arXiv subjects

Xingyu Jiang

Publications and source records attributed to Xingyu Jiang.

17 recordsLinked to original sources

arXiv2026

Wat3R: Underwater 3D Geometry Learning without Annotations

Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations. Pioneering methods rely on massive dense annotations that are impractical in underwater settings. In this paper, we propose Wat3R, a cross-domain semi-supervised learning framework designed to adapt feed-forward 3D reconstruction models from air to underwater scenes. Uniquely, our method eliminates the need for any annotated underwater data following a teacher-student architecture, that learns robust geometry representations merely on abundant unlabeled real underwater video footage. We also design a cross-view consistency loss that leverages geometric cues from other views to compensate for the information degradation in the current view caused by water attenuation and scattering. Furthermore, considering the lack of comprehensive evaluation benchmarks, we construct Water3D, a diverse dataset covering various water bodies and underwater scenarios, designed for geometric task evaluation. Experimental results demonstrate that Wat3R outperforms current state-of-the-art methods in underwater multi-view depth estimation and point cloud reconstruction. The dataset and code are available at https://github.com/LSXI7/Wat3R .

cs.CV↗

arXiv2026

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks

We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from "in-the-wild" terminal recordings. Processing 80,870 terminal recordings, the engine yields a full benchmark of 1,530 validated tasks, spanning 18 real-world categories, ranging from short everyday operations to workflows exceeding 50 steps, and covering 1,280 unique commands. From these, we curate a Verified subset of 200 representative, manually reviewed tasks. Comprehensive benchmarking on TerminalWorld-Verified across eight frontier models and six agents reveals that current systems still struggle with authentic terminal workflows, achieving a maximum pass rate of only 62.5%. Moreover, TerminalWorld captures real-world terminal capabilities distinct from existing expert-curated benchmarks (e.g., Terminal-Bench), with only a weak correlation to their scores (Pearson r=0.20). The automated engine makes TerminalWorld authentic and scalable by construction, enabling it to evaluate agents in real-world terminal environments as developer practices evolve. Data and code are available at https://github.com/EuniAI/TerminalWorld.

cs.AI↗

arXiv2026

RF-Agent: Automated Reward Function Design via Language Agent Tree Search

Designing efficient reward functions for low-level control tasks is a challenging problem. Recent research aims to reduce reliance on expert experience by using Large Language Models (LLMs) with task information to generate dense reward functions. These methods typically rely on training results as feedback, iteratively generating new reward functions with greedy or evolutionary algorithms. However, they suffer from poor utilization of historical feedback and inefficient search, resulting in limited improvements in complex control tasks. To address this challenge, we propose RF-Agent, a framework that treats LLMs as language agents and frames reward function design as a sequential decision-making process, enhancing optimization through better contextual reasoning. RF-Agent integrates Monte Carlo Tree Search (MCTS) to manage the reward design and optimization process, leveraging the multi-stage contextual reasoning ability of LLMs. This approach better utilizes historical information and improves search efficiency to identify promising reward functions. Outstanding experimental results in 17 diverse low-level control tasks demonstrate the effectiveness of our method. The source code is available at https://github.com/deng-ai-lab/RF-Agent.

cs.AI↗

arXiv2025

NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding

Underwater exploration offers critical insights into our planet and attracts increasing attention for its broader applications in resource exploration, national security, etc. We study the underwater scene understanding methods, which aim to achieve automated underwater exploration. The underwater scene understanding task demands multi-task perceptions from multiple granularities. However, the absence of large-scale underwater multi-task instruction-tuning datasets hinders the progress of this research. To bridge this gap, we construct NautData, a dataset containing 1.45 M image-text pairs supporting eight underwater scene understanding tasks. It enables the development and thorough evaluation of the underwater scene understanding models. Underwater image degradation is a widely recognized challenge that interferes with underwater tasks. To improve the robustness of underwater scene understanding, we introduce physical priors derived from underwater imaging models and propose a plug-and-play vision feature enhancement (VFE) module, which explicitly restores clear underwater information. We integrate this module into renowned baselines LLaVA-1.5 and Qwen2.5-VL and build our underwater LMM, NAUTILUS. Experiments conducted on the NautData and public underwater datasets demonstrate the effectiveness of the VFE module, consistently improving the performance of both baselines on the majority of supported tasks, thus ensuring the superiority of NAUTILUS in the underwater scene understanding area. Data and models are available at https://github.com/H-EmbodVis/NAUTILUS.

cs.CV↗

arXiv2025

Global Modeling Matters: A Fast, Lightweight and Effective Baseline for Efficient Image Restoration

Natural image quality is often degraded by adverse weather conditions, significantly impairing the performance of downstream tasks. Image restoration has emerged as a core solution to this challenge and has been widely discussed in the literature. Although recent transformer-based approaches have made remarkable progress in image restoration, their increasing system complexity poses significant challenges for real-time processing, particularly in real-world deployment scenarios. To this end, most existing methods attempt to simplify the self-attention mechanism, such as by channel self-attention or state space model. However, these methods primarily focus on network architecture while neglecting the inherent characteristics of image restoration itself. In this context, we explore a pyramid Wavelet-Fourier iterative pipeline to demonstrate the potential of Wavelet-Fourier processing for image restoration. Inspired by the above findings, we propose a novel and efficient restoration baseline, named Pyramid Wavelet-Fourier Network (PW-FNet). Specifically, PW-FNet features two key design principles: 1) at the inter-block level, integrates a pyramid wavelet-based multi-input multi-output structure to achieve multi-scale and multi-frequency bands decomposition; and 2) at the intra-block level, incorporates Fourier transforms as an efficient alternative to self-attention mechanisms, effectively reducing computational complexity while preserving global modeling capability. Extensive experiments on tasks such as image deraining, raindrop removal, image super-resolution, motion deblurring, image dehazing, image desnowing and underwater/low-light enhancement demonstrate that PW-FNet not only surpasses state-of-the-art methods in restoration quality but also achieves superior efficiency, with significantly reduced parameter size, computational cost and inference time.

cs.CV↗

arXiv2025

Deep Learning Reforms Image Matching: A Survey and Outlook

Image matching, which establishes correspondences between two-view images to recover 3D structure and camera geometry, serves as a cornerstone in computer vision and underpins a wide range of applications, including visual localization, 3D reconstruction, and simultaneous localization and mapping (SLAM). Traditional pipelines composed of ``detector-descriptor, feature matcher, outlier filter, and geometric estimator'' falter in challenging scenarios. Recent deep-learning advances have significantly boosted both robustness and accuracy. This survey adopts a unique perspective by comprehensively reviewing how deep learning has incrementally transformed the classical image matching pipeline. Our taxonomy highly aligns with the traditional pipeline in two key aspects: i) the replacement of individual steps in the traditional pipeline with learnable alternatives, including learnable detector-descriptor, outlier filter, and geometric estimator; and ii) the merging of multiple steps into end-to-end learnable modules, encompassing middle-end sparse matcher, end-to-end semi-dense/dense matcher, and pose regressor. We first examine the design principles, advantages, and limitations of both aspects, and then benchmark representative methods on relative pose recovery, homography estimation, and visual localization tasks. Finally, we discuss open challenges and outline promising directions for future research. By systematically categorizing and evaluating deep learning-driven strategies, this survey offers a clear overview of the evolving image matching landscape and highlights key avenues for further innovation.

cs.CV↗

arXiv2025

You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts

Diffusion models (DMs) have recently demonstrated remarkable success in modeling large-scale data distributions. However, many downstream tasks require guiding the generated content based on specific differentiable metrics, typically necessitating backpropagation during the generation process. This approach is computationally expensive, as generating with DMs often demands tens to hundreds of recursive network calls, resulting in high memory usage and significant time consumption. In this paper, we propose a more efficient alternative that approaches the problem from the perspective of parallel denoising. We show that full backpropagation throughout the entire generation process is unnecessary. The downstream metrics can be optimized by retaining the computational graph of only one step during generation, thus providing a shortcut for gradient propagation. The resulting method, which we call Shortcut Diffusion Optimization (SDO), is generic, high-performance, and computationally lightweight, capable of optimizing all parameter types in diffusion sampling. We demonstrate the effectiveness of SDO on several real-world tasks, including controlling generation by optimizing latent and aligning the DMs by fine-tuning network parameters. Compared to full backpropagation, our approach reduces computational costs by $\sim 90\%$ while maintaining superior performance. Code is available at https://github.com/deng-ai-lab/SDO.

cs.LG↗

arXiv2025

Image Restoration via Multi-domain Learning

Due to adverse atmospheric and imaging conditions, natural images suffer from various degradation phenomena. Consequently, image restoration has emerged as a key solution and garnered substantial attention. Although recent Transformer architectures have demonstrated impressive success across various restoration tasks, their considerable model complexity poses significant challenges for both training and real-time deployment. Furthermore, instead of investigating the commonalities among different degradations, most existing restoration methods focus on modifying Transformer under limited restoration priors. In this work, we first review various degradation phenomena under multi-domain perspective, identifying common priors. Then, we introduce a novel restoration framework, which integrates multi-domain learning into Transformer. Specifically, in Token Mixer, we propose a Spatial-Wavelet-Fourier multi-domain structure that facilitates local-region-global multi-receptive field modeling to replace vanilla self-attention. Additionally, in Feed-Forward Network, we incorporate multi-scale learning to fuse multi-domain features at different resolutions. Comprehensive experimental results across ten restoration tasks, such as dehazing, desnowing, motion deblurring, defocus deblurring, rain streak/raindrop removal, cloud removal, shadow removal, underwater enhancement and low-light enhancement, demonstrate that our proposed model outperforms state-of-the-art methods and achieves a favorable trade-off among restoration performance, parameter size, computational cost and inference latency. The code is available at: https://github.com/deng-ai-lab/SWFormer.

eess.IV↗

arXiv2025

The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey

The Driving World Model (DWM), which focuses on predicting scene evolution during the driving process, has emerged as a promising paradigm in the pursuit of autonomous driving (AD). DWMs enable AD systems to better perceive, understand, and interact with dynamic driving environments. In this survey, we provide a comprehensive overview of the latest progress in DWM. First, we review the DWM ecosystem, which is constructed using mainstream simulators, high-impact datasets, and various metrics that evaluate DWMs across multiple dimensions. We then categorize existing approaches based on the modalities of the predicted scenes, including video, point cloud, occupancy, latent feature, and traffic map, and summarize their specific applications in AD research. In addition, the performance of representative approaches across generating and driving tasks is presented. Finally, we discuss the potential limitations of current research and propose future directions. This survey provides valuable insights into the development and application of DWM, fostering its broader adoption in AD. The relevant papers are collected at https://github.com/LMD0311/Awesome-World-Model.

cs.CV↗

arXiv2024

MINIMA: Modality Invariant Image Matching

Image matching for both cross-view and cross-modality plays a critical role in multimodal perception. In practice, the modality gap caused by different imaging systems/styles poses great challenges to the matching task. Existing works try to extract invariant features for specific modalities and train on limited datasets, showing poor generalization. In this paper, we present MINIMA, a unified image matching framework for multiple cross-modal cases. Without pursuing fancy modules, our MINIMA aims to enhance universal performance from the perspective of data scaling up. For such purpose, we propose a simple yet effective data engine that can freely produce a large dataset containing multiple modalities, rich scenarios, and accurate matching labels. Specifically, we scale up the modalities from cheap but rich RGB-only matching data, by means of generative models. Under this setting, the matching labels and rich diversity of the RGB dataset are well inherited by the generated multimodal data. Benefiting from this, we construct MD-syn, a new comprehensive dataset that fills the data gap for general multimodal image matching. With MD-syn, we can directly train any advanced matching pipeline on randomly selected modality pairs to obtain cross-modal ability. Extensive experiments on in-domain and zero-shot matching tasks, including $19$ cross-modal cases, demonstrate that our MINIMA can significantly outperform the baselines and even surpass modality-specific methods. The dataset and code are available at https://github.com/LSXI7/MINIMA.

cs.CV↗

arXiv2024

Correlation between unconventional superconductivity and strange metallicity revealed by operando superfluid density measurements

Strange-metal behavior has been observed in superconductors ranging from cuprates to pressurized nickelates, but its relationship to unconventional superconductivity remains elusive. Here, we perform operando superfluid density measurements on ion-gated FeSe films. We observe for the first time a synchronized evolution of superconducting condensate and the strange-metal phase with electron doping. A linear scaling between zero-temperature superfluid density and the strange-metal resistivity coefficient is further established, which nails down a direct link between the formation of superfluid in the superconducting state and the scattering of carriers in the strange-metal normal state. Remarkably, the scaling also applies for different iron-based and cuprate superconductors despite their distinct electronic structures and pairing symmetries. Such a correlation can be reproduced in a theoretical calculation on the two-dimensional Yukawa-Sachdev-Ye-Kitaev model by considering a cooperative effect of quantum critical fluctuation and disorder. These findings indicate a fundamental principle governing superconducting condensation and strange-metal scattering in unconventional superconductors.

cond-mat.supr-con↗

arXiv2024

AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding

The recent advancements in point cloud learning have enabled intelligent vehicles and robots to comprehend 3D environments better. However, processing large-scale 3D scenes remains a challenging problem, such that efficient downsampling methods play a crucial role in point cloud learning. Existing downsampling methods either require a huge computational burden or sacrifice fine-grained geometric information. For such purpose, this paper presents an advanced sampler that achieves both high accuracy and efficiency. The proposed method utilizes voxel centroid sampling as a foundation but effectively addresses the challenges regarding voxel size determination and the preservation of critical geometric cues. Specifically, we propose a Voxel Adaptation Module that adaptively adjusts voxel sizes with the reference of point-based downsampling ratio. This ensures that the sampling results exhibit a favorable distribution for comprehending various 3D objects or scenes. Meanwhile, we introduce a network compatible with arbitrary voxel sizes for sampling and feature extraction while maintaining high efficiency. The proposed approach is demonstrated with 3D object detection and 3D semantic segmentation. Compared to existing state-of-the-art methods, our approach achieves better accuracy on outdoor and indoor large-scale datasets, e.g. Waymo and ScanNet, with promising efficiency.

cs.CV↗

arXiv2021

DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception

Multi-object tracking and segmentation (MOTS) is a critical task for autonomous driving applications. The existing MOTS studies face two critical challenges: 1) the published datasets inadequately capture the real-world complexity for network training to address various driving settings; 2) the working pipeline annotation tool is under-studied in the literature to improve the quality of MOTS learning examples. In this work, we introduce the DG-Labeler and DGL-MOTS dataset to facilitate the training data annotation for the MOTS task and accordingly improve network training accuracy and efficiency. DG-Labeler uses the novel Depth-Granularity Module to depict the instance spatial relations and produce fine-grained instance masks. Annotated by DG-Labeler, our DGL-MOTS dataset exceeds the prior effort (i.e., KITTI MOTS and BDD100K) in data diversity, annotation quality, and temporal representations. Results on extensive cross-dataset evaluations indicate significant performance improvements for several state-of-the-art methods trained on our DGL-MOTS dataset. We believe our DGL-MOTS Dataset and DG-Labeler hold the valuable potential to boost the visual perception of future transportation.

cs.CV↗

arXiv2021

Enhancement of Superconductivity Linked with Linear-in-Temperature/Field Resistivity in Ion-Gated FeSe Films

Iron selenide (FeSe) - the structurally simplest iron-based superconductor, has attracted tremendous interest in the past years. While the transition temperature (Tc) of bulk FeSe is $\sim$ 8 K, it can be significantly enhanced to 40 - 50 K by various ways of electron doping. However, the underlying physics for such great enhancement of Tc and so the Cooper pairing mechanism still remain puzzles. Here, we report a systematic study of the superconducting- and normal-state properties of FeSe films via ionic liquid gating. With fine tuning, Tc evolves continuously from below 10 K to above 40 K; in situ two-coil mutual inductance measurements unambiguously confirm the gating is a uniform bulk effect. Close to Tc, the normal-state resistivity shows a linear dependence on temperature and the linearity extends to lower temperatures with the superconductivity suppressed by high magnetic fields. At high fields, the normal-state magnetoresistance exhibits a linear-in-field dependence and obeys a simple scaling relation between applied field and temperature. Consistent behaviors are observed for different-Tc states throughout the gating process, suggesting the pairing mechanism very likely remains the same from low- to high-Tc state. Importantly, the coefficient of the linear-in-temperature resistivity is positively correlated with Tc, similarly to the observations in cuprates, Bechgaard salts and iron pnictide superconductors. Our study points to a short-range antiferromagnetic exchange interaction mediated pairing mechanism in FeSe.

cond-mat.supr-con↗

arXiv2021

Universal scaling of the critical temperature and the strange-metal scattering rate in unconventional superconductors

Dramatic evolution of properties with minute change in the doping level is a hallmark of the complex chemistry which governs cuprate superconductivity as manifested in the celebrated superconducting domes as well as quantum criticality taking place at precise compositions. The strange metal state, where the resistivity varies linearly with temperature, has emerged as a central feature in the normal state of cuprate superconductors. The ubiquity of this behavior signals an intimate link between the scattering mechanism and superconductivity. However, a clear quantitative picture of the correlation has been lacking. Here, we report observation of quantitative scaling laws between the superconducting transition temperature $T_{\rm c}$ and the scattering rate associated with the strange metal state in electron-doped cuprate $\rm La_{2-x}Ce_xCuO_4$ (LCCO) as a precise function of the doping level. High-resolution characterization of epitaxial composition-spread films, which encompass the entire overdoped range of LCCO has allowed us to systematically map its structural and transport properties with unprecedented accuracy and increment of $Δx = 0.0015$. We have uncovered the relations $T_{\rm c}\sim(x_{\rm c}-x)^{0.5}\sim(A_1^\square)^{0.5}$, where $x_c$ is the critical doping where superconductivity disappears on the overdoped side and $A_1^\square$ is the scattering rate of perfect $T$-linear resistivity per CuO$_2$ plane. We argue that the striking similarity of the $T_{\rm c}$ vs $A_1^\square$ relation among cuprates, iron-based and organic superconductors is an indication of a common mechanism of the strange metal behavior and unconventional superconductivity in these systems.

cond-mat.supr-con↗

arXiv2017

Promoting superconductivity in FeSe films via fine manipulation of crystal lattice

Stabilized FeSe thin films in ambient pressure with tunable superconductivity would be a promising candidate for superconducting electronic devices yet its superconducting transition temperature (Tc) is below 10 K in bulk materials. By carefully controlling the depositions on twelve kinds of substrates using pulsed laser deposition technique, high quality single crystalline FeSe samples were fabricated with full width of half maximum 0.515? in the rocking curve and clear four-fold symmetry in phi-scan from x-ray diractions. The films have a maximum Tc 15 K on the CaF2 substrate and do not show obvious decay in the air for more than half a year. Slightly tuning the stoichiometry of the FeSe targets, the Tc becomes adjustable from 15 to < 2 K with quite narrow transition widths less than 2 K, and shows a positive relation with the out-of-plane (c-axis) lattice parameter of the films. However, there is no clear relation between the Tc and the surface atomic distance of the substrates. By reducing the thickness of the films, the Tc decreases and fades away in samples of less than 10 nm, suggesting that the strain effect is not responsible for the enhancement of Tc in our experiments.

cond-mat.supr-con↗

arXiv2017

Doping Mn into (Li1-xFex)OHFe1-ySe superconducting crystals via ion-exchange and ion-release/introduction syntheses

We report the success in introducing Mn into (Li1-xFex)OHFe1-ySe superconducting crystals by applying two different hydrothermal routes, ion exchange (1-Step) and ion release/introduction (2-Step). The micro-region x-ray diffraction and energy dispersive x-ray spectroscopy analyses indicate that the Mn has been doped into the lattice, and its content in the 1-Step fabricated sample is higher than that in the 2-Step one. Magnetic susceptibility and electric transport properties reveal that Mn doping influences little on the superconducting transition, regardless of 1-Step or 2-Step routes. By contrast, the characteristic temperature, T*, where the negative Hall coefficient reaches its minimum, is significantly reduced by Mn doping. This implies that the reduction of the hole carriers contribution is obviously modified, and hence the hole band might have no direct relationship with the superconductivity in (Li1-xFex)OHFe1-ySe superconductors. Our present hydrothermal methods of ion exchange and ion release/introduction provide an efficient way for elements substitution/doping into (Li1-xFex)OHFe1-ySe superconductors, which will promote the in-depth investigations on the role of multiple electron and hole bands and their interplay with the high-temperature superconductivity in the FeSe-based superconductors.

cond-mat.supr-con↗