Text-to-3D scene generation from natural language is highly desirable for digital content creation. However, existing methods are largely domain-restricted or reliant on predefined spatial relationships, limiting their capacity for unconstrained, open-vocabulary 3D scene synthesis. In this paper, we introduce SceneAssistant, a visual-feedback-driven agent designed for open-vocabulary 3D scene generation. Our framework leverages modern 3D object generation model along with the spatial reasoning and planning capabilities of Vision-Language Models (VLMs). To enable open-vocabulary scene composition, we provide the VLMs with a comprehensive set of atomic operations (e.g., Scale, Rotate, FocusOn). At each interaction step, the VLM receives rendered visual feedback and takes actions accordingly, iteratively refining the scene to achieve more coherent spatial arrangements and better alignment with the input text. Experimental results demonstrate that our method can generate diverse, open-vocabulary, and high-quality 3D scenes. Both qualitative analysis and quantitative human evaluations demonstrate the superiority of our approach over existing methods. Furthermore, our method allows users to instruct the agent to edit existing scenes based on natural language commands. Our code is available at https://github.com/ROUJINN/SceneAssistant
Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to planning and contain information irrelevant -- or even detrimental -- to planning. Inspired by the perceptual straightening hypothesis in human visual processing, we introduce temporal straightening to improve representation learning for latent planning. Using a curvature regularizer that encourages locally straightened latent trajectories, we jointly learn an encoder and a predictor. We show that reducing curvature this way makes the Euclidean distance in latent space a better proxy for the geodesic distance and improves the conditioning of the planning objective. We demonstrate empirically that temporal straightening makes gradient-based planning more stable and yields significantly higher success rates across a suite of goal-reaching tasks.
This work pursues automated planning and scheduling of distributed data pipelines, or workflows. We develop a general workflow and resource graph representation that includes both data processing and sharing components with corresponding network interfaces for scheduling. Leveraging these graphs, we introduce WORKSWORLD, a new domain for numeric domain-independent planners designed for permanently scheduled workflows, like ingest pipelines. Our framework permits users to define data sources, available workflow components, and desired data destinations and formats without explicitly declaring the entire workflow graph as a goal. The planner solves a joint planning and scheduling problem, producing a plan that both builds the workflow graph and schedules its components on the resource graph. We empirically show that a state-of-the-art numeric planner running on commodity hardware with one hour of CPU time and 30GB of memory can solve linear-chain workflows of up to 14 components across eight sites.
Applications like Enterprise Resource Planning (ERP) systems have become an indispensable part of the corporate digital infrastructure. These systems store sensitive data about customers, suppliers, and employees, and thus companies have to process these data in accordance with applicable regulations like the GDPR (the EU General Data Protection Regulation). This can be challenging due to a variety of reasons. For example, prior research has shown that developers sometimes lack knowledge about privacy. In this work, we focus on privacy in ERP systems in the context of an international consultancy firm. We investigate the privacy awareness regarding privacy-by-design and data minimization of two important populations: developers of ERP systems and managers and consultants responsible for services related to ERP systems. Applying thematic analysis, we elicit privacy behavioral models of these two populations using Fogg's Behavioral Model (FBM) framework. Our findings provide a means to stimulate more adequate privacy-related behaviors for developers and consultants.
Since the introduction of the PDDL+ modeling language, it was known that temporal planning with durative actions (as in PDDL 2.1) could be compiled into PDDL+. However, no practical compilation was presented in the literature ever since. We present a practical compilation from temporal planning with durative actions into PDDL+, fully capturing the semantics and only assuming the non-self-overlapping of actions. Our compilation is polynomial, retains the plan length up to a constant factor and is experimentally shown to be of practical relevance for hard temporal numeric problems.
Multimodal agents offer a promising path to automating complex document-intensive workflows. Yet, a critical question remains: do these agents demonstrate genuine strategic reasoning, or merely stochastic trial-and-error search? To address this, we introduce MADQA, a benchmark of 2,250 human-authored questions grounded in 800 heterogeneous PDF documents. Guided by Classical Test Theory, we design it to maximize discriminative power across varying levels of agentic abilities. To evaluate agentic behaviour, we introduce a novel evaluation protocol measuring the accuracy-effort trade-off. Using this framework, we show that while the best agents can match human searchers in raw accuracy, they succeed on largely different questions and rely on brute-force search to compensate for weak strategic planning. They fail to close the nearly 20% gap to oracle performance, persisting in unproductive loops. We release the dataset and evaluation harness to help facilitate the transition from brute-force retrieval to calibrated, efficient reasoning.
Multimodal Large Language Models (MLLMs) have demonstrated remarkable video reasoning capabilities across diverse tasks. However, their ability to understand human intent at a fine-grained level in egocentric videos remains largely unexplored. Existing benchmarks focus primarily on episode-level intent reasoning, overlooking the finer granularity of step-level intent understanding. Yet applications such as intelligent assistants, robotic imitation learning, and augmented reality guidance require understanding not only what a person is doing at each step, but also why and what comes next, in order to provide timely and context-aware support. To this end, we introduce EgoIntent, a step-level intent understanding benchmark for egocentric videos. It comprises 3,014 steps spanning 15 diverse indoor and outdoor daily-life scenarios, and evaluates models on three complementary dimensions: local intent (What), global intent (Why), and next-step plan (Next). Crucially, each clip is truncated immediately before the key outcome of the queried step (e.g., contact or grasp) occurs and contains no frames from subsequent steps, preventing future-frame leakage and enabling a clean evaluation of anticipatory step understanding and next-step planning. We evaluate 15 MLLMs, including both state-of-the-art closed-source and open-source models. Even the best-performing model achieves an average score of only 33.31 across the three intent dimensions, underscoring that step-level intent understanding in egocentric videos remains a highly challenging problem that calls for further investigation.
The `15-minute city' has emerged as a central paradigm in urban planning, promoting universal access to work and essential services within short travel times. Its feasibility-particularly for commuting to work-has however rarely been examined quantitatively. Here, we show that proximity to employment is fundamentally constrained by the internal structure of urban economies. Combining urban geometry with empirically observed firm-size distributions, we derive a lower bound on commuting times that holds independently of planning choices or transport technologies. This bound reveals a sharp transition: when employment is sufficiently concentrated, no spatial rearrangement of workplaces can ensure uniformly short commutes, even under optimal placement. Applied to Paris and its near suburbs, we find that achieving universal 15-minute commutes would require substantial economic restructuring or differentiated mobility strategies. The relevant question is therefore not whether an $x$-minute city is achievable, but what the minimal feasible $x$ is given a city's economic structure and spatial scale.
Genetic analyses indicate minimal gene flow across the so-called Eastern Pacific Barrier (EPB) in larvae of the reef-building coral \emph{Porites lobata}. Notably, Clipperton Atoll, situated on the eastern side of the EPB, is the only site that exhibits detectable genetic connectivity with the Line Islands, which lie to the west of the EPB. To elucidate the relationship between this genetic signal and large-scale Pacific Ocean circulation, we analyze historical trajectories of surface-drifting buoys from the Global Drifter Program (GDP). We first discretize the GDP drifter trajectories into a Markov chain representation and subsequently apply transition path theory (TPT) in combination with Bayesian inference. The TPT analysis identifies reactive trajectories -- pathways that connect the Line Islands to Clipperton Atoll with minimal detours -- whose travel times do not exceed 5 months, which is taken as an upper bound for the larval survival time of \emph{P. lobata}. Consistently, the posterior distribution of transport from Pacific islands west of the EPB to Clipperton Atoll attains a local maximum in the Line Islands at a travel time of approximately 2.5 months. Our probabilistic characterization of the Lagrangian dynamics therefore supports a scenario of weak, but non-negligible, permeability of the EPB, in agreement with the genetic evidence, and it motivates a refined dynamical definition of the EPB based on the remaining duration of reactive trajectories. Furthermore, our results indicate that the connectivity between the Line Islands and Clipperton Atoll is governed primarily by the seasonal modulation of the North Equatorial Countercurrent, rather than by the phase of the El Niño--Southern Oscillation (ENSO). Finally, Clipperton Atoll's role as a terminal sink for trajectories is relevant to the planned mining operations.
Multimodal agents can now tackle complex reasoning tasks with diverse tools, yet they still suffer from inefficient tool use and inflexible orchestration in open-ended settings. A central challenge is enabling such agents to continually improve without parameter updates by learning from past trajectories. We identify two complementary forms of reusable knowledge essential for this goal: experiences, providing concise action-level guidance for tool selection and decision making, and skills, providing structured task-level guidance for planning and tool use. To this end, we propose XSkill, a dual-stream framework for continual learning from experience and skills in multimodal agents. XSkill grounds both knowledge extraction and retrieval in visual observations. During accumulation, XSkill distills and consolidates experiences and skills from multi-path rollouts via visually grounded summarization and cross-rollout critique. During inference, it retrieves and adapts this knowledge to the current visual context and feeds usage history back into accumulation to form a continual learning loop. Evaluated on five benchmarks across diverse domains with four backbone models, XSkill consistently and substantially outperforms both tool-only and learning-based baselines. Further analysis reveals that the two knowledge streams play complementary roles in influencing the reasoning behaviors of agents and show superior zero-shot generalization.
We describe the dynamical, photometric, and spectroscopic data available for stars targeted by Spitzer and Herschel to search for cold circumstellar dust emission from debris disks, a collection that we name the Cold Debris Disk Surveys (CDDS). These data include Hipparcos and Gaia parallaxes, 0.4-1250 micron photometry, spectral types, effective temperatures, gravities, bolometric luminosities, visual extinctions, metallicities, lithium abundances, rotational periods, projected rotational velocities, the Ca~II HK and IR triplet activity indicators, and X-ray luminosities for 3675 stars. Within this sample, we investigate the frequency of stellar and planetary companions (including potential new proper motion companions); use the data to assign CDDS stars to the field or one of many moving groups, open clusters, or stellar associations; and investigate correlations between stellar activity indicators. In future papers, we plan to explore the magnitude and frequency of infrared excess emission as a function of host star properties; to search for new companions with Gaia; and to examine the evolution of infrared excesses with the ages of stars in clusters and the field.
Artificial intelligence is increasingly catalyzing scientific automation, with multimodal large language model (MLLM) agents evolving from lab assistants into self-driving lab operators. This transition imposes stringent safety requirements on laboratory environments, where fragile glassware, hazardous substances, and high-precision laboratory equipment render planning errors or misinterpreted risks potentially irreversible. However, the safety awareness and decision-making reliability of embodied agents in such high-stakes settings remain insufficiently defined and evaluated. To bridge this gap, we introduce LABSHIELD, a realistic multi-view benchmark designed to assess MLLMs in hazard identification and safety-critical reasoning. Grounded in U.S. Occupational Safety and Health Administration (OSHA) standards and the Globally Harmonized System (GHS), LABSHIELD establishes a rigorous safety taxonomy spanning 164 operational tasks with diverse manipulation complexities and risk profiles. We evaluate 20 proprietary models, 9 open-source models, and 3 embodied models under a dual-track evaluation framework. Our results reveal a systematic gap between general-domain MCQ accuracy and Semi-open QA safety performance, with models exhibiting an average drop of 32.0% in professional laboratory scenarios, particularly in hazard interpretation and safety-aware planning. These findings underscore the urgent necessity for safety-centric reasoning frameworks to ensure reliable autonomous scientific experimentation in embodied laboratory contexts. The full dataset will be released soon.
Image-based surface reconstruction and characterization are crucial for missions to small celestial bodies (e.g., asteroids), as it informs mission planning, navigation, and scientific analysis. Recent advances in Gaussian splatting enable high-fidelity neural scene representations but typically rely on a spherical harmonic intensity parameterization that is strictly appearance-based and does not explicitly model material properties or light-surface interactions. We introduce AstroSplat, a physics-based Gaussian splatting framework that integrates planetary reflectance models to improve the autonomous reconstruction and photometric characterization of small-body surfaces from in-situ imagery. The proposed framework is validated on real imagery taken by NASA's Dawn mission, where we demonstrate superior rendering performance and surface reconstruction accuracy compared to the typical spherical harmonic parameterization.
Energy management is a fundamental challenge for legged robots in outdoor environments. Endurance directly constrains mission success, while efficient resource use reduces ecological impact. This paper investigates how terrain slope and heading orientation influence the energetic cost of quadruped locomotion. We introduce a simple energy model that relies solely on standard onboard sensors, avoids specialized instrumentation, and remains applicable in previously unexplored environments. The model is identified from field runs on a commercial quadruped and expressed as a compact function of slope angle and heading. Field validation on natural terrain shows near-linear trends of force-equivalent cost with slope angle, consistently higher lateral costs, and additive behavior across trajectory segments, supporting path-level energy prediction for planning-oriented evaluation.
High-voltage direct current (HVDC) technology has played a crucial role for long-distance transmission of renewable power generation. However, the integration of large-capacity HVDC lines introduces significant frequency security challenges during HVDC fault emergencies. This paper proposes an emergency-aware and frequency-constrained HVDC planning method to optimize the capacity of inter-area HVDC tie-lines in a multi-area asynchronously interconnected grid. Firstly, a coordinated emergency frequency control scheme is proposed to allocate the emergency control resources during HVDC faults. Then, an enhanced system frequency response model integrating event-driven emergency frequency control is developed and a weighted oblique decision tree approach is employed to extract frequency nadir security constraints. The proposed planning model considers all potential HVDC fault emergencies while treating candidate HVDC capacities as decision variables. Simulation results demonstrate superior performance in balancing economic efficiency with frequency security requirements, providing a practical solution for inter-area HVDC planning.
This article describes a collaborative learning experience on Software Architecture (SA) between Universidad del Cauca (UNICAUCA) in Colombia and Universidad Nacional de la Plata (UNPL) in Argentina. The goal was to apply and evaluate training patterns, identifying effective practices for replication in other contexts. During the planning phase, both universities compared learning objectives, curricula, and teaching strategies to find common ground for improving student training. Selected training patterns were implemented, and their impact on professors and students was measured. As an integrating activity, a global development experience was carried out in the final part of the course, merging the work teams of the two educational institutions in a development iteration. The evaluation of this experience focused on the competencies achieved through the training patterns, their perceived usefulness, and ease of use based on the Technology Acceptance Model (TAM). The training addressed industry needs for software architecture design skills despite challenges such as the abstract nature of architectures, prerequisite knowledge, difficulty in recreating realistic project environments, team collaboration challenges, and resource limitations. A catalog of training patterns was proposed to provide quality training. These patterns help simulate industry-like environments and structure architectural knowledge for incremental learning. The ability to make architectural decisions is developed over time and through multiple project experiences, emphasizing the need for practical, well-structured training programs.
Inspection and maintenance (I&M) planning involves sequential decision making under uncertainties and incomplete information, and can be modeled as a partially observable Markov decision process (POMDP). While single-agent deep reinforcement learning provides approximate solutions to POMDPs, it does not scale well in multi-component systems. Scalability can be achieved through multi-agent deep reinforcement learning (MADRL), which decentralizes decision-making across multiple agents, locally controlling individual components. However, this decentralization can induce cooperation pathologies that degrade the optimality of the learned policies. To examine these effects in I&M planning, we introduce a set of deteriorating systems in which redundancy is varied systematically. These benchmark environments are designed such that computation of centralized (near-)optimal policies remains tractable, enabling direct comparison of solution methods. We implement and benchmark a broad set of MADRL algorithms spanning fully centralized and decentralized training paradigms, from value-factorization to actor-critic methods. Our results show a clear effect of redundancy on coordination: MADRL algorithms achieve near-optimal performance in series-like settings, whereas increasing redundancy amplifies coordination challenges and can lead to optimality losses. Nonetheless, decentralized agents learn structured policies that consistently outperform optimized heuristic baselines, highlighting both the promise and current limitations of decentralized learning for scalable maintenance planning.
While deep learning has advanced single-image deraining, existing models suffer from a fundamental limitation: they employ a static inference paradigm that fails to adapt to the complex, coupled degradations (e.g., noise artifacts, blur, and color deviation) of real-world rain. Consequently, restored images often exhibit residual artifacts and inconsistent perceptual quality. In this work, we present Derain-Agent, a plug-and-play refinement framework that transitions deraining from static processing to dynamic, agent-based restoration. Derain-Agent equips a base deraining model with two core capabilities: 1) a Planning Network that intelligently schedules an optimal sequence of restoration tools for each instance, and 2) a Strength Modulation mechanism that applies these tools with spatially adaptive intensity. This design enables precise, region-specific correction of residual errors without the prohibitive cost of iterative search. Our method demonstrates strong generalization, consistently boosting the performance of state-of-the-art deraining models on both synthetic and real-world benchmarks.
Radiated power information is crucial to diagnose and optimize the performance of fusion plasmas. Traditionally, at the TCV tokamak, radiated power analysis has only ever been possible following plasma discharge termination. However, recently, TCV bolometer data have become available in real-time. This offers the opportunity of integrating the radiated power information into the TCV plasma control system. In this work, we propose a novel real-time tomography-based Bayesian technique allowing estimation of the power radiated from user-defined regions of interest in the plasma. The real-time estimates are obtained as computationally cheap linear combinations of bolometer measurements, using pre-computed coefficients that are optimized for the specific discharge planned. This method is not, thus, trained on a set of synthetic or tomographically reconstructed emissivity profiles. We detail the derivation of the technique and show its equivalence to traditional tomographic estimates under suitable conditions. We then demonstrate that this technique enables accurate real-time estimation of the total, core, divertor and main chamber radiated power, by its application to a representative and heterogeneous set of TCV discharges. Finally, we discuss the robustness of the technique to faulty detectors, showing that simple precautions allow safe handling of many common issues. The computational routines implementing the described technique are provided as open-source code.
The acquisition of large-scale physical interaction data, a critical prerequisite for modern robot learning, is severely bottlenecked by the prohibitive cost and scalability limits of human-in-the-loop collection paradigms. To break this barrier, we introduce Robust Autonomous Data Acquisition for Robotics (RADAR), a fully autonomous, closed-loop data generation engine that completely removes human intervention from the collection cycle. RADAR elegantly divides the cognitive load into a four-module pipeline. Anchored by 2-5 3D human demonstrations as geometric priors, a Vision-Language Model first orchestrates scene-relevant task generation via precise semantic object grounding and skill retrieval. Next, a Graph Neural Network policy translates these subtasks into physical actions via in-context imitation learning. Following execution, the VLM performs automated success evaluation using a structured Visual Question Answering pipeline. Finally, to shatter the bottleneck of manual resets, a Finite State Machine orchestrates an autonomous environment reset and asymmetric data routing mechanism. Driven by simultaneous forward-reverse planning with a strict Last-In, First-Out causal sequence, the system seamlessly restores unstructured workspaces and robustly recovers from execution failures. This continuous brain-cerebellum synergy transforms data collection into a self-sustaining process. Extensive evaluations highlight RADAR's exceptional versatility. In simulation, our framework achieves up to 90% success rates on complex, long-horizon tasks, effortlessly solving challenges where traditional baselines plummet to near-zero performance. In real-world deployments, the system reliably executes diverse, contact-rich skills (e.g., deformable object manipulation) via few-shot adaptation without domain-specific fine-tuning, providing a highly scalable paradigm for robotic data acquisition.
We present TANGO (Tensor ANd Graph Optimization), a novel motion planning framework that integrates tensor-based compression with structured graph optimization to enable efficient and scalable trajectory generation. While optimization-based planners such as the Graph of Convex Sets (GCS) offer powerful tools for generating smooth, optimal trajectories, they typically rely on a predefined convex characterization of the high-dimensional configuration space-a requirement that is often intractable for general robotic tasks. TANGO builds further by using Tensor Train decomposition to approximate the feasible configuration space in a compressed form, enabling rapid discovery and estimation of task-relevant regions. These regions are then embedded into a GCS-like structure, allowing for geometry-aware motion planning that respects both system constraints and environmental complexity. By coupling tensor-based compression with structured graph reasoning, TANGO enables efficient, geometry-aware motion planning and lays the groundwork for more expressive and scalable representations of configuration space in future robotic systems. Rigorous simulation studies on planar and real robots reinforce our claims of effective compression and higher quality trajectories.
Architectural floor plan design demands joint reasoning over geometry, semantics, and spatial hierarchy, which remains a major challenge for current AI systems. Although recent diffusion and language models improve visual fidelity, they still struggle with coherent spatial reasoning and controllable generation. We present HouseMind, a multimodal large language model that unifies floor plan understanding, generation, and editing in one framework. We introduce discrete room-instance tokens to construct a unified vocabulary that bridges layouts and symbolic reasoning. With multimodal alignment and instruction tuning, the model synthesizes coherent, controllable layouts from text instructions. Experiments show how the framework achieves superior geometric validity and controllability while remaining efficient and locally deployable.
Semantic correspondence is essential for handling diverse in-the-wild images lacking explicit correspondence annotations. While recent 2D foundation models offer powerful features, adapting them for unsupervised learning via nearest-neighbor pseudo-labels has key limitations: it operates locally, ignoring structural relationships, and consequently its reliance on 2D appearance fails to resolve geometric ambiguities arising from symmetries or repetitive features. In this work, we address this by reformulating pseudo-label generation as a Fused Gromov-Wasserstein (FGW) problem, which jointly optimizes inter-feature similarity and intra-structural consistency. Our framework, Shape-of-You (SoY), leverages a 3D foundation model to define this intra-structure in the geometric space, resolving abovementioned ambiguity. However, since FGW is a computationally prohibitive quadratic problem, we approximate it through anchor-based linearization. The resulting probabilistic transport plan provides a structurally consistent but noisy supervisory signal. Thus, we introduce a soft-target loss dynamically blending guidance from this plan with network predictions to build a learning framework robust to this noise. SoY achieves state-of-the-art performance on SPair-71k and AP-10k datasets, establishing a new benchmark in semantic correspondence without explicit geometric annotations. Code is available at Shape-of-You.
Embodied task planning demands vision-language models to generate action sequences that are both visually grounded and causally coherent over time. However, existing training paradigms face a critical trade-off: joint end-to-end training often leads to premature temporal binding, while standard reinforcement learning methods suffer from optimization instability. To bridge this gap, we present Staged Vision-Language Learning (SVLL), a unified three-stage framework for robust, physically-grounded embodied planning. In the first two stages, SVLL decouples spatial grounding from temporal reasoning, establishing robust visual dependency before introducing sequential action history. In the final stage, we identify a key limitation of standard Direct Preference Optimization (DPO), its purely relative nature -- optimizing only the preference gap between winning and losing trajectories while neglecting absolute likelihood constraints on optimal path, often yields unsafe or hallucinated behaviors. To address this, we further introduce Bias-DPO, a novel alignment objective that injects an inductive bias toward expert trajectories by explicitly maximizing likelihood on ground-truth actions while penalizing overconfident hallucinations. By anchoring the policy to the expert manifold and mitigating causal misalignment, SVLL, powered by Bias-DPO, ensures strict adherence to environmental affordances and effectively suppresses physically impossible shortcuts. Finally, extensive experiments on the interactive AI2-THOR benchmark and real-world robotic deployments demonstrate that SVLL outperforms both state-of-the-art open-source (e.g., Qwen2.5-VL-7B) and closed-source models (e.g., GPT-4o, Gemini-2.0-flash) in task success rate, while significantly reducing physical constraint violations.
Real-world robotic tasks are long-horizon and often span multiple floors, demanding rich spatial reasoning. However, existing embodied benchmarks are largely confined to single-floor in-house environments, failing to reflect the complexity of real-world tasks. We introduce MANSION, the first language-driven framework for generating building-scale, multi-floor 3D environments. Being aware of vertical structural constraints, MANSION generates realistic, navigable whole-building structures with diverse, human-friendly scenes, enabling the development and evaluation of cross-floor long-horizon tasks. Building on this framework, we release MansionWorld, a dataset of over 1,000 diverse buildings ranging from hospitals to offices, alongside a Task-Semantic Scene Editing Agent that customizes these environments using open-vocabulary commands to meet specific user needs. Benchmarking reveals that state-of-the-art agents degrade sharply in our settings, establishing MANSION as a critical testbed for the next generation of spatial reasoning and planning.
Projection mapping (PM) enables augmented reality (AR) experiences without requiring users to wear head-mounted displays and supports multi-user interaction. It is regarded as a promising technology for a variety of applications in which users interact with content superimposed onto augmented objects in tabletop workspaces, including remote collaboration, healthcare, industrial design, urban planning, artwork creation, and office work. However, conventional PM systems often suffer from projection shadows when users occlude the light path. Prior approaches employing multiple distributed projectors can compensate for occlusion, but suffer from latency due to computational processing, degrading the user experience. In this research, we introduce a synthetic-aperture PM system that uses a significantly larger number of projectors, arranged densely in the environment, to achieve delay-free, shadowless projection for tabletop workspaces without requiring computational compensation. To address spatial resolution degradation caused by subpixel misalignment among overlaid projections, we develop and validate an offline blur compensation method whose computation time remains independent of the number of projectors. Furthermore, we demonstrate that our shadowless PM plays a critical role in achieving a fundamental goal of PM: altering material properties without evoking projection-like impression. Specifically, we define this perceptual impression as ``sense of projection (SoP)'' and establish a PM design framework to minimize the SoP based on user studies.
Retrieval augmented generation RAG is widely deployed to improve factual accuracy in language models yet it remains unclear whether smaller models of size 7B parameters or less can effectively utilize retrieved information. To investigate this question we evaluate five model sizes from 360M to 8B across three architecture families SmolLM2 Qwen2.5 and Llama 3.1 under four retrieval conditions including no retrieval BM25 dense retrieval using E5 large v2 and oracle retrieval where the retrieved passage is guaranteed to contain the answer. We introduce a parametric knowledge split that separates questions a model can already answer from those that require external knowledge which allows us to isolate utilization failure from retrieval quality failure. We find three main results. First even with oracle retrieval models of size 7B or smaller fail to extract the correct answer 85 to 100 percent of the time on questions they cannot answer alone which indicates a fundamental utilization bottleneck. Second adding retrieval context destroys 42 to 100 percent of answers the model previously knew suggesting a distraction effect driven by the presence of context rather than its quality. Third an error analysis of 2588 oracle failures shows that the dominant failure mode is irrelevant generation where the model ignores the provided context entirely. These patterns hold across multiple prompt templates and retrieval methods. The results indicate that for models below 7B parameters the main limitation of RAG is context utilization rather than retrieval quality and that deploying RAG at this scale can lead to a net negative trade off under standard evaluation conditions.
Travel time is a fundamental component of accessibility measurement, yet most accessibility analyses rely on static timetable data that assume public transport services operate exactly as scheduled. Such representations overlook the substantial variability in travel times arising from operational conditions and service disruptions. In this study, we develop a scalable framework for reconstructing empirical bus timetables from high-frequency vehicle location data. Using national-scale real-time feeds from the UK Bus Open Data Service (BODS), we implement an automated data collection pipeline that continuously archives vehicle positions and daily timetable data. Observed vehicle locations are then matched to scheduled routes to infer stop-level arrival and departure times, enabling the construction of corrected empirical timetables. The resulting dataset allows travel time variability (TTV) to be analysed at fine temporal resolution and across large geographic areas. The computational efficiency and scalability of the framework enable national-scale accessibility analyses that incorporate observed service performance, providing a more realistic evidence base for evaluating public transport services and supporting transport planning.
Text-driven video generation has democratized film creation, but camera control in cinematic multi-shot scenarios remains a significant block. Implicit textual prompts lack precision, while explicit trajectory conditioning imposes prohibitive manual overhead and often triggers execution failures in current models. To overcome this bottleneck, we propose a data-centric paradigm shift, positing that aligned (Caption, Trajectory, Video) triplets form an inherent joint distribution that can connect automated plotting and precise execution. Guided by this insight, we present ShotVerse, a "Plan-then-Control" framework that decouples generation into two collaborative agents: a VLM (Vision-Language Model)-based Planner that leverages spatial priors to obtain cinematic, globally aligned trajectories from text, and a Controller that renders these trajectories into multi-shot video content via a camera adapter. Central to our approach is the construction of a data foundation: we design an automated multi-shot camera calibration pipeline aligns disjoint single-shot trajectories into a unified global coordinate system. This facilitates the curation of ShotVerse-Bench, a high-fidelity cinematic dataset with a three-track evaluation protocol that serves as the bedrock for our framework. Extensive experiments demonstrate that ShotVerse effectively bridges the gap between unreliable textual control and labor-intensive manual plotting, achieving superior cinematic aesthetics and generating multi-shot videos that are both camera-accurate and cross-shot consistent.
End-to-end autonomous driving models are typically trained on multi-city datasets using supervised ImageNet-pretrained backbones, yet their ability to generalize to unseen cities remains largely unexamined. When training and evaluation data are geographically mixed, models may implicitly rely on city-specific cues, masking failure modes that would occur under real domain shifts when generalizing to new locations. In this work we investigate zero-shot cross-city generalization in end-to-end trajectory planning and ask whether self-supervised visual representations improve transfer across cities. We conduct a comprehensive study by integrating self-supervised backbones (I-JEPA, DINOv2, and MAE) into planning frameworks. We evaluate performance under strict geographic splits on nuScenes in the open-loop setting and on NAVSIM in the closed-loop evaluation protocol. Our experiments reveal a substantial generalization gap when transferring models relying on traditional supervised backbones across cities with different road topologies and driving conventions, particularly when transferring from right-side to left-side driving environments. Self-supervised representation learning reduces this gap. In open-loop evaluation, a supervised backbone exhibits severe inflation when transferring from Boston to Singapore (L2 displacement ratio 9.77x, collision ratio 19.43x), whereas domain-specific self-supervised pretraining reduces this to 1.20x and 0.75x respectively. In closed-loop evaluation, self-supervised pretraining improves PDMS by up to 4 percent for all single-city training cities. These results show that representation learning strongly influences the robustness of cross-city planning and establish zero-shot geographic transfer as a necessary test for evaluating end-to-end autonomous driving systems.