Feng Gao

Xuanyi Liu, Deyi Ji, Liqun Liu et al.

Sparse camera-conditioned image-to-video generation presents a pivotal challenge: synthesizing geometrically consistent 3D motion from minimal pose cues. Existing methods, which largely rely on dense supervision or naive interpolation, suffer from severe pose drift and motion discontinuities due to the lack of robust 3D priors. In this paper, we introduce CamGeo, a novel framework that distills rich 3D geometric knowledge from a pre-trained video-to-3D model (VGGT) directly into the diffusion backbone. To achieve this without incurring inference latency, we propose a training-only distillation strategy. Specifically, CamGeo incorporates: (1) keyframe trajectory distillation that enforces cycle-consistency with sparse input poses, (2) cross-frame consistency distillation with both camera trajectory and depth constraints to generate consistent structure across unsupervised frames, and (3) a three-stage coarse-to-fine curriculum learning, progressively scales geometric complexity, from global structure coherence to fine-grained refinement, achieving stable optimization. Extensive experiments demonstrate that CamGeo achieves consistent improvements under various sparsity ratios.

Meng Wang, Feng Gao, Junyu Dong et al.

The joint hyperspectral image (HSI) and LiDAR data classification aims to interpret ground objects at more detailed and precise level. Although deep learning methods have shown remarkable success in the multisource data classification task, self-supervised learning has rarely been explored. It is commonly nontrivial to build a robust self-supervised learning model for multisource data classification, due to the fact that the semantic similarities of neighborhood regions are not exploited in existing contrastive learning framework. Furthermore, the heterogeneous gap induced by the inconsistent distribution of multisource data impedes the classification performance. To overcome these disadvantages, we propose a Nearest Neighbor-based Contrastive Learning Network (NNCNet), which takes full advantage of large amounts of unlabeled data to learn discriminative feature representations. Specifically, we propose a nearest neighbor-based data augmentation scheme to use enhanced semantic relationships among nearby regions. The intermodal semantic alignments can be captured more accurately. In addition, we design a bilinear attention module to exploit the second-order and even high-order feature interactions between the HSI and LiDAR data. Extensive experiments on four public datasets demonstrate the superiority of our NNCNet over state-of-the-art methods. The source codes are available at \url{https://github.com/summitgao/NNCNet}.

Ruifei Zhang, Peiwen Lai, Xiang Wan et al.

Automatic and accurate polyp segmentation plays an essential role in early colorectal cancer diagnosis. However, it has always been a challenging task due to 1) the diverse shape, size, brightness and other appearance characteristics of polyps, 2) the tiny contrast between concealed polyps and their surrounding regions. To address these problems, we propose a lesion-aware dynamic network (LDNet) for polyp segmentation, which is a traditional u-shape encoder-decoder structure incorporated with a dynamic kernel generation and updating scheme. Specifically, the designed segmentation head is conditioned on the global context features of the input image and iteratively updated by the extracted lesion features according to polyp segmentation predictions. This simple but effective scheme endows our model with powerful segmentation performance and generalization capability. Besides, we utilize the extracted lesion representation to enhance the feature contrast between the polyp and background regions by a tailored lesion-aware cross-attention module (LCA), and design an efficient self-attention module (ESA) to capture long-range context relations, further improving the segmentation accuracy. Extensive experiments on four public polyp benchmarks and our collected large-scale polyp dataset demonstrate the superior performance of our method compared with other state-of-the-art approaches. The source code is available at https://github.com/ReaFly/LDNet.

Desen Meng, Feng Gao, Junyu Dong et al.

Recently, change detection methods for synthetic aperture radar (SAR) images based on convolutional neural networks (CNN) have gained increasing research attention. However, existing CNN-based methods neglect the interactions among multilayer convolutions, and errors involved in the preclassification restrict the network optimization. To this end, we proposed a layer attention-based noise-tolerant network, termed LANTNet. In particular, we design a layer attention module that adaptively weights the feature of different convolution layers. In addition, we design a noise-tolerant loss function that effectively suppresses the impact of noisy labels. Therefore, the model is insensitive to noisy labels in the preclassification results. The experimental results on three SAR datasets show that the proposed LANTNet performs better compared to several state-of-the-art methods. The source codes are available at https://github.com/summitgao/LANTNet

Fengtao Zhou, Yingxue Xu, Zhengyu Zhang et al.

Comprehensive molecular profiling is essential for modern precision oncology but remains hindered by prohibitive costs, specimen exhaustion, and protracted turnaround times. While pathology foundation models (PFMs) have demonstrated potential for inferring molecular phenotypes from routine hematoxylin and eosin (H&E) whole-slide images (WSIs), current architectures primarily rely on vision-centric self-supervised learning or vision-language alignment, lacking the spatially resolved molecular supervision required to connect subtle morphological features with underlying genomic alterations. Spatial transcriptomics (ST) emerges as a transformative technology that enables transcriptomic quantification within intact tissue sections, thereby preserving the precise spatial link between histology and molecular profiles. In this study, we present a Spatial Transcriptomics-guided Alignment framework for Molecular Profiling (STAMP), which endows PFMs with intrinsic molecular awareness. To support this paradigm, we curated HumanST-1k, a human ST dataset spanning diverse anatomical organs and sequencing platforms. This atlas yields 1.8 million pairs of H&E patches and corresponding transcriptomic profiles, providing a corpus that links histological structures with their molecular states. To mitigate the technical noise inherent to raw transcriptomics, STAMP applies a pathway-informed alignment strategy that aggregates transcriptomic data into biologically functional pathways, which are subsequently integrated into PFMs via parameter-efficient fine-tuning. This alignment enriches the representation space of PFMs and unlocks their capacity to resolve sub-visual molecular signatures. The clinical utility of these augmented representations was validated through a multi-tier evaluation framework.

Botian Xu, Feng Gao, Chao Yu et al. · tsinghua

In this work, we introduce OmniDrones, an efficient and flexible platform tailored for reinforcement learning in drone control, built on Nvidia's Omniverse Isaac Sim. It employs a bottom-up design approach that allows users to easily design and experiment with various application scenarios on top of GPU-parallelized simulations. It also offers a range of benchmark tasks, presenting challenges ranging from single-drone hovering to over-actuated system tracking. In summary, we propose an open-sourced drone simulation platform, equipped with an extensive suite of tools for drone learning. It includes 4 drone models, 5 sensor modalities, 4 control modes, over 10 benchmark tasks, and a selection of widely used RL baselines. To showcase the capabilities of OmniDrones and to support future research, we also provide preliminary results on these benchmark tasks. We hope this platform will encourage further studies on applying RL to practical drone systems.

Wei Jiang, Jiayu Yang, Yongqi Zhai et al.

Recently, learned image compression has achieved remarkable performance. The entropy model, which estimates the distribution of the latent representation, plays a crucial role in boosting rate-distortion performance. However, most entropy models only capture correlations in one dimension, while the latent representation contain channel-wise, local spatial, and global spatial correlations. To tackle this issue, we propose the Multi-Reference Entropy Model (MEM) and the advanced version, MEM$^+$. These models capture the different types of correlations present in latent representation. Specifically, We first divide the latent representation into slices. When decoding the current slice, we use previously decoded slices as context and employ the attention map of the previously decoded slice to predict global correlations in the current slice. To capture local contexts, we introduce two enhanced checkerboard context capturing techniques that avoids performance degradation. Based on MEM and MEM$^+$, we propose image compression models MLIC and MLIC$^+$. Extensive experimental evaluations demonstrate that our MLIC and MLIC$^+$ models achieve state-of-the-art performance, reducing BD-rate by $8.05\%$ and $11.39\%$ on the Kodak dataset compared to VTM-17.0 when measured in PSNR. Our code is available at https://github.com/JiangWeibeta/MLIC.

Haodong Pan, Feng Gao, Junyu Dong et al.

Removing the noise and improving the visual quality of hyperspectral images (HSIs) is challenging in academia and industry. Great efforts have been made to leverage local, global or spectral context information for HSI denoising. However, existing methods still have limitations in feature interaction exploitation among multiple scales and rich spectral structure preservation. In view of this, we propose a novel solution to investigate the HSI denoising using a Multi-scale Adaptive Fusion Network (MAFNet), which can learn the complex nonlinear mapping between clean and noisy HSI. Two key components contribute to improving the hyperspectral image denoising: A progressively multiscale information aggregation network and a co-attention fusion module. Specifically, we first generate a set of multiscale images and feed them into a coarse-fusion network to exploit the contextual texture correlation. Thereafter, a fine fusion network is followed to exchange the information across the parallel multiscale subnetworks. Furthermore, we design a co-attention fusion module to adaptively emphasize informative features from different scales, and thereby enhance the discriminative learning capability for denoising. Extensive experiments on synthetic and real HSI datasets demonstrate that the proposed MAFNet has achieved better denoising performance than other state-of-the-art techniques. Our codes are available at \verb'https://github.com/summitgao/MAFNet'.

Junyan Lin, Feng Gao, Xiaocheng Shi et al.

Masked image modeling (MIM) is a highly popular and effective self-supervised learning method for image understanding. Existing MIM-based methods mostly focus on spatial feature modeling, neglecting spectral feature modeling. Meanwhile, existing MIM-based methods use Transformer for feature extraction, some local or high-frequency information may get lost. To this end, we propose a spatial-spectral masked auto-encoder (SS-MAE) for HSI and LiDAR/SAR data joint classification. Specifically, SS-MAE consists of a spatial-wise branch and a spectral-wise branch. The spatial-wise branch masks random patches and reconstructs missing pixels, while the spectral-wise branch masks random spectral channels and reconstructs missing channels. Our SS-MAE fully exploits the spatial and spectral representations of the input data. Furthermore, to complement local features in the training stage, we add two lightweight CNNs for feature extraction. Both global and local features are taken into account for feature modeling. To demonstrate the effectiveness of the proposed SS-MAE, we conduct extensive experiments on three publicly available datasets. Extensive experiments on three multi-source datasets verify the superiority of our SS-MAE compared with several state-of-the-art baselines. The source codes are available at \url{https://github.com/summitgao/SS-MAE}.

Wentao Liu, Tong Tian, Lemeng Wang et al.

The automated segmentation of Intracranial Arteries (IA) in Digital Subtraction Angiography (DSA) plays a crucial role in the quantification of vascular morphology, significantly contributing to computer-assisted stroke research and clinical practice. Current research primarily focuses on the segmentation of single-frame DSA using proprietary datasets. However, these methods face challenges due to the inherent limitation of single-frame DSA, which only partially displays vascular contrast, thereby hindering accurate vascular structure representation. In this work, we introduce DIAS, a dataset specifically developed for IA segmentation in DSA sequences. We establish a comprehensive benchmark for evaluating DIAS, covering full, weak, and semi-supervised segmentation methods. Specifically, we propose the vessel sequence segmentation network, in which the sequence feature extraction module effectively captures spatiotemporal representations of intravascular contrast, achieving intracranial artery segmentation in 2D+Time DSA sequences. For weakly-supervised IA segmentation, we propose a novel scribble learning-based image segmentation framework, which, under the guidance of scribble labels, employs cross pseudo-supervision and consistency regularization to improve the performance of the segmentation network. Furthermore, we introduce the random patch-based self-training framework, aimed at alleviating the performance constraints encountered in IA segmentation due to the limited availability of annotated DSA data. Our extensive experiments on the DIAS dataset demonstrate the effectiveness of these methods as potential baselines for future research and clinical applications. The dataset and code are publicly available at https://doi.org/10.5281/zenodo.11396520 and https://github.com/lseventeen/DIAS.

Haopeng Zhang, Zijing Lin, Feng Gao et al.

Synthetic aperture radar (SAR) image change detection is a critical task and has received increasing attentions in the remote sensing community. However, existing SAR change detection methods are mainly based on convolutional neural networks (CNNs), with limited consideration of global attention mechanism. In this letter, we explore Transformer-like architecture for SAR change detection to incorporate global attention. To this end, we propose a convolution and attention mixer (CAMixer). First, to compensate the inductive bias for Transformer, we combine self-attention with shift convolution in a parallel way. The parallel design effectively captures the global semantic information via the self-attention and performs local feature extraction through shift convolution simultaneously. Second, we adopt a gating mechanism in the feed-forward network to enhance the non-linear feature transformation. The gating mechanism is formulated as the element-wise multiplication of two parallel linear layers. Important features can be highlighted, leading to high-quality representations against speckle noise. Extensive experiments conducted on three SAR datasets verify the superior performance of the proposed CAMixer. The source codes will be publicly available at https://github.com/summitgao/CAMixer .

Jiangwei Xie, Feng Gao, Xiaowei Zhou et al.

Synthetic aperture radar (SAR) image change detection is critical in remote sensing image analysis. Recently, the attention mechanism has been widely used in change detection tasks. However, existing attention mechanisms often employ down-sampling operations such as average pooling on the Key and Value components to enhance computational efficiency. These irreversible operations result in the loss of high-frequency components and other important information. To address this limitation, we develop Wavelet-based Bi-dimensional Aggregation Network (WBANet) for SAR image change detection. We design a wavelet-based self-attention block that includes discrete wavelet transform and inverse discrete wavelet transform operations on Key and Value components. Hence, the feature undergoes downsampling without any loss of information, while simultaneously enhancing local contextual awareness through an expanded receptive field. Additionally, we have incorporated a bi-dimensional aggregation module that boosts the non-linear representation capability by merging spatial and channel information via broadcast mechanism. Experimental results on three SAR datasets demonstrate that our WBANet significantly outperforms contemporary state-of-the-art methods. Specifically, our WBANet achieves 98.33\%, 96.65\%, and 96.62\% of percentage of correct classification (PCC) on the respective datasets, highlighting its superior performance. Source codes are available at \url{https://github.com/summitgao/WBANet}.

Meituan LongCat Team, Xunliang Cai, Meng Cheng et al.

Despite advances in audio-driven video generation, achieving commercial-grade stability remains challenging. We present LongCat-Video-Avatar 1.5, an upgraded open-source framework prioritizing systematic engineering and production-readiness over architectural novelty. By upgrading the audio encoder to Whisper Large and meticulously scaling our training recipes, v1.5 achieves accurate lip-synchronization, full-body temporal stability, and robust long-video generation with strict identity consistency. Through rigorous data curation and RLHF Training, the model readily generalizes to stylized domains such as anime and animals, and natively handles complex real-world conditions, such as multi-person interactions and object handling. Furthermore, addressing the practical demands of industrial deployment, we employ advanced step distillation to accelerate inference to an optimal 8 NFE, achieving a favorable trade-off between serving efficiency and visual fidelity. The superiority of our approach is validated through extensive quantitative metrics and a rigorous human evaluation conducted on a comprehensive benchmark of over 500 diverse test cases. Results show that v1.5 achieves competitive or superior performance compared to leading closed-source systems (e.g., HeyGen, OmniHuman 1.5, Kling Avatar 2.0) across human-likeness ratings and expert-level quality assessments on our benchmark. With its open-source release, LongCat-Video-Avatar 1.5 narrows the gap between academic research prototypes and commercial-grade deployment.

Wei Jiang, Jiayu Yang, Yongqi Zhai et al.

The latent representation in learned image compression encompasses channel-wise, local spatial, and global spatial correlations, which are essential for the entropy model to capture for conditional entropy minimization. Efficiently capturing these contexts within a single entropy model, especially in high-resolution image coding, presents a challenge due to the computational complexity of existing global context modules. To address this challenge, we propose the Linear Complexity Multi-Reference Entropy Model (MEM$^{++}$). Specifically, the latent representation is partitioned into multiple slices. For channel-wise contexts, previously compressed slices serve as the context for compressing a particular slice. For local contexts, we introduce a shifted-window-based checkerboard attention module. This module ensures linear complexity without sacrificing performance. For global contexts, we propose a linear complexity attention mechanism. It captures global correlations by decomposing the softmax operation, enabling the implicit computation of attention maps from previously decoded slices. Using MEM$^{++}$ as the entropy model, we develop the image compression method MLIC$^{++}$. Extensive experimental results demonstrate that MLIC$^{++}$ achieves state-of-the-art performance, reducing BD-rate by $13.39\%$ on the Kodak dataset compared to VTM-17.0 in Peak Signal-to-Noise Ratio (PSNR). Furthermore, MLIC$^{++}$ exhibits linear computational complexity and memory consumption with resolution, making it highly suitable for high-resolution image coding. Code and pre-trained models are available at https://github.com/JiangWeibeta/MLIC. Training dataset is available at https://huggingface.co/datasets/Whiteboat/MLIC-Train-100K.

Aoyang Qin, Feng Gao, Qing Li et al.

Conventional imitation learning assumes access to the actions of demonstrators, but these motor signals are often non-observable in naturalistic settings. Additionally, sequential decision-making behaviors in these settings can deviate from the assumptions of a standard Markov Decision Process (MDP). To address these challenges, we explore deep generative modeling of state-only sequences with non-Markov Decision Process (nMDP), where the policy is an energy-based prior in the latent space of the state transition generator. We develop maximum likelihood estimation to achieve model-based imitation, which involves short-run MCMC sampling from the prior and importance sampling for the posterior. The learned model enables \textit{decision-making as inference}: model-free policy execution is equivalent to prior sampling, model-based planning is posterior sampling initialized from the policy. We demonstrate the efficacy of the proposed method in a prototypical path planning task with non-Markovian constraints and show that the learned model exhibits strong performances in challenging domains from the MuJoCo suite.

Yuxin Meng, Feng Gao, Eric Rigall et al.

Traditionally, numerical models have been deployed in oceanography studies to simulate ocean dynamics by representing physical equations. However, many factors pertaining to ocean dynamics seem to be ill-defined. We argue that transferring physical knowledge from observed data could further improve the accuracy of numerical models when predicting Sea Surface Temperature (SST). Recently, the advances in earth observation technologies have yielded a monumental growth of data. Consequently, it is imperative to explore ways in which to improve and supplement numerical models utilizing the ever-increasing amounts of historical observational data. To this end, we introduce a method for SST prediction that transfers physical knowledge from historical observations to numerical models. Specifically, we use a combination of an encoder and a generative adversarial network (GAN) to capture physical knowledge from the observed data. The numerical model data is then fed into the pre-trained model to generate physics-enhanced data, which can then be used for SST prediction. Experimental results demonstrate that the proposed method considerably enhances SST prediction performance when compared to several state-of-the-art baselines.

Qinyuan Cheng, Linyang Li, Guofeng Quan et al.

Task-Oriented Dialogue (TOD) systems are drawing more and more attention in recent studies. Current methods focus on constructing pre-trained models or fine-tuning strategies while the evaluation of TOD is limited by a policy mismatch problem. That is, during evaluation, the user utterances are from the annotated dataset while these utterances should interact with previous responses which can have many alternatives besides annotated texts. Therefore, in this work, we propose an interactive evaluation framework for TOD. We first build a goal-oriented user simulator based on pre-trained models and then use the user simulator to interact with the dialogue system to generate dialogues. Besides, we introduce a sentence-level and a session-level score to measure the sentence fluency and session coherence in the interactive evaluation. Experimental results show that RL-based TOD systems trained by our proposed user simulator can achieve nearly 98% inform and success rates in the interactive evaluation of MultiWOZ dataset and the proposed scores measure the response quality besides the inform and success rates. We are hoping that our work will encourage simulator-based interactive evaluations in the TOD task.

Da Yin, Feng Gao, Govind Thattai et al.

A key goal for the advancement of AI is to develop technologies that serve the needs not just of one group but of all communities regardless of their geographical region. In fact, a significant proportion of knowledge is locally shared by people from certain regions but may not apply equally in other regions because of cultural differences. If a model is unaware of regional characteristics, it may lead to performance disparity across regions and result in bias against underrepresented groups. We propose GIVL, a Geographically Inclusive Vision-and-Language Pre-trained model. There are two attributes of geo-diverse visual concepts which can help to learn geo-diverse knowledge: 1) concepts under similar categories have unique knowledge and visual characteristics, 2) concepts with similar visual features may fall in completely different categories. Motivated by the attributes, we design new pre-training objectives Image Knowledge Matching (IKM) and Image Edit Checking (IEC) to pre-train GIVL. Compared with similar-size models pre-trained with similar scale of data, GIVL achieves state-of-the-art (SOTA) and more balanced performance on geo-diverse V&L tasks.

Junjie Wang, Feng Gao, Junyu Dong et al.

Benefited from the rapid and sustainable development of synthetic aperture radar (SAR) sensors, change detection from SAR images has received increasing attentions over the past few years. Existing unsupervised deep learning-based methods have made great efforts to exploit robust feature representations, but they consume much time to optimize parameters. Besides, these methods use clustering to obtain pseudo-labels for training, and the pseudo-labeled samples often involve errors, which can be considered as "label noise". To address these issues, we propose a Dual Path Denoising Network (DPDNet) for SAR image change detection. In particular, we introduce the random label propagation to clean the label noise involved in preclassification. We also propose the distinctive patch convolution for feature representation learning to reduce the time consumption. Specifically, the attention mechanism is used to select distinctive pixels in the feature maps, and patches around these pixels are selected as convolution kernels. Consequently, the DPDNet does not require a great number of training samples for parameter optimization, and its computational efficiency is greatly enhanced. Extensive experiments have been conducted on five SAR datasets to verify the proposed DPDNet. The experimental results demonstrate that our method outperforms several state-of-the-art methods in change detection results.

Lin Qi, Xuewen Qin, Feng Gao et al.

Hyperspectral unmixing is a critical yet challenging task in hyperspectral image interpretation. Recently, great efforts have been made to solve the hyperspectral unmixing task via deep autoencoders. However, existing networks mainly focus on extracting spectral features from mixed pixels, and the employment of spatial feature prior knowledge is still insufficient. To this end, we put forward a spatial attention weighted unmixing network, dubbed as SAWU-Net, which learns a spatial attention network and a weighted unmixing network in an end-to-end manner for better spatial feature exploitation. In particular, we design a spatial attention module, which consists of a pixel attention block and a window attention block to efficiently model pixel-based spectral information and patch-based spatial information, respectively. While in the weighted unmixing framework, the central pixel abundance is dynamically weighted by the coarse-grained abundances of surrounding pixels. In addition, SAWU-Net generates dynamically adaptive spatial weights through the spatial attention mechanism, so as to dynamically integrate surrounding pixels more effectively. Experimental results on real and synthetic datasets demonstrate the better accuracy and superiority of SAWU-Net, which reflects the effectiveness of the proposed spatial attention mechanism.

Dongdong Hua, Yifei Sun, Renhong Huang et al.

Given a strategically complex board game, human players can quickly learn to devise strategies after playing a few rounds. Autonomous agents require similar capabilities in realistic interactive environments, yet existing agent benchmarks often fail to fully capture such strategic and evolving decision-making scenarios. We present PTCG-Bench, a benchmark built on the Pok'{e}mon Trading Card Game (PTCG) that evaluates LLM agents at two complementary levels: (1) their decision-making performance within a single complex environment, and (2) their ability to self-evolving through accumulated experience. We further include a modular harness ablation to better interpret agent performance without conflating it with model capability. Our experiments show that, although LLM agents can achieve non-trivial gameplay performance, sustained and stable self-evolution remains challenging, and performance is sensitive to harness design. We hope that PTCG-Bench will facilitate future research on harness-aware and self-evolving agents in realistic interactive environments.

Hui Zhang, Lingxiao Wan, Sergi Ramos-Calderer et al.

In the modern financial industry system, the structure of products has become more and more complex, and the bottleneck constraint of classical computing power has already restricted the development of the financial industry. Here, we present a photonic chip that implements the unary approach to European option pricing, in combination with the quantum amplitude estimation algorithm, to achieve a quadratic speedup compared to classical Monte Carlo methods. The circuit consists of three modules: a module loading the distribution of asset prices, a module computing the expected payoff, and a module performing the quantum amplitude estimation algorithm to introduce speed-ups. In the distribution module, a generative adversarial network is embedded for efficient learning and loading of asset distributions, which precisely capture the market trends. This work is a step forward in the development of specialized photonic processors for applications in finance, with the potential to improve the efficiency and quality of financial services.

Weizhi Zhong, Jichang Li, Yinqi Cai et al.

Audio-driven lip sync has recently drawn significant attention due to its widespread application in the multimedia domain. Individuals exhibit distinct lip shapes when speaking the same utterance, attributed to the unique speaking styles of individuals, posing a notable challenge for audio-driven lip sync. Earlier methods for such task often bypassed the modeling of personalized speaking styles, resulting in sub-optimal lip sync conforming to the general styles. Recent lip sync techniques attempt to guide the lip sync for arbitrary audio by aggregating information from a style reference video, yet they can not preserve the speaking styles well due to their inaccuracy in style aggregation. This work proposes an innovative audio-aware style reference scheme that effectively leverages the relationships between input audio and reference audio from style reference video to address the style-preserving audio-driven lip sync. Specifically, we first develop an advanced Transformer-based model adept at predicting lip motion corresponding to the input audio, augmented by the style information aggregated through cross-attention layers from style reference video. Afterwards, to better render the lip motion into realistic talking face video, we devise a conditional latent diffusion model, integrating lip motion through modulated convolutional layers and fusing reference facial images via spatial cross-attention layers. Extensive experiments validate the efficacy of the proposed approach in achieving precise lip sync, preserving speaking styles, and generating high-fidelity, realistic talking face videos.

Wei Lou, Xiang Wan, Guanbin Li et al.

Nuclei classification provides valuable information for histopathology image analysis. However, the large variations in the appearance of different nuclei types cause difficulties in identifying nuclei. Most neural network based methods are affected by the local receptive field of convolutions, and pay less attention to the spatial distribution of nuclei or the irregular contour shape of a nucleus. In this paper, we first propose a novel polygon-structure feature learning mechanism that transforms a nucleus contour into a sequence of points sampled in order, and employ a recurrent neural network that aggregates the sequential change in distance between key points to obtain learnable shape features. Next, we convert a histopathology image into a graph structure with nuclei as nodes, and build a graph neural network to embed the spatial distribution of nuclei into their representations. To capture the correlations between the categories of nuclei and their surrounding tissue patterns, we further introduce edge features that are defined as the background textures between adjacent nuclei. Lastly, we integrate both polygon and graph structure learning mechanisms into a whole framework that can extract intra and inter-nucleus structural characteristics for nuclei classification. Experimental results show that the proposed framework achieves significant improvements compared to the state-of-the-art methods.

Chen Liu, Matthew Amodio, Liangbo L. Shen et al.

Segmenting medical images is critical to facilitating both patient diagnoses and quantitative research. A major limiting factor is the lack of labeled data, as obtaining expert annotations for each new set of imaging data and task can be labor intensive and inconsistent among annotators. We present CUTS, an unsupervised deep learning framework for medical image segmentation. CUTS operates in two stages. For each image, it produces an embedding map via intra-image contrastive learning and local patch reconstruction. Then, these embeddings are partitioned at dynamic granularity levels that correspond to the data topology. CUTS yields a series of coarse-to-fine-grained segmentations that highlight features at various granularities. We applied CUTS to retinal fundus images and two types of brain MRI images to delineate structures and patterns at different scales. When evaluated against predefined anatomical masks, CUTS improved the dice coefficient and Hausdorff distance by at least 10% compared to existing unsupervised methods. Finally, CUTS showed performance on par with Segment Anything Models (SAM, MedSAM, SAM-Med2D) pre-trained on gigantic labeled datasets.

Baogui Huan, Chuanzheng Gong, Dezhong Chen et al.

Convolutional neural networks (CNNs) have been extensively and successfully applied to the task of synthetic aperture radar (SAR) image change detection. However, conventional convolutional layers are inherently limited by their local receptive fields, which mainly capture spatially localized patterns while neglecting the global context that is often crucial for accurately distinguishing subtle or large-scale changes in SAR imagery. To address these limitations, we propose a novel Global Dynamic Context-Aware Network (GDNet) specifically tailored for SAR image change detection. At the core of our approach lies a novel global dynamic convolution module, which adaptively modulates convolution kernel weights according to the global semantic information extracted from the input features. By dynamically incorporating long-range dependencies, this mechanism enables the network to integrate both local detail and global context, thus improving its ability to detect diverse change patterns. In addition, we introduce a carefully designed two-stage Mixup strategy for model training. Unlike conventional single-stage Mixup, our two-stage design generates more diverse and informative training samples, effectively regularizing the model and yielding more stable and reliable classification results even under limited data scenarios. Extensive experiments on three SAR datasets demonstrate the superiority of the proposed GDNet compared to other state-of-the-art methods. These findings highlight the potential of global dynamic modeling and advanced data augmentation strategies for advancing SAR image interpretation. Source codes are available at \url{https://github.com/oucailab/GDNet}.

Feng Gao, Zhilin Jin, Yanhai Gan et al.

Semantic segmentation of multi-source remote sensing images is a fundamental task for Earth observation applications. Existing methods often struggle with insufficient multi-scale context modeling and suboptimal cross-modal feature fusion, limiting their performance in complex high-resolution scenes. To this end, we propose Axial-Relation Guided Fusion Mamba (ARG-Mamba), a state space model-based framework for optical-elevation remote sensing image segmentation. Specifically, we introduce a Multi-Scale State Space Module to capture both fine-grained local details and global contextual dependencies with linear computational complexity. Moreover, an Axial-Relation Guided Fusion Module is designed to explicitly model global cross-modal correlations along horizontal and vertical axes, enabling efficient feature fusion between optical and elevation modalities. Extensive experiments conducted on the ISPRS Vaihingen and Potsdam datasets demonstrate that our ARG-Mamba consistently outperforms state-of-the-art methods while maintaining favorable computational efficiency. The code will be made publicly available at \url{https://github.com/oucailab/ARG-Mamba}.

Wentao Zhu, Xiaoxuan Ma, Dongwoo Ro et al.

Human motion generation aims to generate natural human pose sequences and shows immense potential for real-world applications. Substantial progress has been made recently in motion data collection technologies and generation methods, laying the foundation for increasing interest in human motion generation. Most research within this field focuses on generating human motions based on conditional signals, such as text, audio, and scene contexts. While significant advancements have been made in recent years, the task continues to pose challenges due to the intricate nature of human motion and its implicit relationship with conditional signals. In this survey, we present a comprehensive literature review of human motion generation, which, to the best of our knowledge, is the first of its kind in this field. We begin by introducing the background of human motion and generative models, followed by an examination of representative methods for three mainstream sub-tasks: text-conditioned, audio-conditioned, and scene-conditioned human motion generation. Additionally, we provide an overview of common datasets and evaluation metrics. Lastly, we discuss open problems and outline potential future research directions. We hope that this survey could provide the community with a comprehensive glimpse of this rapidly evolving field and inspire novel ideas that address the outstanding challenges.

Yiran Shi, Dongqi Guo, Tianchen Zhao et al. · tsinghua

Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control. However, the high computational cost of VLA models poses significant efficiency challenges, particularly for resource-constrained edge platforms in real-world deployments. However, since different stages of VLA (observation, action generation and execution) must proceed sequentially, and wait for the completion of the preceding stage, the system suffers from frequent halting and high latency. To address this, We conduct a systematic analysis to identify the challenges for fast and fluent generation, and propose enabling VLAs with the ability to asynchronously parallelize across VLA stages in a "streaming" manner. First, we eliminate the reliance on action chunking and adopt action flow matching, which learns the trajectory of action flows rather than denoising chunk-wise actions. It overlaps the latency of action generation and execution. Second, we design an action saliency-aware adaptive observation mechanism, thereby overlapping the latency of execution and observation. Without sacrificing performance, StreamingVLA achieves substantial speedup and improves the fluency of execution. It achieves a 2.4 $\times$ latency speedup and reduces execution halting by 6.5 $\times$.

Jing Wang, Meichen Song, Feng Gao et al.

We initiate the study of how to perturb the reward in a zero-sum Markov game with two players to induce a desirable Nash equilibrium, namely arbitrating. Such a problem admits a bi-level optimization formulation. The lower level requires solving the Nash equilibrium under a given reward function, which makes the overall problem challenging to optimize in an end-to-end way. We propose a backpropagation scheme that differentiates through the Nash equilibrium, which provides the gradient feedback for the upper level. In particular, our method only requires a black-box solver for the (regularized) Nash equilibrium (NE). We develop the convergence analysis for the proposed framework with proper black-box NE solvers and demonstrate the empirical successes in two multi-agent reinforcement learning (MARL) environments.

Feng Gao, Zheng Gong, Wenli Liu et al.

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.

Bosen Lin, Feng Gao, Yanwei Yu et al.

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.

Bosen Lin, Feng Gao, Yanwei Yu et al.

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.

Shangqing Tong, Peng Ge, Yanan Jiao et al.

Colorectal cancer is a deadly disease that has become increasingly prevalent in recent years. Early detection is crucial for saving lives, but traditional diagnostic methods such as colonoscopy and biopsy have limitations. Colonoscopy cannot provide detailed information within the tissues affected by cancer, while biopsy involves tissue removal, which can be painful and invasive. In order to improve diagnostic efficiency and reduce patient suffering, we studied machine-learningbased approach for colorectal tissue classification that uses acoustic resolution photoacoustic microscopy (ARPAM). With this tool, we were able to classify benign and malignant tissue using multiple machine learning methods. Our results were analyzed both quantitatively and qualitatively to evaluate the effectiveness of our approach.

Yuxing Qiu, Feng Gao, Minchen Li et al.

Recent breakthroughs in Vision-Language (V&L) joint research have achieved remarkable results in various text-driven tasks. High-quality Text-to-video (T2V), a task that has been long considered mission-impossible, was proven feasible with reasonably good results in latest works. However, the resulting videos often have undesired artifacts largely because the system is purely data-driven and agnostic to the physical laws. To tackle this issue and further push T2V towards high-level physical realism, we present an autonomous data generation technique and a dataset, which intend to narrow the gap with a large number of multi-modal, 3D Text-to-Video/Simulation (T2V/S) data. In the dataset, we provide high-resolution 3D physical simulations for both solids and fluids, along with textual descriptions of the physical phenomena. We take advantage of state-of-the-art physical simulation methods (i) Incremental Potential Contact (IPC) and (ii) Material Point Method (MPM) to simulate diverse scenarios, including elastic deformations, material fractures, collisions, turbulence, etc. Additionally, high-quality, multi-view rendering videos are supplied for the benefit of T2V, Neural Radiance Fields (NeRF), and other communities. This work is the first step towards fully automated Text-to-Video/Simulation (T2V/S). Live examples and subsequent work are at https://sites.google.com/view/tpa-net.

Feng Gao, Jiaxu Leng, Ji Gan et al.

DEtection TRansformer (DETR) and its variants (DETRs) have been successfully applied to crowded pedestrian detection, which achieved promising performance. However, we find that, in different degrees of crowded scenes, the number of DETRs' queries must be adjusted manually, otherwise, the performance would degrade to varying degrees. In this paper, we first analyze the two current query generation methods and summarize four guidelines for designing the adaptive query generation method. Then, we propose Rank-based Adaptive Query Generation (RAQG) to alleviate the problem. Specifically, we design a rank prediction head that can predict the rank of the lowest confidence positive training sample produced by the encoder. Based on the predicted rank, we design an adaptive selection method that can adaptively select coarse detection results produced by the encoder to generate queries. Moreover, to train the rank prediction head better, we propose Soft Gradient L1 Loss. The gradient of Soft Gradient L1 Loss is continuous, which can describe the relationship between the loss value and the updated value of model parameters granularly. Our method is simple and effective, which can be plugged into any DETRs to make it query-adaptive in theory. The experimental results on Crowdhuman dataset and Citypersons dataset show that our method can adaptively generate queries for DETRs and achieve competitive results. Especially, our method achieves state-of-the-art 39.4% MR on Crowdhuman dataset.

Shuai Hu, Feng Gao, Xiaowei Zhou et al.

Hyperspectral image (HSI) denoising is critical for the effective analysis and interpretation of hyperspectral data. However, simultaneously modeling global and local features is rarely explored to enhance HSI denoising. In this letter, we propose a hybrid convolution and attention network (HCANet), which leverages both the strengths of convolution neural networks (CNNs) and Transformers. To enhance the modeling of both global and local features, we have devised a convolution and attention fusion module aimed at capturing long-range dependencies and neighborhood spectral correlations. Furthermore, to improve multi-scale information aggregation, we design a multi-scale feed-forward network to enhance denoising performance by extracting features at different scales. Experimental results on mainstream HSI datasets demonstrate the rationality and effectiveness of the proposed HCANet. The proposed model is effective in removing various types of complex noise. Our codes are available at \url{https://github.com/summitgao/HCANet}.

Rakesh Vaideeswaran, Feng Gao, Abhinav Mathur et al.

The domain of joint vision-language understanding, especially in the context of reasoning in Visual Question Answering (VQA) models, has garnered significant attention in the recent past. While most of the existing VQA models focus on improving the accuracy of VQA, the way models arrive at an answer is oftentimes a black box. As a step towards making the VQA task more explainable and interpretable, our method is built upon the SOTA VQA framework by augmenting it with an end-to-end explanation generation module. In this paper, we investigate two network architectures, including Long Short-Term Memory (LSTM) and Transformer decoder, as the explanation generator. Our method generates human-readable textual explanations while maintaining SOTA VQA accuracy on the GQA-REX (77.49%) and VQA-E (71.48%) datasets. Approximately 65.16% of the generated explanations are approved by humans as valid. Roughly 60.5% of the generated explanations are valid and lead to the correct answers.

Wei Jiang, Peirong Ning, Jiayu Yang et al.

The effective receptive field (ERF) plays an important role in transform coding, which determines how much redundancy can be removed during transform and how many spatial priors can be utilized to synthesize textures during inverse transform. Existing methods rely on stacks of small kernels, whose ERFs remain insufficiently large, or heavy non-local attention mechanisms, which limit the potential of high-resolution image coding. To tackle this issue, we propose Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compression (LLIC). Specifically, for the first time in the learned image compression community, we introduce a few large kernelbased depth-wise convolutions to reduce more redundancy while maintaining modest complexity. Due to the wide range of image diversity, we further propose a mechanism to augment convolution adaptability through the self-conditioned generation of weights. The large kernels cooperate with non-linear embedding and gate mechanisms for better expressiveness and lighter pointwise interactions. Our investigation extends to refined training methods that unlock the full potential of these large kernels. Moreover, to promote more dynamic inter-channel interactions, we introduce an adaptive channel-wise bit allocation strategy that autonomously generates channel importance factors in a self-conditioned manner. To demonstrate the effectiveness of the proposed transform coding, we align the entropy model to compare with existing transform methods and obtain models LLIC-STF, LLIC-ELIC, and LLIC-TCM. Extensive experiments demonstrate that our proposed LLIC models have significant improvements over the corresponding baselines and reduce the BD-Rate by 9.49%, 9.47%, 10.94% on Kodak over VTM-17.0 Intra, respectively. Our LLIC models achieve state-of-the-art performances and better trade-offs between performance and complexity.

Xiangyu Liu, Feng Gao, Xiaomei Zhang et al.

Existing audio-driven video digital human generation models rely on multi-step denoising, resulting in substantial computational overhead that severely limits their deployment in real-world settings. While one-step distillation approaches can significantly accelerate inference, they often suffer from training instability. To address this challenge, we propose TurboTalk, a two-stage progressive distillation framework that effectively compresses a multi-step audio-driven video diffusion model into a single-step generator. We first adopt Distribution Matching Distillation to obtain a strong and stable 4-step student, and then progressively reduce the denoising steps from 4 to 1 through adversarial distillation. To ensure stable training under extreme step reduction, we introduce a progressive timestep sampling strategy and a self-compare adversarial objective that provides an intermediate adversarial reference that stabilizes progressive distillation. Our method achieve single-step generation of video talking avatar, boosting inference speed by 120 times while maintaining high generation quality.

Peng Gao, Feng Gao, Jian-Cheng Ni et al.

Drug-drug interaction prediction is a crucial issue in molecular biology. Traditional methods of observing drug-drug interactions through medical experiments require significant resources and labor. This paper presents a medical knowledge graph question answering model, dubbed MedKGQA, that predicts drug-drug interaction by employing machine reading comprehension from closed-domain literature and constructing a knowledge graph of drug-protein triplets from open-domain documents. The model vectorizes the drug-protein target attributes in the graph using entity embeddings and establishes directed connections between drug and protein entities based on the metabolic interaction pathways of protein targets in the human body. This aligns multiple external knowledge and applies it to learn the graph neural network. Without bells and whistles, the proposed model achieved a 4.5% improvement in terms of drug-drug interaction prediction accuracy compared to previous state-of-the-art models on the Qangaroo MedHop dataset. Experimental results demonstrate the efficiency and effectiveness of the model and verify the feasibility of integrating external knowledge in machine reading comprehension tasks.

Haoru Wang, Wentao Zhu, Luyi Miao et al.

Human motion generation is a critical task with a wide range of applications. Achieving high realism in generated motions requires naturalness, smoothness, and plausibility. Despite rapid advancements in the field, current generation methods often fall short of these goals. Furthermore, existing evaluation metrics typically rely on ground-truth-based errors, simple heuristics, or distribution distances, which do not align well with human perceptions of motion quality. In this work, we propose a data-driven approach to bridge this gap by introducing a large-scale human perceptual evaluation dataset, MotionPercept, and a human motion critic model, MotionCritic, that capture human perceptual preferences. Our critic model offers a more accurate metric for assessing motion quality and could be readily integrated into the motion generation pipeline to enhance generation quality. Extensive experiments demonstrate the effectiveness of our approach in both evaluating and improving the quality of generated human motions by aligning with human perceptions. Code and data are publicly available at https://motioncritic.github.io/.

Chuanzheng Gong, Feng Gao, Junyan Lin et al.

Hyperspectral image (HSI) and SAR/LiDAR data offer complementary spectral and structural information for land-cover classification. However, their effective fusion remains challenging due to two major limitations: The spectral redundancy in high-dimensional HSI and the heterogeneous characteristics between multi-source data. To this end, we propose Representative Spectral Correlation Network (RSCNet), a novel multi-source image classification framework specifically designed to address the above challenges through spectral selection and adaptive interaction. The network incorporates two key components: (1) Key Band Selection Module (KBSM) that adaptively selects task-relevant spectral bands from the original HSI under cross-source guidance, thereby alleviating redundancy and mitigating information loss from conventional PCA-based spectral reduction. Moreover, the learned band subset exhibits highly discriminative spectral structures that align with discriminative semantic cues, promoting compact yet expressive representations. (2) Cross-source Adaptive Fusion Module (CAFM) that performs cross-source attention weighting and local-global contextual refinement to enhance cross-source feature interaction. Experiments on three public benchmark datasets demonstrate that our RSCNet achieves superior performance compared with state-of-the-art methods, while maintaining substantially lower computational complexity. Our codes are publicly available at https://github.com/oucailab/RSCNet.

Tengya Zhang, Feng Gao, Lin Qi et al.

Hyperspectral image super-resolution is essential for enhancing the spatial fidelity of HSI data, yet existing deep learning methods often struggle with substantial spectral redundancy and the limited non-linear modeling capacity of standard feed-forward networks (FFNs). To address these challenges, we propose Spectral Dynamic Attention Network (SDANet), a framework designed to adaptively suppress redundant spectral interactions. SDANet integrates two key components: 1) Dynamic Channel Sparse Attention (DCSA) module that computes channel-wise correlations and selectively preserves the most informative attention responses through dynamic and data-dependent sparsification. 2) Frequency-Enhanced Feed-Forward Network (FE-FFN) that jointly models spatial and frequency-domain representations to enhance non-linear expressiveness. Extensive experiments on two benchmark datasets demonstrate that SDANet achieves state-of-the-art HISR performance while maintaining competitive efficiency. The code will be made publicly available at https://github.com/oucailab/SDANet.

Jie Liang, Jiahao Wu, Chao Wang et al.

Dynamic 3D scene reconstruction is essential for immersive media such as VR, MR, and XR, yet remains challenging for long multi-view sequences with large-scale motion. Existing dynamic Gaussian approaches are either Frame-Stream, offering scalability but poor temporal stability, or Clip, achieving local consistency at the cost of high memory and limited sequence length. We propose ClipGStream, a hybrid reconstruction framework that performs stream optimization at the clip level rather than the frame level. The sequence is divided into short clips, where dynamic motion is modeled using clip-independent spatio-temporal fields and residual anchor compensation to capture local variations efficiently, while inter-clip inherited anchors and decoders maintain structural consistency across clips. This Clip-Stream design enables scalable, flicker-free reconstruction of long dynamic videos with high temporal coherence and reduced memory overhead. Extensive experiments demonstrate that ClipGStream achieves state-of-the-art reconstruction quality and efficiency. The project page is available at: https://liangjie1999.github.io/ClipGStreamWeb/

Han Luo, Feng Gao, Junyu Dong et al.

Hyperspectral image (HSI) and synthetic aperture radar (SAR) data joint classification is a crucial and yet challenging task in the field of remote sensing image interpretation. However, feature modeling in existing methods is deficient to exploit the abundant global, spectral, and local features simultaneously, leading to sub-optimal classification performance. To solve the problem, we propose a hierarchical attention and parallel filter fusion network for multi-source data classification. Concretely, we design a hierarchical attention module for hyperspectral feature extraction. This module integrates global, spectral, and local features simultaneously to provide more comprehensive feature representation. In addition, we develop parallel filter fusion module which enhances cross-modal feature interactions among different spatial locations in the frequency domain. Extensive experiments on two multi-source remote sensing data classification datasets verify the superiority of our proposed method over current state-of-the-art classification approaches. Specifically, our proposed method achieves 91.44% and 80.51% of overall accuracy (OA) on the respective datasets, highlighting its superior performance.

Caoshuo Li, Zengmao Ding, Xiaobin Hu et al.

As one of the earliest writing systems, Oracle Bone Script (OBS) preserves the cultural and intellectual heritage of ancient civilizations. However, current OBS research faces two major challenges: (1) the interpretation of OBS involves a complex workflow comprising multiple serial and parallel sub-tasks, and (2) the efficiency of OBS information organization and retrieval remains a critical bottleneck, as scholars often spend substantial effort searching for, compiling, and managing relevant resources. To address these challenges, we present OracleAgent, the first agent system designed for the structured management and retrieval of OBS-related information. OracleAgent seamlessly integrates multiple OBS analysis tools, empowered by large language models (LLMs), and can flexibly orchestrate these components. Additionally, we construct a comprehensive domain-specific multimodal knowledge base for OBS, which is built through a rigorous multi-year process of data collection, cleaning, and expert annotation. The knowledge base comprises over 1.4M single-character rubbing images and 80K interpretation texts. OracleAgent leverages this resource through its multimodal tools to assist experts in retrieval tasks of character, document, interpretation text, and rubbing image. Extensive experiments demonstrate that OracleAgent achieves superior performance across a range of multimodal reasoning and generation tasks, surpassing leading mainstream multimodal large language models (MLLMs) (e.g., GPT-4o). Furthermore, our case study illustrates that OracleAgent can effectively assist domain experts, significantly reducing the time cost of OBS research. These results highlight OracleAgent as a significant step toward the practical deployment of OBS-assisted research and automated interpretation systems.

Jiayu Chen, Chao Yu, Yuqing Xie et al. · tsinghua

Executing precise and agile flight maneuvers is critical for quadrotors in various applications. Traditional quadrotor control approaches are limited by their reliance on flat trajectories or time-consuming optimization, which restricts their flexibility. Recently, RL-based policy has emerged as a promising alternative due to its ability to directly map observations to actions, reducing the need for detailed system knowledge and actuation constraints. However, a significant challenge remains in bridging the sim-to-real gap, where RL-based policies often experience instability when deployed in real world. In this paper, we investigate key factors for learning robust RL-based control policies that are capable of zero-shot deployment in real-world quadrotors. We identify five critical factors and we develop a PPO-based training framework named SimpleFlight, which integrates these five techniques. We validate the efficacy of SimpleFlight on Crazyflie quadrotor, demonstrating that it achieves more than a 50% reduction in trajectory tracking error compared to state-of-the-art RL baselines. The policy derived by SimpleFlight consistently excels across both smooth polynominal trajectories and challenging infeasible zigzag trajectories on small thrust-to-weight quadrotors. In contrast, baseline methods struggle with high-speed or infeasible trajectories. To support further research and reproducibility, we integrate SimpleFlight into a GPU-based simulator Omnidrones and provide open-source access to the code and model checkpoints. We hope SimpleFlight will offer valuable insights for advancing RL-based quadrotor control. For more details, visit our project website at https://sites.google.com/view/simpleflight/.

Feng Gao, Sheng Liu, Chuanzheng Gong et al.

Multi-source remote sensing data joint classification aims to provide accuracy and reliability of land cover classification by leveraging the complementary information from multiple data sources. Existing methods confront two challenges: inter-frequency multi-source feature coupling and inconsistency of complementary information exploration. To solve these issues, we present a Prototype-based Information Compensation Network (PICNet) for land cover classification based on HSI and SAR/LiDAR data. Specifically, we first design a frequency interaction module to enhance the inter-frequency coupling in multi-source feature extraction. The multi-source features are first decoupled into high- and low-frequency components. Then, these features are recoupled to achieve efficient inter-frequency communication. Afterward, we design a prototype-based information compensation module to model the global multi-source complementary information. Two sets of learnable modality prototypes are introduced to represent the global modality information of multi-source data. Subsequently, cross-modal feature integration and alignment are achieved through cross-attention computation between the modality-specific prototype vectors and the raw feature representations. Extensive experiments on three public datasets demonstrate the significant superiority of our PICNet over state-of-the-art methods. The codes are available at https://github.com/oucailab/PICNet.

Feng Gao, Miao Fu, Jingchao Cao et al.

Semantic segmentation of high-resolution remote sensing images plays a crucial role in land-use monitoring and urban planning. Recent remarkable progress in deep learning-based methods makes it possible to generate satisfactory segmentation results. However, existing methods still face challenges in adapting network parameters to various land cover distributions and enhancing the interaction between spatial and frequency domain features. To address these challenges, we propose the Adaptive Frequency Enhancement Network (AFENet), which integrates two key components: the Adaptive Frequency and Spatial feature Interaction Module (AFSIM) and the Selective feature Fusion Module (SFM). AFSIM dynamically separates and modulates high- and low-frequency features according to the content of the input image. It adaptively generates two masks to separate high- and low-frequency components, therefore providing optimal details and contextual supplementary information for ground object feature representation. SFM selectively fuses global context and local detailed features to enhance the network's representation capability. Hence, the interactions between frequency and spatial features are further enhanced. Extensive experiments on three publicly available datasets demonstrate that the proposed AFENet outperforms state-of-the-art methods. In addition, we also validate the effectiveness of AFSIM and SFM in managing diverse land cover types and complex scenarios. Our codes are available at https://github.com/oucailab/AFENet.