arXiv subjects

Feng Gao

Publications and source records attributed to Feng Gao.

At least 55 records · Page 3Linked to original sources

arXiv2026

Lightweight Multimodal LLM-Enabled Cost-Effective Defect Grading of Power Transmission Equipment

Defect grading of power transmission equipment (DGPTE) is crucial to the stability of electric energy transmission. Although existing machine learning methods exhibit strong capabilities in defect detection, they are plagued by difficulties in integrating expert experience and facing class imbalance in more refined defect grading field. To address this issue, this paper introduces a novel defect grading framework based on multimodal large language model (MLLM). Specifically, this approach maximizes the commercial MLLMs' potential of DGPTE through in-context learning and obtains the state-of-te-art (SOTA) model. By sending a secondary request to this model, a small number of chain of thought-based question-answer pairs (Q\&As) are generated, which effectively reduces the cost of manual annotation. In this way, these high-quality interpretable Q\&As are used to train Qwen3-VL-8B via Low-Rank Adaption-based supervised fine-tuning (SFT). Experimental results on three DGPTE tasks demonstrate that fine-tuning only the language model layer yields the SOTA performance. Furthermore, multi-task joint fine-tuning verifies the feasibility of handling multiple grading tasks within only a single lightweight MLLM.

cs.CL↗

arXiv2026

UAV-CB: A Complex-Background RGB-T Dataset and Local Frequency Bridge Network for UAV Detection

Detecting Unmanned Aerial Vehicles (UAVs) in low-altitude environments is essential for perception and defense systems but remains highly challenging due to complex backgrounds, camouflage, and multimodal interference. In real-world scenarios, UAVs are frequently visually blended with surrounding structures such as buildings, vegetation, and power lines, resulting in low contrast, weak boundaries, and strong confusion with cluttered background textures. Existing UAV detection datasets, though diverse, are not specifically designed to capture these camouflage and complex-background challenges, which limits progress toward robust real-world perception. To fill this gap, we construct UAV-CB, a new RGB-T UAV detection dataset deliberately curated to emphasize complex low-altitude backgrounds and camouflage characteristics. Furthermore, we propose the Local Frequency Bridge Network (LFBNet), which models features in localized frequency space to bridge both the frequency-spatial fusion gap and the cross-modality discrepancy gap in RGB-T fusion. Extensive experiments on UAV-CB and public benchmarks demonstrate that LFBNet achieves state-of-the-art detection performance and strong robustness under camouflaged and cluttered conditions, offering a frequency-aware perspective on multimodal UAV perception in real-world applications.

cs.CV↗

arXiv2026

From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding

Self-supervised visual pre-training methods face an inherent tension: contrastive learning (CL) captures global semantics but loses fine-grained detail, while masked image modeling (MIM) preserves local textures but suffers from "attention drift" due to semantically-agnostic random masking. We propose C2FMAE, a coarse-to-fine masked autoencoder that resolves this tension by explicitly learning hierarchical visual representations across three data granularities: semantic masks (scene-level), instance masks (object-level), and RGB images (pixel-level). Two synergistic innovations enforce a strict top-down learning principle. First, a cascaded decoder sequentially reconstructs from scene semantics to object instances to pixel details, establishing explicit cross-granularity dependencies that parallel decoders cannot capture. Second, a progressive masking curriculum dynamically shifts the training focus from semantic-guided to instance-guided and finally to random masking, creating a structured learning path from global context to local features. To support this framework, we construct a large-scale multi-granular dataset with high-quality pseudo-labels for all 1.28M ImageNet-1K images. Extensive experiments show that C2FMAE achieves significant performance gains on image classification, object detection, and semantic segmentation, validating the effectiveness of our hierarchical design in learning more robust and generalizable representations.

cs.CV↗

arXiv2026

MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation

We propose MAViD, a novel Multimodal framework for Audio-Visual Dialogue understanding and generation. Existing approaches primarily focus on non-interactive systems and are limited to producing constrained and unnatural human speech. The primary challenge of this task lies in effectively integrating understanding and generation capabilities, as well as achieving seamless multimodal audio-video fusion. To solve these problems, we propose a Conductor-Creator architecture that divides the dialogue system into two primary components. The Conductor is tasked with understanding, reasoning, and generating instructions by breaking them down into motion and speech components, thereby enabling fine-grained control over interactions. The Creator then delivers interactive responses based on these instructions. Furthermore, to address the difficulty of generating long videos with consistent identity, timbre, and tone using dual DiT structures, the Creator adopts a structure that combines autoregressive (AR) and diffusion models. The AR model is responsible for audio generation, while the diffusion model ensures high-quality video generation. Additionally, we propose a novel fusion module to enhance connections between contextually consecutive clips and modalities, enabling synchronized long-duration audio-visual content generation. Extensive experiments demonstrate that our framework can generate vivid and contextually coherent long-duration dialogue interactions and accurately interpret users' multimodal queries.

cs.CV↗

arXiv2026

PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation

Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but also predictive modeling of environment dynamics and spatial structure. We propose PROSPECT, a unified streaming navigation agent that couples a streaming Vision-Language-Action (VLA) policy with latent predictive representation learning. PROSPECT uses CUT3R as a streaming 3D foundation spatial encoder to produce long-context, absolute-scale spatial features, and fuses them with SigLIP semantic features via cross-attention. During training, we introduce learnable stream query tokens that query the streaming context and predict next-step 2D and 3D latent features (rather than pixels or explicit modalities), supervised in the latent spaces of frozen SigLIP and CUT3R teachers. The predictive branch shapes internal representations without inference overhead. Experiments on VLN-CE benchmarks and real-robot deployment demonstrate state-of-the-art performance and improved long-horizon robustness under diverse lighting. We will release code for the community soon.

cs.CV↗

arXiv2026

Intrinsic Geometry-Appearance Consistency Optimization for Sparse-View Gaussian Splatting

3D human reconstruction from a single image is a challenging problem and has been exclusively studied in the literature. Recently, some methods have resorted to diffusion models for guidance, optimizing a 3D representation via Score Distillation Sampling(SDS) or generating a back-view image for facilitating reconstruction. However, these methods tend to produce unsatisfactory artifacts (\textit{e.g.} flattened human structure or over-smoothing results caused by inconsistent priors from multiple views) and struggle with real-world generalization in the wild. In this work, we present \emph{MVD-HuGaS}, enabling free-view 3D human rendering from a single image via a multi-view human diffusion model. We first generate multi-view images from the single reference image with an enhanced multi-view diffusion model, which is well fine-tuned on high-quality 3D human datasets to incorporate 3D geometry priors and human structure priors. To infer accurate camera poses from the sparse generated multi-view images for reconstruction, an alignment module is introduced to facilitate joint optimization of 3D Gaussians and camera poses. Furthermore, we propose a depth-based Facial Distortion Mitigation module to refine the generated facial regions, thereby improving the overall fidelity of the reconstruction. Finally, leveraging the refined multi-view images, along with their accurate camera poses, MVD-HuGaS optimizes the 3D Gaussians of the target human for high-fidelity free-view renderings. Extensive experiments on Thuman2.0 and 2K2K datasets show that the proposed MVD-HuGaS achieves state-of-the-art performance on single-view 3D human rendering.

cs.CV↗

arXiv2026

Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design

In real underwater environments, downstream image recognition tasks such as semantic segmentation and object detection often face challenges posed by problems like blurring and color inconsistencies. Underwater image enhancement (UIE) has emerged as a promising preprocessing approach, aiming to improve the recognizability of targets in underwater images. However, most existing UIE methods mainly focus on enhancing images for human visual perception, frequently failing to reconstruct high-frequency details that are critical for task-specific recognition. To address this issue, we propose a Downstream Task-Inspired Underwater Image Enhancement (DTI-UIE) framework, which leverages human visual perception model to enhance images effectively for underwater vision tasks. Specifically, we design an efficient two-branch network with task-aware attention module for feature mixing. The network benefits from a multi-stage training framework and a task-driven perceptual loss. Additionally, inspired by human perception, we automatically construct a Task-Inspired UIE Dataset (TI-UIED) using various task-specific networks. Experimental results demonstrate that DTI-UIE significantly improves task performance by generating preprocessed images that are beneficial for downstream tasks such as semantic segmentation, object detection, and instance segmentation. The codes are publicly available at https://github.com/oucailab/DTIUIE.

cs.CV↗

arXiv2026

U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation

Full-stack multimodal interaction in real-time is a central goal in building intelligent embodied agents capable of natural, dynamic communication. However, existing systems are either limited to unimodal generation or suffer from degraded reasoning and poor cross-modal alignment, preventing coherent and perceptually grounded interactions. In this work, we introduce U-Mind, the first unified system for high-intelligence multimodal dialogue that supports real-time generation and jointly models language, speech, motion, and video synthesis within a single interactive loop. At its core, U-Mind implements a Unified Alignment and Reasoning Framework that addresses two key challenges: enhancing cross-modal synchronization via a segment-wise alignment strategy, and preserving reasoning abilities through Rehearsal-Driven Learning. During inference, U-Mind adopts a text-first decoding pipeline that performs internal chain-of-thought planning followed by temporally synchronized generation across modalities. To close the loop, we implement a real-time video rendering framework conditioned on pose and speech, enabling expressive and synchronized visual feedback. Extensive experiments demonstrate that U-Mind achieves state-of-the-art performance on a range of multimodal interaction tasks, including question answering, instruction following, and motion generation, paving the way toward intelligent, immersive conversational agents.

cs.CV↗

arXiv2026

VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play

Robot sports, characterized by well-defined objectives, explicit rules, and dynamic interactions, present ideal scenarios for demonstrating embodied intelligence. In this paper, we present VolleyBots, a novel robot sports testbed where multiple drones cooperate and compete in the sport of volleyball under physical dynamics. VolleyBots integrates three features within a unified platform: competitive and cooperative gameplay, turn-based interaction structure, and agile 3D maneuvering. These intertwined features yield a complex problem combining motion control and strategic play, with no available expert demonstrations. We provide a comprehensive suite of tasks ranging from single-drone drills to multi-drone cooperative and competitive tasks, accompanied by baseline evaluations of representative reinforcement learning (RL), multi-agent reinforcement learning (MARL) and game-theoretic algorithms. Simulation results show that on-policy RL methods outperform off-policy methods in single-agent tasks, but both approaches struggle in complex tasks that combine motion control and strategic play. We additionally design a hierarchical policy which achieves 69.5% win rate against the strongest baseline in the 3 vs 3 task, demonstrating its potential for tackling the complex interplay between low-level control and high-level strategy. To highlight VolleyBots' sim-to-real potential, we further demonstrate the zero-shot deployment of a policy trained entirely in simulation on real-world drones.

cs.RO↗

arXiv2026

Mastering Multi-Drone Volleyball through Hierarchical Co-Self-Play Reinforcement Learning

In this paper, we tackle the problem of learning to play 3v3 multi-drone volleyball, a new embodied competitive task that requires both high-level strategic coordination and low-level agile control. The task is turn-based, multi-agent, and physically grounded, posing significant challenges due to its long-horizon dependencies, tight inter-agent coupling, and the underactuated dynamics of quadrotors. To address this, we propose Hierarchical Co-Self-Play (HCSP), a hierarchical reinforcement learning framework that separates centralized high-level strategic decision-making from decentralized low-level motion control. We design a three-stage population-based training pipeline to enable both strategy and skill to emerge from scratch without expert demonstrations: (I) training diverse low-level skills, (II) learning high-level strategy via self-play with fixed low-level skills, and (III) joint fine-tuning through co-self-play. Experiments show that HCSP achieves superior performance, outperforming non-hierarchical self-play and rule-based hierarchical baselines with an average 82.9% win rate and a 71.5% win rate against the two-stage variant. Moreover, co-self-play leads to emergent team behaviors such as role switching and coordinated formations, demonstrating the effectiveness of our hierarchical design and training scheme. The project page is at https://hi-co-self-play.github.io.

cs.AI↗

arXiv2026

MLICv2: Enhanced Multi-Reference Entropy Modeling for Learned Image Compression

Recent advances in learned image compression (LIC) have achieved remarkable performance improvements over traditional codecs. Notably, the MLIC series-LICs equipped with multi-reference entropy models-have substantially surpassed conventional image codecs such as Versatile Video Coding (VVC) Intra. However, existing MLIC variants suffer from several limitations: performance degradation at high bitrates due to insufficient transform capacity, suboptimal entropy modeling that fails to capture global correlations in initial slices, and lack of adaptive channel importance modeling. In this paper, we propose MLICv2 and MLICv2+, enhanced successors that systematically address these limitations through improved transform design, dvanced entropy modeling, and exploration of the potential of instance-specific optimization. For transform enhancement, we introduce a lightweight token mixing block inspired by the MetaFormer architecture, which effectively mitigates high-bitrate performance degradation while maintaining computational efficiency. For entropy modeling improvements, we propose hyperprior-guided global correlation prediction to extract global context even in the initial slice of latent representation, complemented by a channel reweighting module that dynamically emphasizes informative channels. We further explore enhanced positional embedding and guided selective compression strategies for superior context modeling. Additionally, we apply the Stochastic Gumbel Annealing (SGA) to demonstrate the potential for further performance improvements through input-specific optimization. Extensive experiments demonstrate that MLICv2 and MLICv2+ achieve state-of-the-art results, reducing Bjøntegaard-Delta Rate by 16.54%, 21.61%, 16.05% and 20.46%, 24.35%, 19.14% on Kodak, Tecnick, and CLIC Pro Val datasets, respectively, compared to VTM-17.0 Intra.

eess.IV↗

arXiv2026

MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling

Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body movements, long-range dynamics, and fine-grained human-environment interactions. This often leads to unrealistic or physically implausible movements with inadequate structural coherence. To conquer these challenges, we propose MoSA, which decouples the process of human video generation into two components, i.e., structure generation and appearance generation. MoSA first employs a 3D structure transformer to generate a human motion sequence from the text prompt. The remaining video appearance is then synthesized under the guidance of this structural sequence. We achieve fine-grained control over the sparse human structures by introducing Human-Aware Dynamic Control modules with a dense tracking constraint during training. The modeling of human-environment interactions is improved through the proposed contact constraint. Those two components work comprehensively to ensure the structural and appearance fidelity across the generated videos. This paper also contributes a large-scale human video dataset, which features more complex and diverse motions than existing human video datasets. We conduct comprehensive comparisons between MoSA and a variety of approaches, including general video generation models, human video generation models, and human animation models. Experiments demonstrate that MoSA substantially outperforms existing approaches across the majority of evaluation metrics.

cs.CV↗

arXiv2026

Generative Deep Learning for the Two-Dimensional Quantum Rotor Model

The advancement of diverse generative deep learning models and their variants has furnished substantial insights for investigating quantum many-body problems. In this work, we design two models based on the foundational architecture of generative adversarial networks (GANs) to investigate the ground-state properties and phase transition characteristics of the two-dimensional quantum rotor model (QRM). Within a semi-supervised learning framework, we incorporate multiple layers of transposed convolutions in the generator, enabling the conditional GAN to more efficiently extract low-dimensional encoded information. Analysis of one-dimensional latent variables associated with ground-state samples for different system sizes allows us to pinpoint the location of the critical point. In addition, we introduce dynamically adaptive weighting factors related to the distributional characteristics into the loss function of the deep convolutional GAN, and utilize upsampling techniques to enlarge the generated sample sizes. Comparisons of the optimization processes for mean magnetization and potential energy density across different magnetization regimes of QRM demonstrate that our model can efficiently generate valid ground-state samples, significantly reducing computational time. Our results highlight the promising potential of generative deep learning in quantum phase transition research, especially in critical point identification and the auxiliary generation of simulation data for quantum many-body models.

quant-ph↗

arXiv2026

WISDOM project -- XVIII. Molecular gas distributions and kinematics of three megamaser galaxies

The co-evolution of galaxies and supermassive black holes (SMBHs) underpins our understanding of galaxy evolution, but different methods to measure SMBH masses have only infrequently been cross-checked. We attempt to identify targets to cross-check two of the most accurate methods, megamaser and cold molecular gas dynamics. Three promising galaxies are selected from all those with existing megamaser SMBH mass measurements. We present Atacama Large Millimeter/sub-millimeter Array (ALMA) 12CO(2-1) and 230-GHz continuum observations with angular resolutions of about 0.5". Every galaxy has an extended rotating molecular gas disc and 230-GHz continuum source(s), but all also have irregularities and/or non-axisymmetric features: NGC1194 is highly inclined and has disturbed and lopsided central 12CO(2-1) emission; NGC3393 has a nuclear disc with fairly regular but patchy 12CO(2-1) emission with little gas near the kinematic major axis, faint emission in the very centre and two brighter structures reminiscent of a nuclear ring and/or spiral; NGC5765B has a strong bar and very bright 12CO(2-1) emission concentrated along two bisymmetric offset dust lanes and two bisymmetric nuclear spiral arms. 12CO(2-1) and 12CO(3-2) observations with the James Clerk Maxwell Telescope are compared with the ALMA observations. Because of the disturbed gas kinematics and the impractically long integration times required for higher angular resolution observations, none of the three galaxies is suitable for a future SMBH mass measurement. Nonetheless, increasing the number of molecular gas observations of megamaser galaxies is valuable, and the ubiquitous disturbances suggest a link between large-scale gas properties and the existence of megamasers.

astro-ph.GA↗

arXiv2026

Frequency-Enhanced Hilbert Scanning Mamba for Short-Term Arctic Sea Ice Concentration Prediction

While Mamba models offer efficient sequence modeling, vanilla versions struggle with temporal correlations and boundary details in Arctic sea ice concentration (SIC) prediction. To address these limitations, we propose Frequency-enhanced Hilbert scanning Mamba Framework (FH-Mamba) for short-term Arctic SIC prediction. Specifically, we introduce a 3D Hilbert scan mechanism that traverses the 3D spatiotemporal grid along a locality-preserving path, ensuring that adjacent indices in the flattened sequence correspond to neighboring voxels in both spatial and temporal dimensions. Additionally, we incorporate wavelet transform to amplify high-frequency details and we also design a Hybrid Shuffle Attention module to adaptively aggregate sequence and frequency features. Experiments conducted on the OSI-450a1 and AMSR2 datasets demonstrate that our FH-Mamba achieves superior prediction performance compared with state-of-the-art baselines. The results confirm the effectiveness of Hilbert scanning and frequency-aware attention in improving both temporal consistency and edge reconstruction for Arctic SIC forecasting. Our codes are publicly available at https://github.com/oucailab/FH-Mamba.

eess.IV↗

arXiv2026

Enhancing Underwater Images via Adaptive Semantic-aware Codebook Learning

Underwater Image Enhancement (UIE) is an ill-posed problem where natural clean references are not available, and the degradation levels vary significantly across semantic regions. Existing UIE methods treat images with a single global model and ignore the inconsistent degradation of different scene components. This oversight leads to significant color distortions and loss of fine details in heterogeneous underwater scenes, especially where degradation varies significantly across different image regions. Therefore, we propose SUCode (Semantic-aware Underwater Codebook Network), which achieves adaptive UIE from semantic-aware discrete codebook representation. Compared with one-shot codebook-based methods, SUCode exploits semantic-aware, pixel-level codebook representation tailored to heterogeneous underwater degradation. A three-stage training paradigm is employed to represent raw underwater image features to avoid pseudo ground-truth contamination. Gated Channel Attention Module (GCAM) and Frequency-Aware Feature Fusion (FAFF) jointly integrate channel and frequency cues for faithful color restoration and texture recovery. Extensive experiments on multiple benchmarks demonstrate that SUCode achieves state-of-the-art performance, outperforming recent UIE methods on both reference and no-reference metrics. The code will be made public available at https://github.com/oucailab/SUCode.

cs.CV↗

arXiv2026

ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting

Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded regions. While state-of-the-art generative models can synthesize auxiliary views to provide additional supervision, these views inevitably contain geometric inconsistencies and textural misalignments that propagate and amplify artifacts during 3D reconstruction. To effectively harness these imperfect supervisory signals, we propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO. Specifically, ERGO decomposes the optimization losses in 3D Gaussian splatting into two components, i.e., excess risk that quantifies the suboptimality gap between current and optimal parameters, and Bayes error that models the irreducible noise inherent in synthesized views. This decomposition enables ERGO to dynamically estimate the view-specific excess risk and adaptively adjust loss weights during optimization. Furthermore, we introduce geometry-aware and texture-aware objectives that complement the excess-risk-derived weighting mechanism, establishing a synergistic global-local optimization paradigm. Consequently, ERGO demonstrates robustness against supervision noise while consistently enhancing both geometric fidelity and textural quality of the reconstructed 3D content. Extensive experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.

cs.CV↗

arXiv2026

VISION-ICE: Video-based Interpretation and Spatial Identification of Arrhythmia Origins via Neural Networks in Intracardiac Echocardiography

Contemporary high-density mapping techniques and preoperative CT/MRI remain time and resource intensive in localizing arrhythmias. AI has been validated as a clinical decision aid in providing accurate, rapid real-time analysis of echocardiographic images. Building on this, we propose an AI-enabled framework that leverages intracardiac echocardiography (ICE), a routine part of electrophysiology procedures, to guide clinicians toward areas of arrhythmogenesis and potentially reduce procedural time. Arrhythmia source localization is formulated as a three-class classification task, distinguishing normal sinus rhythm, left-sided, and right-sided arrhythmias, based on ICE video data. We developed a 3D Convolutional Neural Network trained to discriminate among the three aforementioned classes. In ten-fold cross-validation, the model achieved a mean accuracy of 66.2% when evaluated on four previously unseen patients (substantially outperforming the 33.3% random baseline). These results demonstrate the feasibility and clinical promise of using ICE videos combined with deep learning for automated arrhythmia localization. Leveraging ICE imaging could enable faster, more targeted electrophysiological interventions and reduce the procedural burden of cardiac ablation. Future work will focus on expanding the dataset to improve model robustness and generalizability across diverse patient populations.

cs.CV↗