Searcharxiv⌕ Search

arXiv subjects

Pai Peng

Publications and source records attributed to Pai Peng.

At least 19 recordsLinked to original sources

RSLiveBench-UAV: A Continually Evolving Vision-Language Benchmark for Aerial Spatial Intelligence

Aerial spatial intelligence (ASI) requires models to understand objects and spatial relationships across changing viewpoints and scales. Evaluating these abilities as models evolve calls for fresh physical observations, yet producing new aerial spatial questions requires repeatedly establishing entity identities, geometric references, and cross-view correspondences. We introduce \textbf{RSLiveBench-UAV}, a continually evolving vision-language benchmark driven by recurring acquisition of real UAV imagery. Its update protocol admits images captured after the preceding release and delays answer disclosure. An entity-centered production workflow uses geometry-assisted association to link repeated observations of physical vehicles, reuse human-verified attributes, and combine them with view-specific annotations and spatial references for traceable question generation. All tasks use deterministic scoring without model judges. We evaluate 30 general-purpose, remote-sensing, and embodied models on 35,491 question records from ten scenes, covering 17 tasks across 2D perception, 3D perception, cross-view perception, and reasoning. All 18 tested embodied models outperform the three selected remote-sensing comparators in Overall, although the strongest embodied model scores 43.29 versus 59.88 for GPT-6-Astra. Fine-grained vehicle recognition remains challenging, and performance varies across heights and camera pitches. Retrospective scene-group comparisons and rolling-window replay characterize score-pattern consistency under scene renewal. RSLiveBench-UAV connects fresh physical observations, entity-centered answer production, and systematic model evaluation to support continual assessment of ASI. Benchmark will release at https://rslivebench.space

cs.CV↗

MORE: Learning Motion-Oriented Registers for Driving World Models and Planning

By predicting future states, latent world models provide rich self-supervision for end-to-end driving, but often inherit dense features from pretrained visual encoders as their world-state interface. This creates a mismatch: visual pretraining produces information-rich, spatially dense features, but their adaptation for motion-conditioned world modeling and planning is deferred to downstream training. The dense grid also makes future prediction more computationally expensive as visual resolution increases. We therefore argue that video pretraining should directly learn state representations suited to downstream world modeling and planning, rather than relying on downstream training to adapt inherited visual features. We propose ***MORE***, a V-JEPA framework that learns **M**otion-**O**riented **RE**gisters during video pretraining as a shared state interface for driving world models and planning. MORE injects temporally aligned ego motion into a small set of registers and uses them as the sole context for masked patch prediction, channeling dense patch-level supervision through a compact state bottleneck. A complementary blockwise register-masking objective further shapes predictive structure in the register space. During downstream training, the same register space defines the future states predicted by the world model and provides shared scene memory for trajectory generation and scoring. On NAVSIM-v2, MORE outperforms the state of the art by 1.6 in EPDMS, while achieving superior efficiency with only 1/10 the inference latency of DriveLaW. These results support learning the state interface for world modeling and planning directly during video pretraining.

cs.CV↗

DroneWAM: Efficient World Action Model for Drone Visual Navigation

World-action models give visual navigation agents a way to anticipate how candidate actions will change future observations and to act from the predicted consequences. For drones, this capability must operate under tight accuracy and efficiency constraints. We present DroneWAM, an efficient world-action model for drone visual navigation. DroneWAM adopts a JEPA-based architecture to model future states directly in representation space, avoiding the cost of explicit future image generation. A pretrained Resampler further compresses dense encoder features into fewer latent tokens, reducing the computation repeated at each imagined step. We also introduce adaptive rollout, where a preference-trained Gate adaptively allocates prediction depth according to the current scene. To support learning under richer aerial motion, we construct DroneNav-6D, a simulated visual navigation dataset with synchronized RGB observations, 6-DoF flight trajectories, control commands, and randomized wind disturbances. On DroneNav-6D, DroneWAM achieves the best trajectory accuracy among the compared methods. Adaptive rollout further reduces the average prediction depth from 8 to 4.58 while improving trajectory accuracy, demonstrating that predictive computation can be allocated more effectively across scenes. \href{https://github.com/1e12Leon/DroneWAM}{Codes and data} will be released.

cs.CV↗

Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimization

GUI agents increasingly operate across websites, mobile apps, and desktop environments, yet the field still reports progress primarily through task success. We argue that practical deployment depends equally on efficiency: how much context, computation, action budget, and runtime overhead an agent consumes while succeeding. This survey studies efficient GUI agents through an end-to-end systems lens that preserves the current technical axes of observation efficiency, context and memory efficiency, action efficiency, and planner-side/system efficiency. For each subsection, we expand the seed literature through targeted search plus backward and forward citation chaining, then synthesize the dominant mechanisms, reported efficiency signals, and new overheads they introduce. Across the literature, recent progress converges on a small set of recurring ideas: selective reading instead of full-context ingestion, global-to-local visual allocation, recoverable memory rather than raw history replay, verification-aware control, and hybrid runtimes that can switch between GUI and non-GUI execution. We conclude by identifying the main open problems, including honest accounting of verifier cost, cross-benchmark comparability, and co-design of observation, memory, and execution layers under real latency and privacy constraints.

cs.CL↗

RISE: Adaptive Imagination for World Action Models

World Action Models (WAMs) improve planning by incorporating future world evolution into action generation, yet existing methods allocate a fixed imagination budget to every scene. We propose RISE (\textbf{R}efining \textbf{I}magination through \textbf{SE}lective Rollout), a system-level adaptive imagination framework that makes sequential \textsc{Roll}/\textsc{Stop} decisions according to the expected planning benefit of continued rollout. At each step, a Latent Evaluator estimates the risk revealed by the current prefix and how much planning could improve if imagination continues, while a Rollout Gate weighs this expected benefit against additional computation cost. Since factual driving logs expose only one realized future, we further construct \textbf{CounterDrive}, a counterfactual dataset with diverse outcomes and risk levels, to enrich future dynamics and provide localized risk supervision. Each retained sample undergoes expert verification and annotation of trajectory validity, incident onset, and causal category, providing a reusable resource for safety-critical world-modeling research. Experiments on NAVSIM and nuScenes show that RISE achieves the best overall planning performance while reducing unnecessary rollout, with additional transfer results supporting its plug-in generality across WAM architectures.

cs.CV↗

High-efficiency loading of 2,400 Ytterbium atoms in optical tweezer arrays

Neutral atom arrays have emerged as a powerful platform for quantum computation, simulation, and metrology.Among them, alkaline-earth-like atoms exhibit distinct advantages, including long coherence time, high-fidelity Rydberg gates, and erasure correction for efficient quantum error correction. However, their scalability has lagged behind that of the alkali atoms. Here, we report 2400 ytterbium-174 atoms trapped in an optical tweezer array with enhanced loading efficiency of 83.5(1)\% via blue-detuned light-assisted collisions. We develop a quantitative model of the collision dynamics and find good agreement between the calculated inelastic collision rates and the experimentally measured loading efficiencies.Notably, the loading efficiency is largely maintained for array sizes ranging from dozens to thousands, exhibiting excellent scalability. We further demonstrate that the enhancement exists robustly across a range of interatomic potentials, suggesting its utility for other atomic species. To establish the capability of the $^{174}$Yb arrays toward universal quantum computation, we propose to encode the qubit in the ground-clock state manifold and estimate a 99.9\% two-qubit gate fidelity with experimentally feasible parameters. Our work advances the prospects for realizing large-scale quantum computers using alkaline-earth-like atoms.

quant-ph↗

Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs

Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis. However, their application in gastrointestinal endoscopy is currently hindered by two critical limitations: the misalignment between general model reasoning and standardized clinical cognitive pathways, and the lack of causal association between visual features and diagnostic outcomes. In this paper, we propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges. First, we endow the model with rigorous clinical analytical capabilities by constructing the hierarchical clinical cognition dataset and employing Supervised Fine-Tuning (SFT). Unlike conventional approaches, this strategy internalizes the hierarchical diagnostic logic of experts, ranging from anatomical localization and morphological evaluation to microvascular analysis, directly into the model. Second, to eliminate visual bias, we provide a theoretical analysis demonstrating that standard supervised tuning inevitably converges to spurious background correlations. Guided by this insight, we propose a counterfactual-driven reinforcement learning strategy to enforce causal rectification. By generating counterfactual normal samples via lesion masking and optimizing through clinical-cognition-centric rewards, we constrain the model to strictly ground its diagnosis in causal lesion features. Extensive experiments demonstrate that our approach achieves State-of-the-Art (SoTA) performance across multiple benchmarks, significantly enhancing diagnostic accuracy in complex clinical scenarios.

cs.CV↗

Logical qubits with erasure conversion using metastable neutral atoms

Implementing large-scale quantum algorithms with practical advantage will require fault-tolerance achieved through quantum error correction, but the associated overhead is prohibitive. This overhead can be reduced by engineering physical qubits with fewer errors, and by shaping the residual errors to be more easily correctable. In this work, we demonstrate quantum error correcting codes and logical qubit circuits in a metastable ytterbium-171 nuclear spin qubit with a noise bias towards erasure errors. These errors can be located separately from any syndrome information diagnosing the error, and we demonstrate adaptive circuit execution based on erasure information. We show that dephasing errors on the qubit during coherent transport can be strongly suppressed, and implement entangling gates that maintain a high fidelity in the presence of gate beam inhomogeneity or pointing errors. Furthermore, we demonstrate logical qubit encoding in the [[4, 2, 2]] code, with error correction during decoding based on mid-circuit erasure measurements despite the fact that the code is too small to correct any Pauli errors. Finally, we demonstrate logical qubit teleportation between multiple code blocks with conditionally selected ancillas based on mid-circuit erasure checks, a key part of leakage-robust error correction schemes using neutral atoms.

quant-ph↗

Terahertz frequency upconversion by coherently driving charge dynamics in the InSb/CdTe heterostructure

We investigate terahertz (THz) harmonic generation in the InSb/CdTe heterostructure, demonstrating, for the first time, efficient in-plane magnetic field-induced second-harmonic generation (SHG). We also achieve significant third-harmonic generation (THG), rivalling Dirac materials such as graphene and Cd3As2. Our theoretical analysis identifies the primary SHG mechanism as the orbital-Zeeman correction to Drude conductivity, while the dominant THG contribution also shows Drude-like behavior. The results provide a general route to efficient THz harmonic generation in high mobility materials.

cond-mat.mtrl-sci↗

The DAWN of World-Action Interactive Models

A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action Models (WAMs) largely miss this reciprocity, treating world prediction and action generation as either isolated parallel branches or rigid predict-then-plan pipelines. We formalize this perspective as World-Action Interactive Models (WAIMs), and instantiate it in autonomous driving with \textbf{DAWN} (\textbf{D}enoising \textbf{A}ctions and \textbf{W}orld i\textbf{N}teractive model), a simple yet strong latent generative baseline. DAWN operates in a compact semantic latent space and couples a \emph{World Predictor} with a \emph{World-Conditioned Action Denoiser}: the predicted world hypothesis conditions action denoising, while the denoised action hypothesis is fed back to update the world prediction, so that both are recursively refined during inference. Rather than eliminating test-time world evolution altogether or rolling out the full future in pixel space, DAWN performs a short explicit latent rollout that is sufficient to support long-horizon trajectory generation in complex interactive scenes. Experiments show that DAWN achieves strong planning performance and favorable safety-related results across multiple autonomous driving benchmarks. More broadly, our results suggest that interactive world-action generation is a principled path toward truly actionable world models.

cs.CV↗

Evaluating Low-Light Image Enhancement Across Multiple Intensity Levels

Imaging in low-light environments is challenging due to reduced scene radiance, which leads to elevated sensor noise and reduced color saturation. Most learning-based low-light enhancement methods rely on paired training data captured under a single low-light condition and a well-lit reference. The lack of radiance diversity limits our understanding of how enhancement techniques perform across varying illumination intensities. We introduce the Multi-Illumination Low-Light (MILL) dataset, containing images captured at diverse light intensities under controlled conditions with fixed camera settings and precise illuminance measurements. MILL enables comprehensive evaluation of enhancement algorithms across variable lighting conditions. We benchmark several state-of-the-art methods and reveal significant performance variations across intensity levels. Leveraging the unique multi-illumination structure of our dataset, we propose improvements that enhance robustness across diverse illumination scenarios. Our modifications achieve up to 10 dB PSNR improvement for DSLR and 2 dB for the smartphone on Full HD images.

cs.CV↗

VisionNVS: Self-Supervised Inpainting for Novel View Synthesis under the Virtual-Shift Paradigm

A fundamental bottleneck in Novel View Synthesis (NVS) for autonomous driving is the inherent supervision gap on novel trajectories: models are tasked with synthesizing unseen views during inference, yet lack ground truth images for these shifted poses during training. In this paper, we propose VisionNVS, a camera-only framework that fundamentally reformulates view synthesis from an ill-posed extrapolation problem into a self-supervised inpainting task. By introducing a ``Virtual-Shift'' strategy, we use monocular depth proxies to simulate occlusion patterns and map them onto the original view. This paradigm shift allows the use of raw, recorded images as pixel-perfect supervision, effectively eliminating the domain gap inherent in previous approaches. Furthermore, we address spatial consistency through a Pseudo-3D Seam Synthesis strategy, which integrates visual data from adjacent cameras during training to explicitly model real-world photometric discrepancies and calibration errors. Experiments demonstrate that VisionNVS achieves superior geometric fidelity and visual quality compared to LiDAR-dependent baselines, offering a robust solution for scalable driving simulation.

cs.CV↗

WildSVG: Towards Reliable SVG Generation Under Real-Word Conditions

We introduce the task of SVG extraction, which consists in translating specific visual inputs from an image into scalable vector graphics. Existing multimodal models achieve strong results when generating SVGs from clean renderings or textual descriptions, but they fall short in real-world scenarios where natural images introduce noise, clutter, and domain shifts. A central challenge in this direction is the lack of suitable benchmarks. To address this need, we introduce the WildSVG Benchmark, formed by two complementary datasets: Natural WildSVG, built from real images containing company logos paired with their SVG annotations, and Synthetic WildSVG, which blends complex SVG renderings into real scenes to simulate difficult conditions. Together, these resources provide the first foundation for systematic benchmarking SVG extraction. We benchmark state-of-the-art multimodal models and find that current approaches perform well below what is needed for reliable SVG extraction in real scenarios. Nonetheless, iterative refinement methods point to a promising path forward, and model capabilities are steadily improving

cs.CV↗

Cross-Modal Mapping: Mitigating the Modality Gap for Few-Shot Image Classification

Few-shot image classification remains a critical challenge in the field of computer vision, particularly in data-scarce environments. Existing methods typically rely on pre-trained visual-language models, such as CLIP. However, due to the modality gap, which is the inconsistent distribution of image and text features in the joint embedding space, directly using these features as class prototypes often leads to suboptimal performance. To address this issue, we propose a novel Cross-Modal Mapping (CMM) method. This method globally aligns image features with the text feature space through linear transformation and optimizes their local spatial relationships using triplet loss, thereby significantly enhancing cross-modal consistency. Experimental results show that compared to other methods, CMM simplifies the training process and demonstrates higher efficiency. Furthermore, CMM improves the average Top-1 accuracy by 1.06% on 11 benchmark datasets compared to methods that partially fine-tune the backbone, and it performs excellently on 4 distribution shift datasets. Notably, CMM effectively mitigates the modality gap in pre-trained models, enabling text features to serve as effective class prototypes for image features, thus providing an efficient and highly generalizable solution for few-shot learning.

cs.CV↗

Slit-Induced Reflection Mode Conversion Between Fundamental Lamb Modes in Elastic Plates with Low-Frequency and Broadband Response

We present a compact slit-based interface that enables reflection mode conversion in an elastic plate by transforming an incident lowest-order antisymmetric Lamb mode into a reflected lowest-order symmetric Lamb mode. The interface is realized by introducing inclined vacuum slits along the lateral sides of the plate. This geometry intentionally breaks symmetry and produces a strongly localized, vortex-like deformation near the slit tips, which provides an efficient coupling pathway from the antisymmetric incident response to a symmetric reflected component. The conversion is quantified in a consistent, field-based manner by extracting the reflected antisymmetric level from the standing-wave envelope on a probe line placed sufficiently far from the slits, and then inferring the converted symmetric energy under a lossless assumption with only two reflected propagating channels. The proposed design delivers strong low-frequency conversion and sustains broadband half-power operation, while parametric studies confirm that the performance is tunable and robust over a wide range of slit angles and widths.

physics.app-ph↗

Ultra-low-frequency reflection mode conversion from compressional to shear waves enabled by periodic inclined slits

A periodically patterned free surface with inclined slits can convert an incident compressional wave into a reflected shear wave with nearly complete efficiency at very low frequency. The system is described by two-dimensional in-plane linear elasticity, and the slits are treated as voids. The conversion is quantified by the ratio between the reflected shear-wave energy and the incident compressional-wave energy, obtained from mode decomposition and energy-flux evaluation below the surface. The results indicate that the inclined geometry introduces strong coupling between normal and tangential motions at the boundary, enabling suppression of the ordinary compressional reflection while redirecting the reflected energy into the shear channel. This simple, geometry-controlled mechanism provides a compact route for low-frequency elastic-wave polarization control.

physics.app-ph↗

EPD-Serve: A Flexible Multimodal EPD Disaggregation Inference Serving System On Ascend

With the widespread adoption of large multimodal models, efficient inference across text, image, audio, and video modalities has become critical. However, existing multimodal inference systems typically employ monolithic architectures that tightly couple the Encode, Prefill, and Decode stages on homogeneous hardware, neglecting the heterogeneous computational characteristics of each stage. This design leads to inefficient resource utilization and limited system throughput. To address these issues, we propose EPD-Serve, a stage-level disaggregated inference serving system for multimodal models. EPD-Serve decouples the inference pipeline into independent Encode, Prefill, and Decode stages, enabling logical isolation and flexible co-located deployment through dynamic orchestration. Leveraging the Ascend interconnect topology, EPD-Serve introduces asynchronous feature prefetching between Encode and Prefill stages and a hierarchical grouped KV cache transmission mechanism between Prefill and Decode stages to improve cross-node communication efficiency. In addition, EPD-Serve incorporates multi-route scheduling, instance-level load balancing, and multi-stage hardware co-location with spatial multiplexing to better support diverse multimodal workloads. Comprehensive experiments on multimodal understanding models demonstrate that, under high-concurrency scenarios, EPD-Serve improves end-to-end throughput by 57.37-69.48% compared to PD-disaggregated deployment, while satisfying strict SLO constraints, including TTFT below 2000 ms and TPOT below 50 ms. These results highlight the effectiveness of stage-level disaggregation for optimizing multimodal large model inference systems.

cs.DC↗

RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow

Remote sensing imagery presents vast, inherently unstructured spatial data, necessitating sophisticated reasoning to interpret complex user intents and contextual relationships beyond simple recognition tasks. In this paper, we aim to construct an Earth observation workflow to handle complex queries by reasoning about spatial context and user intent. As a reasoning workflow, it should autonomously explore and construct its own inference paths, rather than being confined to predefined ground-truth sequences. Ideally, its architecture ought to be unified yet generalized, possessing capabilities to perform diverse reasoning tasks through one model without requiring additional fine-tuning. Existing remote sensing approaches rely on supervised fine-tuning paradigms and task-specific heads, limiting both autonomous reasoning and unified generalization. To this end, we propose RemoteReasoner, a unified workflow for geospatial reasoning. The design of RemoteReasoner integrates a multi-modal large language model (MLLM) for interpreting user instructions and localizing targets, together with task transformation strategies that enable multi-granularity tasks, including object-, region-, and pixel-level. In contrast to existing methods, our framework is trained with reinforcement learning (RL) to endow the MLLM sufficient reasoning autonomy. At the inference stage, our transformation strategies enable diverse task output formats without requiring task-specific decoders or further fine-tuning. Experiments demonstrated that RemoteReasoner achieves state-of-the-art (SOTA) performance across multi-granularity reasoning tasks. Furthermore, it retains the MLLM's inherent generalization capability, demonstrating robust performance on unseen tasks and out-of-distribution categories.

cs.CV↗