Furthermore, a zero-initialization strategy is introduced to gradually activate cross-modal collaboration, enabling a smooth transition from modality-specific learning to cooperative representation learning. Extensive experiments on four multi-modal benchmarks, including aerial detection (GAIIC), autonomous driving (FLIR), low-light surveillance (LLVIP), and diverse real-world scenarios (M3FD), demonstrate that A2DINOv3 consistently achieves state-of-the-art performance in multi-modal object detection.

Jiekang Feng, Zhihe Fan, Yunqi Zhu +6

School of Artificial Intelligence, Tianjin University · School of Sports Training, Tianjin University of Sport · School of Computer Science and Engineering, University of New South Wales +2

Cross-Modal Fusion Cross-Modal Learning Dinov3 Collaboration

Date pendingcs.RO

CLAP: Cross-Embodiment Video World Models are Zero-Shot Physical Simulators

State-of-the-art action-conditioned video models are typically restricted to a single robot embodiment, preventing them from leveraging the vast corpus of heterogeneous video data that contains rich signals for learning generalizable physics. To bridge this gap, we introduce CLAP, a framework for cross-embodiment action-conditioned video generation capable of being trained on diverse, internet-scale videos across human and robotic agents. CLAP is grounded in the insight that universal physical laws govern spatiotemporal dynamics regardless of the actor. However, cross-embodiment learning is non-trivial because action representations vary sharply across robot platforms and are typically absent in human videos. CLAP addresses this fundamental challenge through the following core contributions. First, CLAP reconciles disparate action spaces using end-effector poses, language instructions, and latent actions. Second, to resolve their individual limitations, CLAP introduces a curriculum-based cross-embodiment learning recipe that first learns foundational physical priors across unlabeled video data using latent actions and subsequently grounds them in end-effector action spaces for zero-shot deployment to real-world tasks. Crucially, CLAP approaches or surpasses state-of-the-art single-embodiment video models in challenging environments like DROID. These performance advantages compound via few-shot adaptation to establish a novel paradigm for training single-embodiment video world models. Ultimately, CLAP delivers the most comprehensive suite of action-conditioned video world models to date - spanning diverse action-conditioning spaces (end-effector, language, and latent) and robot morphologies (including cross-embodiment, DROID, Bridge, bimanual YAM robots, and G1 humanoids). We open-source all code and models. Project Website at https://omni-clap.github.io .

Kechen Liu, Ola Shorinwa

Princeton University

Cross-Embodiment Transfer Video World Models End-Effector Pose Curriculum

Date pendingcs.LG

TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification

The widespread adoption of encrypted traffic poses severe challenges to current security situational awareness systems based on network traffic monitoring. In existing dataset-driven training and testing studies, limitations such as shortcut learning induced by spurious feature correlations and sample imbalance caused by the long-tail distribution of real-world traffic result in weak generalization of traffic identification performance to real-world network traffic. To address these limitations, we propose TDDM-Melatt, a disentangled memory-based traffic classification framework with diffusion-based data augmentation. First, we design Melatt, a memory-decoupled traffic representation model, which employs Competitive Gating Long Short-Term Memory (CG-LSTM) to construct the encoder and decoder. We design a spurious-correlation-free pre-training and inference paradigm, employing strict topology anonymization and a frozen pre-trained encoder strategy to cut off the model's learning pathways for spurious features. During inference, classification is performed efficiently by a downstream classifier on the frozen representations. Second, we propose a Traffic Denoising Diffusion Model (TDDM) tailored to the characteristics of traffic data. Extensive experiments are conducted on 4 representative public benchmark datasets. Under strict flow-level splitting and anonymization, TDDM-Melatt outperforms 6 basic classification models and 6 SOTA representation learning models. The proposed method provides a new and effective technical pathway for encrypted traffic classification in real-world network environments.

Ze Chen, Qiming Yu, Zijia Song +2

National University of Defense Technology Hefei, Anhui, China

Network Traffic Reconstruction-Based Anomaly Detection Discrete Diffusion Model Denoising Diffusion Probabilistic Model Frozen Encoder

Date pendingcs.RO

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments. Modern vision-language models (VLMs) already encode spatial priors for visual grounding, spatial reasoning, and pointing, but these capabilities are rarely elicited directly for robot control. Existing navigation systems instead rely on task- or embodiment-specific components, fragmenting perception, reasoning, and action while offering limited generalization. Here we present LightNav-0, a compact generalist embodied navigation model that elicits the spatial intelligence of a pretrained VLM and aligns it with navigation, without task-specific prediction heads. LightNav-0 represents diverse navigation tasks through a unified token interface: dual-channel pointing expresses task-, scene-, and embodiment-agnostic spatial intent, while a residual vector-quantized action tokenizer maps this intent to precise, embodiment-specific trajectories. Together with temporally aware visual history compression, ER mid-training, supervised fine-tuning, and reinforcement learning, this formulation supports instruction following, open-vocabulary object navigation, and visual tracking within a single model. The navigation training corpus spans 2K+ scenes and 4K+ hours of embodied navigation data. LightNav-ER, the embodied-reasoning checkpoint used to initialize LightNav-0, attains the highest complete-set average across 8 embodied-reasoning benchmarks, while LightNav-0 achieves state-of-the-art monocular success rates across all 10 public navigation simulation settings. Real-world evaluations further demonstrate zero-shot generalization across robot embodiments, diverse scenes, and static and dynamic targets. These results establish compact VLMs as a unified and transferable backbone for generalist embodied navigation.

Shaoan Wang, Aocheng Luo, Fei Huang +17

Light Origins Team

Embodied Navigation Spatial Reasoning

Date pendingcs.AI

SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation

Cumulative culture enables humans to preserve, reuse, and extend knowledge and skills across experiences and generations. Inspired by this principle, we introduce \textit{SimSkill}, a self-evolving agent built around the Simulation of Urban MObility (SUMO) traffic simulator. SimSkill continually identifies capability gaps, generates and solves environment-grounded tasks, verifies solutions through an action--critic loop, and consolidates experience into episodic, procedural, and semantic memory. Through autonomous exploration, it builds a library of reusable skills and knowledge spanning major stages of the traffic-simulation workflow. We evaluate SimSkill on two held-out benchmarks across three backbone LLMs, with each result independently verified. It improves verified success by up to 25 percentage points, and ablations show complementary contributions from procedural and semantic memory. Its benefits remain backbone- and budget-dependent, as memory does not improve every model or uniformly reduce inference cost. More broadly, SimSkill illustrates a natural-language-centered design paradigm for LLM-based agent systems. Its high-level control logic, operating principles, and accumulated knowledge are expressed in natural language, while an LLM integrates them with executable tools and code to realize precise and reproducible execution. All code and experimental data are publicly available at https://github.com/qiliuchn/SimSkill-V1.

Qi Liu, Qinzheng Wang, Can Li +2

School of Transportation, Jilin University, 5988 Renmin St., Changchun, Jilin 130022, China · Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation, Tongji University, 4800 Cao’an Rd., Shanghai 201804, China

Microscopic Traffic Simulations Self-Evolving Agents Traffic Long-Term Memory

Date pendingcs.CV

Catalogue Photography as a Cold Start: Toward Deployable Rotary Milling Tool Recognition

Verifying that manufactured batches of rotary milling tools, also known as carbide burrs, conform to production order sheets remains a largely manual and error-prone quality assurance task. Automating this process with computer vision faces a critical cold-start constraint since no labelled imagery from the deployment environment is available, leaving manufacturer catalogue photography as the sole source of supervision. We investigate how far catalogue supervision can support an industrial recognition pipeline under domain shift, explicitly measuring the gap between catalogue separability and performance on held-out field photographs. Our findings reveal three key insights. First, off-the-shelf frozen feature extractors do not reliably separate the two task attributes, head shape and tooth profile, motivating targeted representation learning. Second, metric learning produces near-perfect unsupervised cluster discovery on catalogue images (adjusted Rand index 0.94--0.97), yet on field photographs under half of the accuracy gained from training survives. Third, the largest transfer gains do not come from model scale or representation complexity, but from simple changes that reduce domain sensitivity: converting images to grayscale (+0.22) and constraining retrieval against the known order sheet (+0.11). We therefore treat catalogue photography as a useful cold start rather than a deployment-ready training domain, and provide empirical baselines and an evaluation protocol for catalogue-to-field transfer in precision tool manufacturing.

Abilash Philip Madavath, Chandra Yuvesh Aubeeluck, Augustin Raju +3

TH Köln – University of Applied Sciences, Cologne, Germany

Computer Vision Domain Shift Cold-Start

Date pendingcs.MA

EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?

Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what they observe and what they can do. In practice, this harness continually evolves as new capabilities are added. We introduce EVOHARNESSBENCH, a benchmark for evaluating agents under controlled harness evolution across three axes (tools, skills, and agents). Unlike existing continual-learning benchmarks for agents, which typically place non-stationarity (i.e., what changes over time) in the task stream while keeping the harness fixed, EVOHARNESSBENCH places non-stationarity in the externally supplied harness itself. It contains 17 multi-stage harness streams constructed deterministically from verifier-based benchmarks, comprising 802 tasks, 520 tools, 42 skills, and 62 agents. We evaluate two complementary settings corresponding to the central challenges of harness evolution: deployment evaluation, which isolates retention of previously accessible competence as the harness expands, and self-evolving adaptation evaluation, which tests whether accumulated experience remains useful as new capabilities are introduced. Our results reveal three persistent gaps. First, harness expansion alone can degrade performance on previously solved tasks, producing harness-induced forgetting. Second, gains from self-evolving adaptation remain inconsistent across stages of harness evolution, capability axes, and environments. Third, retention and adaptation can pull in different directions: preserving earlier competence does not necessarily improve adaptation to newly introduced capabilities, and vice versa. These results establish harness evolution as a distinct challenge for building agents that can keep pace with an evolving harness while preserving previously effective behavior.

Zixuan Ke, Vaidehi Patil, Haizhou Shi +9

Salesforce Research · University of North Carolina at Chapel Hill, conducted this work during an internship at Salesforce Research · University of Wisconsin–Madison +1

Agent Harness Llm-Based Agent Reusable Skills Forgetting

Date pendingcs.AI

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of 8 models spanning capability tiers across 54 benchmarks; every model is run with Terminus-2 and with one of 3 native harnesses. This enables a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Index, a curated set of 82 difficult, diverse, and high-quality tasks spanning 29 benchmarks, refined from the adapted suite through difficulty filtering, AI and human audit, and an audit-and-fix loop. Harbor-Index preserves the challenge and breadth of large-scale agentic evaluations while being affordable to run; no evaluated model-harness configuration exceeds 30% pass rate, and the strongest (GPT-5.5 with Codex) reaches 28.0%. We release the adapters, evaluation results, in-depth analysis, and Harbor-Index as open-source artifacts to support more reliable and comprehensive evaluation of language-model agents.

Lin Shi (Audrey), Haowei Lin (Audrey), Zixuan Zhu (Audrey) +123

Agentic Benchmarks Agentic Evaluations Unified Evaluation Adversarial Evaluation Harbor Environments Infrastructure

Date pendingcs.RO

GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning

Robot manipulation foundation models require scalable evaluation and data generation across diverse scenarios, with simulation providing an environment for both. Automated scene generation offers a promising path, yet prior work has largely emphasized coarse-grained scene layouts rather than fine-grained functional object compositions. Motivated by this gap, we present GIF, an agentic Generation framework for Interactive and Functional object compositions. In this framework, we recast this problem as disentangled reconstruction followed by relative pose recovery. CoGen produces instance-disentangled meshes with coarse initial poses leveraging complementary strengths of 2D and 3D generative models. GPRM refines the relative pose under joint geometric and physical guidance, and a VLM verifier selects the candidate that best matches the structured specification. We further construct a benchmark spanning eight representative contact-geometry classes and compare with state-of-the-art generators; GIF improves both asset quality and relation matching, while reducing collision rate to below 1%. Finally, we synthesize data for policy learning, revealing diversity scaling in both simulation and real-world deployment.

Long Xu, Zhiqi Zhang, Mi Yan +8

Galbot · Zhejiang University · Peking University +3

Indoor Scene Generation Articulated Objects 3D Generative Models Robot Systems Meshes

Date pendingcs.CV

SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine Activities

Smart healthcare monitoring systems require precise action recognition to ensure well-being and timely intervention in critical situations such as falls, particularly for mobility-challenged individuals. Existing datasets are often clip-based, lacking the frame-level detail needed to recognize actions online, as they unfold. To address this, we introduce SAFER-Activities, a dataset for fall detection and physical activity monitoring, with a dedicated subset for wheelchair use scenarios. It comprises over 66 hours of video data captured by multiple cameras, with 85,310 action instances and frame-level annotations for 30 action classes. We benchmark action recognition on SAFER-Activities with 2D and 3D skeleton models, RGB models with frozen backbones, and multimodal fusion strategies, and evaluate on in-lab, out-of-distribution, and cross-dataset test sets. Skeleton-based models generalize best under domain shift; fusing frozen RGB features with the skeleton stream improves in-domain recognition over the baseline CNN1D, most clearly on the wheelchair subset, but degrades out of distribution. Cross-dataset and qualitative evaluations confirm that models trained on SAFER-Activities transfer well to unseen environments and external fall data. To support research on robust fall detection and activity monitoring, we release the dataset and code at https://safer-activities.github.io/.

Diwas Lamsal, Pramod Wickramatilake, Jednipat Moonrinta +2

KU Leuven, Leuven 3000, Belgium · Asian Institute of Technology, Khlong Luang, Pathum Thani 12120, Thailand

Robust Fall Detection Human Activity Recognition Autonomous Powered Wheelchair Robotic Datasets Pedestrian Detection Video Surveillance+6

Date pendingcs.RO

SwingBot: Learning Whole-Body Brachiation for Humanoid Robots

Brachiation enables primates to move across overhead supports when ground paths are blocked, suggesting a complementary locomotion mode for robots operating in cluttered or hazardous environments. Bringing this capability to high-DoF humanoid robots is difficult because the controller must discover a long-horizon release-swing-capture sequence, coordinate alternating contacts with whole-body momentum, and act without reliable measurements of segment-relative displacement or hook-contact state. We present SwingBot, a learning framework for continuous humanoid brachiation with passive wrist hooks. SwingBot makes the task trainable by organizing learning around the structure of brachiation: biomimetic keyframes make rare release-swing-capture transitions reachable during early exploration, and recurrent privileged-state estimation provides compact position and contact latents for deployment. Hardware experiments demonstrate continuous bar traversal and robustness to payload, external disturbances and different bar spacings, showing that this formulation offers a practical route to whole-body robotic brachiation.

Yujie Xiong, Peng Zhai, Taixian Hou +6

College of Intelligent Robotics and Advanced Manufacturing, Fudan University

Adaptive Locomotion Robot Systems

Oct 1, 2026cs.AI

Beyond State-of-the-Art: Standardising Environmental Impact Metrics for AI Research

As the capabilities and ubiquity of Large Language Models (LLMs) grow, so does their environmental footprint. Despite calls for responsible AI, the machine learning community lacks standardised practices for carbon accounting. Our automated literature review of the 5,285 papers accepted to NeurIPS 2025 reveals that reporting of environmental impact is nearly non-existent. To catalyse a shift toward sustainable AI, we define standardised sustainability metrics for evaluating model training efficiency, accompanied by simple heuristics to estimate the carbon cost of LLM inference. We implement these metrics in carbonbenchmark, a drop-in software solution for tracking and reporting emissions. Finally, to combat the pursuit of marginal accuracy gains at disproportionate environmental costs, we formalise the

Smallest Model that Achieves the Job' (SMAJ), a framework which challenges the field to prioritise computational efficiency and environmental accountability alongside traditional

State-of-the-Art' (SotA) accuracy.

Lachlan McGinness, Dan Pagendam, Robert Offner

School of Computing, Australian National University · Commonwealth Scientific and Industrial Research Organisation

Artificial Intelligence Infrastructure

Sep 28, 2026cs.AI

Calibrated Uncertainty for Informative Path Planning in Aquatic Environmental Monitoring

Informative Path Planning for scalar field reconstruction uses predictive uncertainty to direct sensing vehicles toward maximally informative locations. Gaussian Processes provide this signal but their stationary isotropic kernels are misspecified for non-homogeneous phenomena such as oil spills, producing miscalibrated estimates that degrade planning. We investigate whether replacing the Gaussian Process with a well-calibrated Deep Ensemble improves path planning outcomes, and whether uncertainty quality interacts with the choice of planning algorithm. Five strategies (

ε

-Greedy, Value Greedy, Uncertainty Greedy, Monte Carlo Tree Search, and Receding Horizon Orienteering) share a common Deep Ensemble backbone trained on physics-based oil spill simulations. On held-out stochastic spill scenarios, the Deep Ensemble reduces normalised reconstruction error by

83\%

relative to the Gaussian Process baseline. Crucially, well-calibrated uncertainty amplifies the importance of the planning strategy: the performance gap between algorithms is negligible under miscalibrated models but becomes substantial under the ensemble, where multi-step lookahead planners outperform greedy selection by up to

32\%

in reconstruction error and achieve IoU above

0.85

. Monte Carlo Tree Search is the recommended planner, matching Orienteering in reconstruction quality at an order-of-magnitude lower computational cost.

Samuel Yanes Luis, Alejandro Casado Pérez, Alejandro Mendoza Barrionuevo +3

Department of Electronic Technology, University of Sevilla, Sevilla, Spain · Department of Electronic Engineering, University of Sevilla, Sevilla, Spain

Optimal Sensor Placement Pixel-Level Prediction

Sep 28, 2026cs.CV

Advancing Wildlife Conservation through Multimodal Animal Re-Identification with Environmental Metadata

Identifying individual animals is crucial for effective wildlife monitoring and conservation efforts. Recent advancements in computer vision have shown promise in animal re-identification (Animal ReID) by leveraging data from camera traps. However, existing Animal ReID datasets rely exclusively on visual data, overlooking environmental metadata that ecologists have identified as highly correlated with animal behavior and identity, such as temperature and circadian rhythms. Meanwhile, modern vision-language models (VLMs) offer rich multimodal reasoning capabilities, but existing resources underutilize their text-processing potential. To address these limitations, we propose MetaWild, a multimodal Animal ReID dataset comprising 20,890 images across six species, paired with environmental metadata extracted from embedded camera trap overlays and scene contexts. Additionally, to facilitate the use of metadata in existing ReID methods, we propose the Meta-Feature Adapter (MFA), a lightweight module that can be incorporated into existing VLM-based ReID methods, allowing ReID models to leverage both environmental metadata and visual information to improve ReID performance. Experiments on MetaWild show that combining baseline ReID models with MFA to incorporate metadata consistently improves performance compared to using visual information alone, validating the effectiveness of incorporating metadata in re-identification.

Yuzhuo Li, Di Zhao, Tingrui Qiao +3

School of Computer Science, University of Auckland Auckland, New Zealand

Animal Re-Identification

Sep 27, 2026cs.LG

Diffusion-Based Rollouts as a Stabilization Mechanism for Long-Horizon Environmental Forecasting

Extending forecast lead times while maintaining predictive skill remains a major challenge in environmental forecasting. We investigate diffusion-based rollouts as a stabilization mechanism for recursive forecasting using low-dimensional water-level time series and high-dimensional precipitation fields. Across both modalities, diffusion suppresses recursive error growth, with the largest stabilization occurring where deterministic rollouts are most unstable. However, stabilization does not guarantee forecast fidelity. In the water-level experiments, forecasts progressively lose event-level fidelity as the rollout loses access to external predictive information, and trajectory-level comparisons show that diffusion can remain numerically stable while contracting toward central values and exhibiting reduced variability. In the precipitation experiments, which retain conditioning from numerical weather prediction throughout the rollout, diffusion better preserves spatial organization and event-detection skill. Together, these contrasting experiments indicate that diffusion can control recursive error amplification, while its practical benefit also depends on the predictive information available to constrain future evolution.

Marina Vicens-Miquel, Amy McGovern, Aaron J. Hill +2

University of Oklahoma, School of Meteorology, Norman, Oklahoma · University of Oklahoma, School of Computer Science, Norman, Oklahoma · NSF AI Institute for Research on Trustworthy AI in Weather, Climate, and Coastal Oceanography, Norman, Oklahoma +2

Long-Horizon Forecasting

Sep 22, 2026cs.RO

Zephyron: Integrated Design and Analytical Evaluation of a Solar-Assisted Mobile Manipulator for Multimodal Environmental Reconnaissance and Distributed Visual Inference

Environmental reconnaissance needs mobile platforms that carry sensors, preserve measurement context, and return interpretable evidence under limited energy and communication. We present a literature-informed engineering design for Zephyron, a four-wheel rover with a front manipulator, environmental sensors, distributed computer vision, local recording, and a raised rear solar module. The design keeps the prototype layout but replaces unsupported numerical assumptions with an explicit component and geometry baseline. A reproducible search retrieved 5,000 records (4,858 unique) for screening, followed by targeted review of primary literature and manufacturer documentation. The baseline uses 165 mm wheels, a 12 kg mass budget, a 72 Wh battery-energy basis, and a 20 W photovoltaic module. With rolling-resistance coefficient 0.04, steady ascent of a 10 degree grade needs about 0.517 N m per wheel under equal load sharing. An illustrative 40 W motion load gives 1.44 h from 57.6 Wh usable energy, and a 25 percent driving duty gives 4.19 h without solar input; these are calculated scenarios, not measured performance. Sensor models show how integration time, calibration, temperature, and communication delay constrain interpretation, and a quality-aware stop-and-sample policy links these constraints to mission execution. Lightweight detectors, reference-based sensor learning, and executable data-integrity checks define a reproducible machine-learning evaluation pathway. The contribution is a traceable design and evaluation framework with editable 3D models, subsystem diagrams, and reproducible analytical data. Experimental validation is required before assigning payload, endurance, detection, or field-operating ratings.

Sabik Bin Sultan, Shafi Bin Sultan, Safwan Sadad

Bangladesh Air Force Shaheen College Kurmitola · St.Joseph Higher Secondary School · Greenland Residential School

Topic pending

Sep 17, 2026cs.CV

Compact Vision Models for Iris Presentation Attack Detection under Presentation Attack Instrument Shift and Environmental Degradation

Iris presentation attack detection (PAD) is security-critical when a subsystem that appears reliable during development encounters presentation attack instruments (PAIs) or acquisition conditions absent from validation data. We benchmark three compact scratch-trained computer-vision models, each with at most approximately 0.26 million trainable parameters, on the Notre Dame subset of LivDet-Iris 2017 under PAI-driven domain shift and environmental degradation. All models are trained without external pretraining or data augmentation and evaluated over five seeds. A validation-selected threshold is transferred unchanged to the known-attack, unknown-attack, corrupted, and pooled test partitions. From known to unknown attack presentations, Attack Presentation Classification Error Rate (APCER) increases by 17.11-30.47 percentage points and Detection Equal Error Rate (D-EER) increases by 7.38-12.73 percentage points. At the validation-selected threshold, ZACH-ViT obtains the lowest unknown-attack APCER (47.69 +/- 4.84%) and D-EER (38.87 +/- 0.93%), while Compact-TransMIL obtains the lowest Bona Fide Presentation Classification Error Rate (BPCER). ZACH-ViT also gives the lowest unknown-attack BPCER at an APCER limit of 10% (81.29 +/- 1.95%). The high absolute errors show that the comparative advantage of the best compact model does not constitute deployment readiness under unknown PAIs.

Athanasios Angelakis, Marta Gomez-Barrero

BioML Lab, RI CODE, UniBw, Munich, Germany

Adversarial Examples Vision Foundation Models Cross-Domain Shifts Environment

Sep 16, 2026cs.RO

A3P5 NEMESIS Integrated Rover Design for Environmental Reconnaissance and Robotic Sampling with Reproducible Mobility Analysis and an External Data Machine Learning Calibration Benchmark

A3P5 NEMESIS is a four-wheel rover intended to combine remote inspection, environmental observation and lightweight manipulation within one serviceable platform. This study develops a photo-constrained geometric reconstruction, a subsystem architecture and a reproducible analytical assessment while distinguishing physical prototype evidence from proposed functions. An exploratory search retrieved 5,000 bibliographic records across ten queries, yielding 4,897 distinct DOI records and 1,212 metadata candidates; selected primary studies and technical documents informed the design. The reconstructed configuration retains the carbon-pattern enclosure, independently steered wheel assemblies, folded manipulator, inclined camera mast and side sampling equipment. A declared 24 kg scenario predicts 3.28 newton-metres of gearbox-output torque per wheel on a 20-degree grade under equal load sharing; a separate static model shows how a 2 kg forward payload reduces the geometric front-tipping bound from 38.1 degrees to 32.7 degrees. These are design screens, not measured operating limits. A public-data calibration benchmark uses 7,344 eligible hourly observations, eight sensor/environmental predictors and chronological training, validation and test partitions. Validation-selected ridge regression achieves a held-out CO root-mean-square error of 0.502 milligrams per cubic metre, with a 95% daily-block bootstrap interval of 0.435-0.569 milligrams per cubic metre. This result concerns an external sensor array and cannot establish NEMESIS accuracy. The combined analysis identifies priority measurements, proposed control interfaces and mission-specific validation requirements. The contribution is a traceable engineering design study and evaluation framework for a prototype whose integrated field performance remains to be established.

Shafi Bin Sultan, Sabik Bin Sultan, Safwan Sadad

St. Joseph Higher Secondary School · BAF Shaheen College Kurmitola · Greenland Residential School

Autonomous Surface Vehicles Ground Reaction Forces Geometric Reconstruction Mobility Machine Learning

Sep 15, 2026cs.CL

Quantifying Organizational Environmental Action from Web Data and Large Language Models

Quantifying organizational environmental action from publicly available web content remains a challenging environmental data science problem because relevant information can be dispersed across multiple webpages and is primarily communicated through unstructured text. We present a scalable computational framework for transforming organizational web content into structured measures of environmental action and demonstrate the approach using Jewish congregations in the United States. We constructed a national database of 4,964 congregations by integrating multiple geospatial, knowledge-base, directory, and manually reviewed sources. Of these, 2,657 had active websites that were successfully crawled, producing a corpus of 154,454 webpages. We compared three approaches for detecting environmental actions: keyword retrieval followed by large language model (LLM) classification, semantic vector retrieval followed by LLM classification, and direct LLM classification classification without preliminary retrieval. Agreement with an expert human reviewer was lowest for keyword retrieval (

κ

= 0.26), higher for semantic vector retrieval (

κ

= 0.42), and similar for direct LLM classification (

κ

= 0.40). Although semantic retrieval achieved the highest agreement, its retrieval recall was 0.87, indicating loss of relevant content before classification. Applied to the complete corpus, direct LLM classification identified at least one environmental action at 1,398 congregations (53%), providing greater coverage than either retrieval-based approach. These results demonstrate that preliminary retrieval can reduce computational cost but may exclude relevant information before it reaches the classifier. The framework provides a reproducible approach for extracting organization-level environmental information from unstructured web content that can be adapted to other institutions.

Quinn Reynolds, Daniel Shore, Vianey Leos Barajas +2

Department of Statistical Sciences, University of Toronto · School of the Environment, University of Toronto

Online Data Selection Organizational Scale Sustainability Text Corpora Environment

Sep 14, 2026cs.PF

The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices

The rapid diffusion of generative artificial intelligence raises privacy, latency, and performance concerns that motivate a shift toward "local-first" AI, where inferences are performed on the user's device instead of on remote cloud servers. This paradigm also places a significant computational load on battery-powered smartphones, potentially shortening battery life and increasing the overall replacement rate of mobile devices. This paper presents a systematic study of the energy consumption, performance, and accuracy of on-device large language model (LLM) inference. We evaluate 18 models from different model families, sizes, and quantization levels, on two modern smartphones and on a server, using the respective state-of-the-art for such deployments. We measure the energy per generated token, inter-token latency, model accuracy, and battery-cycle consumption. Our results show that (i) on-device inference is on average 3 times less energy-efficient than batched server inference; (ii) the relationship between quantization bit-width and energy per token is non-monotonic, with energy sweet spots on both tested smartphones; (iii) eight out of 18 model configurations lie on the Pareto front of accuracy and energy-efficiency, allowing practitioners to build battery-aware model routers; and (iv) realistic modeling assumptions do not allow local inference to be less environmentally impacting per token than batched server inference, with 88--90% of that impact attributable to device embodied carbon rather than electricity consumption. These findings challenge the premise that local AI is more sustainable than cloud inference, and motivate the need for context-aware and life-cycle-aware model selection when deploying edge AI on battery-powered mobile platforms.

Édouard Guégain, Tristan Coignion

DRI, GREENSPECTOR · Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, Talence, France

LLM Inference Efficiency Artificial Intelligence Systems Device Generative Artificial Intelligence Environment Prices

Sep 12, 2026cs.CY

Buyer Artificial Intelligence-Enabled Environmental Governance and Supplier Environmental Controversies: An Organizational Information Processing and Signaling

Environmental controversies in global supply chains pose significant risks for global buyers. This study examines whether overseas suppliers' exposure to buyers' artificial intelligence (AI)-enabled environmental governance reduces supplier environmental controversies. Drawing on organizational information processing theory and signaling theory, we investigate how suppliers' exposure to AI-enabled governance influences their environmental controversies and the institutional contingencies under which this effect varies. Using text analysis to measure buyer AI-enabled environmental governance, we analyze panel data on 2,505 suppliers of U.S.-listed firms across 41 countries from 2020 to 2024 with multidimensional fixed-effects models. We find that suppliers' exposure to buyer AI-enabled environmental governance is negatively associated with supplier environmental controversies in the following year. This negative relationship is stronger in supplier countries with higher AI readiness and regulatory quality. The study contributes to research on AI-enabled sustainability governance and sustainable supply chain risk management.

Yongchao Martin Ma, Xinya Guan

School of Management Huazhong University of Science & Technology, PR China · School of Economics and Management Harbin Engineering University Harbin, PR China

Artificial Intelligence Governance Supply Chain Optimization Sustainability Environment Logistic Regression

Sep 1, 2026cs.CV

Agentic Multimodal Models for Environmental Hyperspectral Unmixing

Hyperspectral unmixing is a key task in remote sensing that aims to decompose mixed pixels in hyperspectral images into their constituent material signatures, or endmembers, and their fractional abundances. Conventional modular approaches estimate the scene composition through successive model-order estimation, endmember extraction, and abundance estimation stages, whose errors can lead to redundant or ambiguous candidate components and ultimately affect the recovered decomposition. We introduce an algorithm-agnostic, large vision-language model (LVLM)-driven agentic framework that refines the outputs of such pipelines rather than replacing their underlying numerical algorithms. Starting from an initial decomposition, the agent iteratively gathers complementary spectral and spatial evidence through dedicated tools, including spectral-library retrieval and abundance-map visualization, and modifies the active endmember set through merge and discard operations followed by abundance re-estimation. We apply the same refinement procedure to several modular pipelines combining different model-order, extraction, and abundance-estimation methods, and evaluate it on HYDICE Urban, Jasper Ridge, and Stonewall Playa. Experiments show that the proposed agent consistently improves endmember cardinality and generally improves the recovered spectral signatures and abundance maps across heterogeneous modular pipelines, while remaining competitive with integrated end-to-end unmixing methods, including CNN-AE, uDAS, and R-CoNMF. These results highlight the potential of tool-using LVLM agents to combine spectral and spatial evidence for algorithm-agnostic refinement of physically grounded hyperspectral unmixing decompositions. Code is publicly available at https://anonymous.4open.science/r/agentic-hu.

Michał Cholewa, Luca Ciampi, Nicola Messina +2

IITiS-PAS, Gliwice, Poland · ISTI-CNR, Pisa, Italy

Hyperspectral Unmixing Multimodal Agents Modular Agentic Framework

Aug 12, 2026cs.CY

Quantifying the Relationship Between Clinical Safety and Environmental Impact in Therapeutic LLMs

The deployment of large language models (LLMs) in mental health contexts raises questions about the relationship between clinical safety and environmental cost. In this paper, we examine this relationship by combining K-Bench clinical safety scores with EcoLogits life-cycle assessment estimates across 47 supported model configurations. We evaluate model performance and environmental impact across four dimensions: energy use, carbon emissions, water consumption, and abiotic depletion. The results indicate a non-linear trade-off at the upper end of the safety distribution: a 2.61 percentage-point increase in clinical safety score corresponded to an approximately 60-fold increase in estimated energy use per million output tokens. Row-level analyses further suggest that additional test-time compute did not consistently improve clinical safety and, in some configurations, was associated with lower clinical safety scores. These findings suggest that relying solely on larger models or additional inference-time computation may be an inefficient strategy for improving safety in therapeutic AI systems. We discuss the implications for sustainable deployment and highlight dynamic model selection, including model cascading, as a potential approach for reducing environmental impact while preserving clinical performance in higher-risk cases.

Alireza A. Safaei, Laura M. Vowels, Matthew J. Vowels +2

University of Isfahan Isfahan, Iran · University of Roehampton London, UK · Kivira Health New York City, New York, U.S.A.

Large Language Model Safety Environment Quantifying

Aug 3, 2026cs.CV

UAV-Based Environmental Monitoring of Rip-Current Indicators Using Wavelet-Derived Texture Features

Rip currents are recurrent coastal natural hazards that threaten beachgoers and create operational challenges for lifeguards and coastal managers. Reliable monitoring from standard RGB (red-green-blue) imagery acquired by unmanned aerial vehicles (UAVs) remains difficult because hazardous channels often appear as subtle gaps in breaking waves, foam texture, or sediment patterns, and these signatures are affected by illumination, sea state, and environmental noise. This study presents a physically informed coastal environmental monitoring workflow for detecting visually expressed rip-current indicators that integrates wavelet-derived spatial-frequency texture features with deep learning. We evaluate multiple strategies for incorporating Discrete Wavelet Transform features into convolutional architectures, from computationally efficient channel replacement to dual-stream fusion with attention mechanisms. Performance is assessed against a standard RGB baseline using a task specific convolutional neural network for image-level presence classification and a YOLOv8 model for object-level localization. Under the evaluated dataset conditions, integrating wavelet derived texture features improves performance over RGB-only models. The dual-stream architecture achieves the strongest classification performance, exceeding 95% accuracy with high recall, while channel replacement is most effective for YOLOv8 object detection, reaching 94% mAP@50 for localization. Explainable artificial intelligence analyses provide qualitative evidence that the models attend to visually plausible wave-gap regions associated with rip currents. These results suggest that under the conditions of the evaluated dataset, physically informed wavelet integration may support UAV-based decision-support tools for interpretable beach-safety risk mitigation.

Yonatan Ben Avraham, Baruch Binyaminov, Yehudit Aperstein

1Intelligent Systems, Afeka Academic College of Engineering, Tel Aviv 6998812, Israel

Discrete Wavelet Transform Unmanned Aerial Vehicles

Jul 31, 2026cs.LG

AutoCause: A Python framework that automates expert decisions in environmental time-series causal discovery

Environmental time-series causal discovery requires expert decisions about method choice, conditional-independence tests, lag horizons, sample-size adequacy, multiple-testing control, and evidence interpretation. Applied inconsistently across datasets, these choices yield graphs that cannot be compared, reproduced, or audited. We present AutoCause, an open-source Python workflow that records each decision, derives defaults from an extended causal-audit module, and admits domain-informed overrides. The workflow wraps four established causal-discovery methods from three families, adds non-causal reference models, and grades links by method-count support. On 145 datasets from DGP-Atlas, TimeGraph, and a topology-derived CausalRivers reference, the methods recover complementary parts of the reference graphs. Majority-supported links are more precise than single-method links on the synthetic benchmarks but not against river topology. AutoCause converts inconsistent expert practice into an auditable, repeatable analysis; causal interpretation remains with the analyst. Available at https://github.com/marcoruizrueda/autocause.

Marco Ruiz, Miguel Arana-Catania, David R. Ardila +1

ISR-Lisbon, Instituto Superior Técnico, Av. Rovisco Pais 1, Lisbon, 1049-001, Portugal · Digital Scholarship at Oxford, University of Oxford, Oxford, OX1 3BG, United Kingdom · Jet Propulsion Lab., Caltech, Pasadena, CA 91109, California, USA

Causal Foundation Models Causal Reasoning Reproducibility Algorithm Auditing Expert Demonstrations