论文检索

Yue Li, Meng Tian, Dechang Zhu, Jiangtong Zhu, Zhenyu Lin, Zhiwei Xiong, Xinhai Zhao

Large vision-language models (VLMs) for autonomous driving (AD) are evolving beyond perception and cognition tasks toward motion planning. However, we identify two critical challenges in this direction: (1) VLMs tend to learn shortcuts by relying heavily on history input information, achieving seemingly strong planning results without genuinely understanding the visual inputs; and (2) the chain-of-thought (COT) reasoning processes are always misaligned with the motion planning outcomes, and how to effectively leverage the complex reasoning capability to enhance planning remains largely underexplored. In this paper, we start from a small-scale domain-specific VLM and propose Drive-R1, designed to bridge the scenario reasoning and motion planning for AD. Drive-R1 first undergoes the supervised finetuning on an elaborate dataset containing both long and short COT data. Drive-R1 is encouraged to reason step-by-step from visual input to final planning decisions. Subsequently, Drive-R1 is trained within a reinforcement learning framework that incentivizes the discovery of reasoning paths that are more informative for planning, guided by rewards based on predicted trajectories and meta actions. Experimental evaluations on the nuScenes and DriveLM-nuScenes benchmarks demonstrate that Drive-R1 achieves superior performance compared to existing state-of-the-art VLMs. We believe that Drive-R1 presents a promising direction for bridging reasoning and planning in AD, offering methodological insights for future research and applications.

Yuan-Ming Li, An-Lan Wang, Ling-An Zeng, Kun-Yu Lin, Yu-Ming Tang, Weishi Zheng

To guide a learner in mastering action skills, it is crucial for a coach to 1) reason through the learner's action execution and technical points (TechPoints), and 2) provide detailed, comprehensible feedback on what is done well and what can be improved. However, existing score-based action assessment methods are still far from reaching this practical scenario. To bridge this gap, we investigate a new task termed Descriptive Action Coaching (DescCoach) which requires the model to provide detailed commentary on what is done well and what can be improved beyond a simple quality score for action execution. To this end, we first build a new dataset named EE4D-DescCoach. Through an automatic annotation pipeline, our dataset goes beyond the existing action assessment datasets by providing detailed TechPoint-level commentary. Furthermore, we propose TechCoach, a new framework that explicitly incorporates TechPoint-level reasoning into the DescCoach process. The central to our method lies in the Context-aware TechPoint Reasoner, which enables TechCoach to learn TechPoint-related quality representation by querying visual context under the supervision of TechPoint-level coaching commentary. By leveraging the visual context and the TechPoint-related quality representation, a unified TechPoint-aware Action Assessor is then employed to provide the overall coaching commentary together with the quality score. Combining all of these, we establish a new benchmark for DescCoach and evaluate the effectiveness of our method through extensive experiments.

Yongcheng Li, Xuekuan Wang, Zhifei Zhang, Cairong Zhao

Long-Tailed Multi-Label Recognition (LTML) is a critical yet challenging task due to two core issues: the severe scarcity of training samples for rare "tail" classes, and the complex co-occurrence patterns among labels that often lead to biased models. To address this, we propose DP-VLPA, a novel Dual-Phase Visual-Language Pretraining and Adaptation framework. In the first phase, our Structured Tail-Aware Generation (STAG) module employs a Large Language Model (LLM) to create detailed descriptions that explicitly emphasize tail classes and their contextual relationships, providing a strong and less-biased feature foundation. In the second adaptation phase, we ensure this knowledge is applied effectively. A Dynamic Query Reweighting (DQR) mechanism forces the model to attend to crucial tail-class evidence. Simultaneously, a Co-occurrence-Aware (COA) loss explicitly teaches the model the statistical dependencies between labels, correcting for co-occurrence biases. Extensive experiments on VOC-LT and COCO-LT datasets demonstrate state-of-the-art performance, achieving mAP scores of 90.72% and 74.42% respectively - surpassing previous best methods by 2.84% and 8.23%.

Yixiao Li, Xiaoyuan Yang, Weide Liu, Xin Jin, Xu Jia, Yu-Kun Lai, Paul L. Rosin, Hantao Liu, Wei Zhou

As super-resolution (SR) techniques introduce unique distortions that fundamentally differ from those caused by traditional degradation processes (e.g., compression), there is an increasing demand for specialized video quality assessment (VQA) methods tailored to SR-generated content. One critical factor affecting perceived quality is temporal inconsistency, which refers to irregularities between consecutive frames. However, existing VQA approaches rarely quantify this phenomenon or explicitly investigate its relationship with human perception. Moreover, SR videos exhibit amplified inconsistency levels as a result of enhancement processes. In this paper, we propose Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment (TIG-SVQA) that underscores the critical role of temporal inconsistency in guiding the quality assessment of SR videos. We first design a perception-oriented approach to quantify frame-wise temporal inconsistency. Based on this, we introduce the Inconsistency Highlighted Spatial Module, which localizes inconsistent regions at both coarse and fine scales. Inspired by the human visual system, we further develop an Inconsistency Guided Temporal Module that performs progressive temporal feature aggregation: (1) a consistency-aware fusion stage in which a visual memory capacity block adaptively determines the information load of each temporal segment based on inconsistency levels, and (2) an informative filtering stage for emphasizing quality-related features. Extensive experiments on both single-frame and multi-frame SR video scenarios demonstrate that our method significantly outperforms state-of-the-art VQA approaches.

Yingping Li, Yutong Zou, Yunshi Huang, Changzhe Jiao, Xinlin Wang, Shen Peng, Zhang Guo, Shuiping Gou

Transductive Information Maximization (TIM) is a leading transductive few-shot learning method that maximizes the mutual information between query features and their predicted labels, while incorporating supervision from the support set. However, its potential remains underexplored, primarily due to the limited utilization of textual knowledge provided by vision-language models (VLMs) such as CLIP. To address this, we propose TIM++, an enhanced framework that incorporates both visual and textual information for few-shot CLIP adaptation. Specifically, TIM++ introduces a Kullback-Leibler (KL) divergence-based regularization term that encourages the model’s posterior predictions to align with CLIP’s zero-shot output distribution, especially focusing on the most confident predictions. Additionally, we develop an improved prototype initialization strategy that leverages both support and query features enriched with CLIP-guided semantics. Extensive experiments on 11 public datasets demonstrate that TIM++ consistently outperforms the standard TIM, achieving average accuracy gains of 19.25% and 10.88% in 1-shot and 2-shot settings, respectively. TIM++ also surpasses other existing state-of-the-art methods, establishing a new benchmark for few-shot learning with VLMs.

Yinglu Li, Zhiying Lu, Zhihang Liu, Yiwei Sun, Chuanbin Liu, Hongtao Xie

Multi-modal Retrieval-Augmented Generation (RAG) has become a critical method for empowering LLMs by leveraging candidate visual documents. However, current methods consider the entire document as the basic retrieval unit, introducing substantial irrelevant visual content in two ways: 1) Relevant documents often contain large regions unrelated to the query, diluting the focus on salient information; 2) Retrieving multiple documents to increase recall further introduces redundant and irrelevant documents. These redundant contexts distract the model's attention and further degrade the performance. To address this challenge, we propose RegionRAG, a novel framework that shifts the retrieval paradigm from the document level to the region level. During training, we design a hybrid supervision strategy from both labeled data and unlabeled data to pinpoint relevant patches. During inference, we propose a dynamic pipeline that intelligently groups salient patches into complete semantic regions. By delegating the task of identifying relevant regions to the retriever, RegionRAG enables the generator to focus solely on concise, query-relevant visual content, improving both efficiency and accuracy. Experiments on six benchmarks demonstrate that RegionRAG achieves state-of-the-art performance. It improves retrieval accuracy by 10.02% in R@1 on average, and boosts question answering accuracy by 3.56% while using only 71.42% visual tokens compared with prior methods.

Yinghui Li, Qianyu Zhou, Di Shao, Hao Yang, Ye Zhu, Richard Dazeley, Xuequan Lu

Domain adaptive point cloud completion (DA PCC) aims to narrow the geometric and semantic discrepancies between the labeled source and unlabeled target domains. Existing methods either suffer from limited receptive fields or quadratic complexity due to using CNNs or vision Transformers. In this paper, we present the first work that studies the adaptability of state space models (SSMs) in DA PCC and find that directly applying SSMs to DA PCC will encounter several challenges: directly serializing 3D point clouds into 1D sequences often disrupts the spatial topology and local geometric features of the target domain. Besides, the overlook of designs in the learning domain-agnostic representations hinders the adaptation performance. To address these issues, we propose a novel framework, DAPointMamba for DA PCC, that exhibits strong adaptability across domains and has the advantages of global receptive fields and efficient linear complexity. It has three novel modules. In particular, Cross-Domain Patch-Level Scanning introduces patch-level geometric correspondences, enabling effective local alignment. Cross-Domain Spatial SSM Alignment further strengthens spatial consistency by modulating patch features based on cross-domain similarity, effectively mitigating fine-grained structural discrepancies. Cross-Domain Channel SSM Alignment actively addresses global semantic gaps by interleaving and aligning feature channels. Extensive experiments on both synthetic and real-world benchmarks demonstrate that our DAPointMamba outperforms state-of-the-art methods with less computational complexity and inference latency.

Ying Li, Xiaobao Wei, Xiaowei Chi, Yuming Li, Zhongyu Zhao, Hao Wang, Ningning Ma, Ming Lu, Sirui Han

Data scarcity continues to be a critical bottleneck in the field of robotic manipulation, limiting the ability to train robust and generalizable models. While diffusion models provide a promising approach to synthesizing realistic robotic manipulation videos, their effectiveness hinges on the availability of precise and reasonable control instructions. Current methods primarily rely on 2D trajectories as instruction prompts, which inherently face issues with 3D spatial ambiguity. In this work, we present a novel framework named ManipDreamer3Dfor generating plausible 3D-aware robotic manipulation videos from the input image and the text instruction. Our method combines 3D trajectory planning with a reconstructed 3D occupancy map created from a third-person perspective, along with a novel trajectory-to-video diffusion model. Specifically, ManipDreamer3D first reconstructs the 3D occupancy representation from the input image and then computes an optimized 3D end-effector trajectory, minimizing path length, avoiding collisions and retiming. Next, we employ a latent editing technique to create video sequences from the initial image latent, text instruction and the optimized 3D trajectory. This process conditions our specially trained trajectory-to-video diffusion model to produce robotic pick-and-place videos. Our method significantly reduces human intervention requirements by autonomously planing plausible 3D trajectories. Experimental results demonstrate its superior visual quality and precision.

Yifan Li, Kun Zhou, Xin Zhao, Lei Fang, Jirong Wen

As scaling up training data has significantly improved the general multimodal capabilities of Large Vision-Language Models (LVLMs), they still suffer from the hallucination issue, generating text that is inconsistent with the visual input. This phenomenon motivates us to systematically investigate the role of training data in hallucination. We introduce a new benchmark, POPEv2, which consists of counterfactual images collected from the training data of LVLMs with certain objects masked. Through comprehensive evaluation on POPEv2, we find that current LVLMs suffer from training bias: they fail to fully leverage their training data and hallucinate more frequently on images seen during training. Specifically, they perform poorly on counterfactual images, often incorrectly answering “Yes” to questions about masked objects. To understand this issue, we conduct probing experiments on the models’ internal components, revealing that this training bias is primarily located in the language modeling (LM) head, which fails to correctly translate accurate visual representations into textual outputs. Based on these findings, we propose Obliviate, an efficient and lightweight unlearning method designed to mitigate object hallucination via training bias unlearning. Obliviate identifies the discrepancy between ground-truth labels and model outputs on the training data as a proxy for bias and adopts a parameter- and data-efficient fine-tuning strategy that only updates the LM head. Extensive experiments demonstrate the effectiveness of our approach. While only reusing the training data and updating approximately 2% of the parameters, Obliviate significantly reduces hallucination across both discriminative and generative tasks. Furthermore, it demonstrates strong scalability with respect to both model size (2B to 72B) and training data volume, and exhibits promising generalization to hallucination types beyond object-level hallucination.

Yaoqian Li, Xikai Yang, Dunyuan Xu, Yang YU, Litao Zhao, Xiaowei Hu, Jinpeng Li, Pheng-Ann Heng

Vision-Language Models (VLMs) have shown significant potential in surgical scene analysis, yet existing models are limited by frame-level datasets and lack high-quality video data with procedural surgical knowledge. To address these challenges, we make the following contributions: (i) SurgPub-Video, a comprehensive dataset of over 3,000 surgical videos and 25 million annotated frames across 11 specialities, sourced from peer-reviewed clinical journals, (ii) SurgLLaVA-Video, a specialized VLM for surgical video understanding, built upon the TinyLLaVA-Video architecture that supports both video-level and frame-level inputs, and (iii) a video-level surgical Visual Question Answering (VQA) benchmark, covering diverse 11 surgical specialities, such as vascular, cardiology, and thoracic. Extensive experiments, conducted on the proposed benchmark and three additional surgical downstream tasks (action recognition, skill assessment, and triplet recognition), show that SurgLLaVA-Video significantly outperforms both general-purpose and surgical-specific VLMs with only three billion parameters.

Yanshu Li, Jianjiang Yang, Zhennan Shen, Ligong Han, Haoyan Xu, Ruixiang Tang

Modern large vision-language models (LVLMs) convert each input image into a large set of tokens that far outnumber the text tokens. Although this improves visual perception, it also introduces severe image token redundancy. Because image tokens contain sparse information, many contribute little to reasoning but greatly increase inference cost. Recent image token pruning methods address this issue by identifying important tokens and removing the rest. These methods improve efficiency with only small performance drops. However, most of them focus on single-image tasks and overlook multimodal in-context learning (ICL), where redundancy is higher and efficiency is more important. Redundant tokens weaken the advantage of multimodal ICL for rapid domain adaptation and lead to unstable performance. When existing pruning methods are applied in this setting, they cause large accuracy drops, which exposes a clear gap and the need for new approaches. To address this, we propose Contextually Adaptive Token Pruning (CATP), a training-free pruning method designed for multimodal ICL. CATP uses two stages of progressive pruning that fully reflect the complex cross-modal interactions in the input sequence. After removing 77.8% of the image tokens, CATP achieves an average performance gain of 0.6% over the vanilla model on four LVLMs and eight benchmarks, clearly outperforming all baselines. At the same time, it improves efficiency by reducing inference latency by an average of 10.78%. CATP strengthens the practical value of multimodal ICL and lays the foundation for future progress in interleaved image-text settings.

Yanshu Li, Jianjiang Yang, Ziteng Yang, Bozheng Li, Ligong Han, Hongyang He, Zhengtao Yao, Yingjie Victor Chen, Songlin Fei, Dongfang Liu 等

Multimodal in-context learning (ICL) is becoming a key capability that allows large vision-language models (LVLMs) to adapt to novel tasks without parameter updates, which expands their usefulness in many real-world applications. However, ICL performance remains unstable even when the in-context demonstrations (ICDs) are well matched, showing that LVLMs still struggle to make full use of the provided context. While existing work mainly focuses on prompt engineering or post-hoc logit calibration, we study the attention mechanisms inside LVLMs to address their inherent limitations. We identify two important weaknesses in their self-attention that hinder effective ICL. To address these weaknesses, we propose Context-Aware Modulated Attention (CAMA), a training-free and plug-and-play method that dynamically adjusts attention logits based on the input in-context sequence. CAMA uses a two-stage modulation process that strengthens attention to semantically important tokens, especially visual ones. Across four LVLMs and seven benchmarks, CAMA consistently outperforms vanilla models and baselines, showing clear effectiveness and generalization. It can also activate the intended benefits of prompt engineering methods and remains robust across different sequence configurations. Therefore, CAMA opens up new directions for improving multimodal reasoning through a deeper understanding of attention dynamics.

Yanqi Li, Jianwei Niu, Ningbo Gu, Tao Ren

Open-Vocabulary Object Detection (OVOD) aims to detect both known and novel categories in complex visual scenes, surpassing the limitations of conventional closed-set detectors. Recent advances in vision-language models (VLMs) like CLIP have enabled zero-shot recognition by aligning visual features with large-scale textual embeddings. However, current OVOD approaches often fall short by overlooking critical contextual and semantic cues necessary for discovering a broader range of novel objects. To address this, we propose BFDet, a scene-to-object reasoning framework that leverages the complementary strengths of Large Language Models (LLMs) and VLMs. BFDet introduces a novel scene-to-object reasoning mechanism grounded in foreground-background context interaction. It first uses high-confidence objects to infer the scene-level background. This scene background then guides the discovery of foreground objects by prompting an LLM to generate scene-sensitive novel object candidates. These candidates are subsequently verified through cross-modal alignment and used as high-quality pseudo-labels to enrich detector training. Designed as a plug-and-play module, BFDet integrates seamlessly into existing detection pipelines and consistently improves performance on novel categories across COCO and LVIS benchmarks.

Yanjun Li, Yuqian Fu, Tianwen Qian, Qi'Ao Xu, Silong Dai, Danda Pani Paudel, Luc Van Gool, Xiaoling Wang

Recent advances in Multimodal Large Language Models (MLLMs) have significantly pushed the frontier of egocentric video question answering (EgocentricQA). However, existing benchmarks and studies are mainly limited to common daily activities such as cooking and cleaning. In contrast, real-world deployment inevitably encounters domain shifts, where target domains differ substantially in both visual style and semantic content. To bridge this gap, we introduce EgoCross, a comprehensive benchmark designed to evaluate the cross-domain generalization of MLLMs in EgocentricQA. EgoCross covers four diverse and challenging domains, including surgery, industry, extreme sports, and animal perspective, representing realistic and high-impact application scenarios. It comprises approximately 1,000 QA pairs across 798 video clips, spanning four key QA tasks: prediction, recognition, localization, and counting. Each QA pair provides both OpenQA and CloseQA formats to support fine-grained evaluation. Extensive experiments show that most existing MLLMs, whether general-purpose or egocentric-specialized, struggle to generalize to domains beyond daily life, highlighting the limitations of current models. Furthermore, we conduct several pilot studies, e.g., fine-tuning and reinforcement learning, to explore potential improvements. We hope EgoCross and our accompanying analysis will serve as a foundation for advancing domain-adaptive, robust egocentric video understanding.

Yanhui Li, Yunkang Cao, Chengliang Liu, Yuan Xiong, Xinghui Dong, Chao Huang

Industrial anomaly detection is a critical component of modern manufacturing, yet the scarcity of defective samples restricts traditional detection methods to scenario-specific applications. Although Vision-Language Models (VLMs) demonstrate significant advantages in generalization capabilities, their performance in industrial anomaly detection remains limited. To address this challenge, we propose IAD-R1, a universal post-training framework applicable to VLMs of different architectures and parameter scales, which substantially enhances their anomaly detection capabilities. IAD-R1 employs a two-stage training strategy: the Perception Activation Supervised Fine-Tuning (PA-SFT) stage utilizes a meticulously constructed high-quality Chain-of-Thought dataset (Expert-AD) for training, enhancing anomaly perception capabilities and establishing reasoning-to-answer correlations; the Structured Control Group Relative Policy Optimization (SC-GRPO) stage employs carefully designed reward functions to achieve a capability leap from "Anomaly Perception" to "Anomaly Interpretation". Experimental results demonstrate that IAD-R1 achieves significant improvements across 7 VLMs, the largest improvement was on the DAGM dataset, with average accuracy 43.3% higher than the 0.5B baseline. Notably, the 0.5B parameter model trained with IAD-R1 surpasses commercial models including GPT-4.1 and Claude-Sonnet-4 in zero-shot settings, demonstrating the effectiveness and superiority of IAD-R1.

Yangwei Li, Xiaochuan Wang, Xin Shang, Haisheng Li

Point cloud quality assessment (PCQA) has advanced significantly with synthetic datasets offering diverse distortion coverage for model training. However, when applied to new application scenarios, models often suffer from performance drops due to mismatched distortion characteristics between source and target domains. Most current methods use all available synthetic distortions, which may introduce irrelevant features and hinder generalization. To address this, we propose DST-PCQA, a distortion-selective training framework for PCQA. Unlike previous approaches that treat all distortions equally, DST-PCQA identifies and selects distortion types most relevant to a target domain by analyzing inter-domain distortion similarity. This selective strategy reduces negative transfer and enables efficient domain-specific training. To fully leverage the selected distortions for both classification and quality prediction, we adopt a dual-branch architecture that fuses 2D visual cues and 3D geometric structure via cross-modal attention. This design supports multi-level feature alignment across modalities and enables fine-grained distortion understanding. Extensive evaluations across three target domains have verified the effectiveness of DST-PCQA over full-set training baselines. Moreover, its distortion-selective strategy is orthogonal to existing model-based PCQA methods, enabling improved cross-domain performance and reduced training costs across a wide range of architectures.

Yanfeng Li, Tao Tan, Qinquan Gao, Zhiwen Cao, Xiaohong Liu, Yue Sun

High-fidelity 3D meshes can be tokenized into one-dimension (1D) sequences and directly modeled using autoregressive approaches for faces and vertices. However, existing methods suffer from insufficient resource utilization, resulting in slow inference and the ability to handle only small-scale sequences, which severely constrains the expressible structural details. We introduce the Latent Autoregressive Network (LANE), which incorporates compact autoregressive dependencies in the generation process, achieving a 6× improvement in maximum generatable sequence length compared to existing methods. To further accelerate inference, we propose the Adaptive Computation Graph Reconfiguration (AdaGraph) strategy, which effectively overcomes the efficiency bottleneck of traditional serial inference through spatiotemporal decoupling in the generation process. Experimental validation demonstrates that LANE achieves superior performance across generation speed, structural detail, and geometric consistency, providing an effective solution for high-quality 3D mesh generation.

Yan Li, Yingzhao Li, Gim Hee Lee

In this paper, we present an active exploration framework for high-fidelity 3D reconstruction that incrementally builds a multi-level uncertainty space and selects next-best-views through an uncertainty-driven motion planner. We introduce a hybrid implicit–explicit representation that fuses neural fields with Gaussian primitives to jointly capture global structural priors and locally observed details. Based on this hybrid state, we derive a hierarchical uncertainty volume that quantifies both implicit global structure quality and explicit local surface confidence. To focus optimization on the most informative regions, we propose an uncertainty-driven keyframe selection strategy that anchors high-entropy viewpoints as sparse attention nodes, coupled with a viewpoint-space sliding window for uncertainty-aware local refinement. The planning module formulates next-best-view selection as an Expected Hybrid Information Gain problem and incorporates a risk-sensitive path planner to ensure efficient and safe exploration. Extensive experiments on challenging benchmarks demonstrate that our approach consistently achieves state-of-the-art accuracy, completeness, and rendering quality, highlighting its effectiveness for real-world active reconstruction and robotic perception tasks.

Yan Li, Ze Yang, Keisuke Tateno, Federico Tombari, Liang Zhao, Gim Hee Lee

Minimal parametrization of 3D lines plays a critical role in camera localization and structural mapping. Existing representations in robotics and computer vision predominantly handle independent lines, overlooking structural regularities such as sets of parallel lines that are pervasive in man-made environments. This paper introduces RiemanLine, a unified minimal representation for 3D lines formulated on Riemannian manifolds that jointly accommodates both individual lines and parallel-line groups. Our key idea is to decouple each line landmark into global and local components: a shared vanishing direction optimized on the unit sphere, and scaled normal vectors constrained on orthogonal subspaces, enabling compact encoding of structural regularities. For n parallel lines, the proposed representation reduces the parameter space from 4n (orthonormal form) to 2n+2, naturally embedding parallelism without explicit constraints. We further integrate this parameterization into a factor graph framework, allowing global direction alignment and local reprojection optimization within a unified manifold-based bundle adjustment. Extensive experiments on ICL-NUIM, TartanAir, and synthetic benchmarks demonstrate that our method achieves significantly more accurate pose estimation and line reconstruction, while reducing parameter dimensionality and improving convergence stability.

Xuyang Li, Chenyu Li, Danfeng Hong

Optical satellites, with their diverse band layouts and ground sampling distances, supply indispensable evidence for tasks ranging from ecosystem surveillance to emergency response. However, significant discrepancies in band composition and spatial resolution across different optical sensors present major challenges for existing Remote Sensing Foundation Models (RSFMs). These models are typically pretrained on fixed band configurations and resolutions, making them vulnerable to real world scenarios involving missing bands, cross sensor fusion, and unseen spatial scales, thereby limiting their generalization and practical deployment. To address these limitations, we propose Any Optical Model (AOM), a universal RSFM explicitly designed to accommodate arbitrary band compositions, sensor types, and resolution scales. To preserve distinctive spectral characteristics even when bands are missing or newly introduced, AOM introduces a spectrum-independent tokenizer that assigns each channel a dedicated band embedding, enabling explicit encoding of spectral identity. To effectively capture texture and contextual patterns from sub-meter to hundred-meter imagery, we design a multi-scale adaptive patch embedding mechanism that dynamically modulates the receptive field. Furthermore, to maintain global semantic consistency across varying resolutions, AOM incorporates a multi-scale semantic alignment mechanism alongside a channel-wise self-supervised masking and reconstruction pretraining strategy that jointly models spectral-spatial relationships. Extensive experiments on over 10 public datasets, including those from Sentinel-2, Landsat, and HLS, demonstrate that AOM consistently achieves state-of-the-art (SOTA) performance under challenging conditions such as band missing, cross sensor, and cross resolution settings. These results highlight AOM as a crucial step toward building truly general-purpose RSFMs.