arXiv subjects

Weilong Guo

Publications and source records attributed to Weilong Guo.

6 recordsLinked to original sources

arXiv2026

Learn Temporal Consistency For Robust Satellite Video Detector

Satellite video object detection (SVOD) for oriented and fine-grained objects plays an important role in satellite applications. Most existing SVOD methods only focus on one or a few coarse-grained categories of moving objects and represent objects with horizontal bounding boxes. They have difficulty extracting complete, accurate, and consistent information about objects in whole satellite videos. In this paper, we propose a satellite video object detection framework based on Temporal Consistency Learning (TCL). TCL adeptly detects oriented and fine-grained objects by leveraging the rich temporal contexts within satellite videos. The framework integrates three key modules: temporal and fine-grained feature aggregation (TFA), structure encoding (SE), and temporal consistency constraint (TCC). TFA and TCC modules facilitate consistent representation learning across frames, while the SE module encodes both appearance and structural information for precise fine-grained recognition. Experimental results on the SAT-MTB benchmark dataset demonstrate TCL's superior performance, achieving a new state-of-the-art oriented and fine-grained detection accuracy of 47.7% mAP--a 4.8% improvement over the baseline. Furthermore, our TCL framework readily accommodates existing image-based detectors, leading to enhanced detection accuracies.

cs.CV↗

arXiv2026

Multi-view feature High-order Fusion for Space Weak Object Detection and Segmentation

Weak objects are common in images and videos of space applications. However, it is hard to learn proper representations from their limited appearance information. Inspired by multi-view learning, we develop simple multi-view attentions, treating their outputs as multi-view features. We also propose a multi-view feature high-order fusion method (MHF) to aggregate more accurate and richer features of weak objects. Our MHF extends the commonly used low-order feature fusion method to higher orders. It enhances the model's capacity to capture relevant and complementary information about weak objects. This is achieved by introducing high-order multi-view features perception and a recursive task-contribution gated selection of multi-view features. The new operation is highly flexible and customizable. It is compatible with various variants of multi-view feature representations. We conduct extensive experiments on two newly constructed space science datasets and an open, large-scale satellite video dataset. Our MHF serves as a plug-and-play module and significantly improves various vision transformers and convolution-based detection and segmentation models. We achieve all state-of-the-art accuracies on both tasks across three datasets. Our MHF can be a new basic module for visual modeling that effectively represents weak objects in terms of multi-view learning. The code will be available at https://github.com/Kingdroper/MHF.

cs.CV↗

arXiv2026

Action with Visual Primitives

Vision-Language-Action (VLA) models have emerged as a promising paradigm for generalist robotic manipulation. A common design in current architectures maps language instructions and visual observations to actions in a single forward pass. While conceptually simple, this formulation entangles instruction comprehension, spatial scene understanding, and motor control within a single learning objective. As a result, the action expert must implicitly relearn cognitive and perceptual capabilities already present in the pretrained VLM, which can limit both learning efficiency and generalization. We introduce AVP (Action with Visual Primitives), an end-to-end architecture that implements this visual-primitive-centric interface: the VLM infers the next-stage target and emits visual-primitive tokens that condition a flow-matching action expert, with supervision derived from end-effector kinematics. Real-robot experiments on general pick-and-place tasks show that AVP improves the success rate by 37.04% over pi_0.5 and outperforms other recent methods, with consistent gains in data efficiency, spatial-compositional generalization, and object-level transfer.

cs.RO↗

arXiv2025

Linear exciton Hall and Nernst effects in monolayer two-dimensional semiconductors

This paper focuses on the study of linear exciton Hall and Nernst effects in monolayer two-dimensional (2D) semiconductors, employing the semi-classical transport theory. By deriving the exciton Berry curvature in momentum space for a general inhomogeneous 2D system, we establish its dependence on the Berry curvature and the effective mass of electron and hole. As illustrative examples, the exciton Hall effect in monolayer transition metal dichalcogenides (TMDs) and black phosphorus (BP) are calculated. For these materials, we demonstrate that a linear Hall (Nernst) exciton current with the non-zero Berry curvature is strictly forbidden by the symmetries. This finding aligns with earlier experimental observations on the exciton Hall effect in MoSe$_2$. In contrast, a strong anisotropy in BP leads to a net linear Hall current of excitons, exhibiting a relatively large value and resembling an anomalous Hall effect rather than a valley Hall effect. Our work reveals that the specific symmetry of 2D materials can induce a significant linear exciton Hall (Nernst) effect even without Berry curvature, which is normally forbidden with non-zero Berry curvature in the monolayer 2D material. This observation holds promise for future optoelectronic applications and offers exciting possibilities for experimental exploration.

cond-mat.mes-hall↗

arXiv2025

Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency

Large Language Models (LLMs) excel at reasoning, traditionally requiring high-quality large-scale data and extensive training. Recent works reveal a very appealing Less-Is-More phenomenon where very small, carefully curated high-quality datasets match resource-intensive approaches. In this work, we further systematically relax their quality constraints by adding controlled noise via persona context relevance and comparing datasets of different qualities. Counterintuitively, we find that mixing relevant and irrelevant contexts consistently across training and inference stages yields optimal results -- a phenomenon we term training-testing co-design. Dataset quality comparisons show that high-quality data benefits weaker models on easy questions, while low-quality data achieves higher scores on hard questions with capable models. Across our experiments, reasoning performance is linked to reasoning efficiency. We, for the first time, found adding noisy and irrelevant contexts into queries can improve reasoning efficiency without any prices and targeted designs. Building on these insights, we propose Input-Time Scaling: applying small, low-quality data to capable models with training-testing co-design. This maintains Less-Is-More while further removing labor-intensive quality curation and improving reasoning effectiveness and efficiency, making the approach more applicable and affordable. Our method achieves 76.7% pass@1 on AIME24/25 using Qwen2.5-32B-Instruct, and 90.0%/80.0% with DeepSeek-R1-Distill-Qwen-32B -- state-of-the-art among Qwen2.5-32B variants. We are open-sourcing our datasets, pipelines, evaluation results, and checkpoints to facilitate reproducibility and further research.

cs.LG↗

arXiv2019

CFS: A Distributed File System for Large Scale Container Platforms

We propose CFS, a distributed file system for large scale container platforms. CFS supports both sequential and random file accesses with optimized storage for both large files and small files, and adopts different replication protocols for different write scenarios to improve the replication performance. It employs a metadata subsystem to store and distribute the file metadata across different storage nodes based on the memory usage. This metadata placement strategy avoids the need of data rebalancing during capacity expansion. CFS also provides POSIX-compliant APIs with relaxed semantics and metadata atomicity to improve the system performance. We performed a comprehensive comparison with Ceph, a widely-used distributed file system on container platforms. Our experimental results show that, in testing 7 commonly used metadata operations, CFS gives around 3 times performance boost on average. In addition, CFS exhibits better random-read/write performance in highly concurrent environments with multiple clients and processes.

cs.DC↗