Wei Liu

Hua Chang, Xin Xu, Wei Liu et al.

Chinese opera is celebrated for preserving classical art. However, early filming equipment limitations have degraded videos of last-century performances by renowned artists (e.g., low frame rates and resolution), hindering archival efforts. Although space-time video super-resolution (STVSR) has advanced significantly, applying it directly to opera videos remains challenging. The scarcity of datasets impedes the recovery of high frequency details, and existing STVSR methods lack global modeling capabilities, compromising visual quality when handling opera's characteristic large motions. To address these challenges, we pioneer a large scale Chinese Opera Video Clip (COVC) dataset and propose the Mamba-based multiscale fusion network for space-time Opera Video Super-Resolution (MambaOVSR). Specifically, MambaOVSR involves three novel components: the Global Fusion Module (GFM) for motion modeling through a multiscale alternating scanning mechanism, and the Multiscale Synergistic Mamba Module (MSMM) for alignment across different sequence lengths. Additionally, our MambaVR block resolves feature artifacts and positional information loss during alignment. Experimental results on the COVC dataset show that MambaOVSR significantly outperforms the SOTA STVSR method by an average of 1.86 dB in terms of PSNR. Dataset and Code will be publicly released.

Zhenteng Li, Sheng Lian, Dengfeng Pan et al.

Object detection in Unmanned Aerial Vehicle (UAV) images poses significant challenges due to complex scale variations and class imbalance among objects. Existing methods often address these challenges separately, overlooking the intricate nature of UAV images and the potential synergy between them. In response, this paper proposes AD-Det, a novel framework employing a coherent coarse-to-fine strategy that seamlessly integrates two pivotal components: Adaptive Small Object Enhancement (ASOE) and Dynamic Class-balanced Copy-paste (DCC). ASOE utilizes a high-resolution feature map to identify and cluster regions containing small objects. These regions are subsequently enlarged and processed by a fine-grained detector. On the other hand, DCC conducts object-level resampling by dynamically pasting tail classes around the cluster centers obtained by ASOE, main-taining a dynamic memory bank for each tail class. This approach enables AD-Det to not only extract regions with small objects for precise detection but also dynamically perform reasonable resampling for tail-class objects. Consequently, AD-Det enhances the overall detection performance by addressing the challenges of scale variations and class imbalance in UAV images through a synergistic and adaptive framework. We extensively evaluate our approach on two public datasets, i.e., VisDrone and UAVDT, and demonstrate that AD-Det significantly outperforms existing competitive alternatives. Notably, AD-Det achieves a 37.5% Average Precision (AP) on the VisDrone dataset, surpassing its counterparts by at least 3.1%.

Guanzhong Chen, Shaoxiong Yang, Chao Li et al.

Large Language Models (LLMs) have achieved remarkable success across diverse natural language processing tasks, yet their deployment in real-world applications is hindered by fixed knowledge cutoffs and difficulties in generating controllable, accurate outputs in a single inference. Multi-agent systems (MAS) built from specialized LLM agents offer a promising solution, enabling dynamic collaboration and iterative reasoning. However, optimizing these systems remains a challenge, as conventional methods such as prompt engineering and supervised fine-tuning entail high engineering overhead and limited adaptability. Reinforcement learning (RL), particularly multi-agent reinforcement learning (MARL), provides a scalable framework by refining agent policies based on system-level feedback. Nevertheless, existing MARL algorithms, such as Multi-Agent Proximal Policy Optimization (MAPPO), rely on Critic networks, which can cause training instability and increase computational burden. To address these limitations and target the prototypical Multi-Agent Search System (MASS), we propose Multi-Agent Heterogeneous Group Policy Optimization (MHGPO), a novel Critic-free algorithm that guides policy updates by estimating relative reward advantages across heterogeneous groups of rollouts. MHGPO eliminates the need for Critic networks, enhancing stability and reducing computational overhead. Additionally, we introduce three group rollout sampling strategies that trade off between efficiency and effectiveness. Experiments on a multi-agent LLM-based search system demonstrate that MHGPO consistently outperforms MAPPO in both task performance and computational efficiency, without requiring warm-up, underscoring its potential for stable and scalable optimization of complex LLM-based MAS.

Jinpeng Wang, Chao Li, Ting Ye et al.

Reinforcement Learning with Verifiable Rewards (RLVR) demonstrates significant potential in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing RLVR methods are often constrained by issues such as coarse-grained rewards, reward noise, and inefficient exploration, which lead to unstable training and entropy collapse. To address this challenge, we propose the Intrinsic Confidence-Driven Group Relative Preference Optimization method (ICPO). The intuition behind it lies in the fact that the probabilities of an LLM generating different responses can inherently and directly reflect its self-assessment of the reasoning process. Inspired by the idea of preference modeling, ICPO calculates a preference advantage score for each response by comparing the relative generation probabilities of multiple responses under the same input prompt, and integrates this score with verifiable rewards to guide the exploration process. We have discovered that the preference advantage score not only alleviates the issues of coarse-grained rewards and reward noise but also effectively curbs overconfident errors, enhances the relative superiority of undervalued high-quality responses, and prevents the model from overfitting to specific strategies. Comprehensive experiments across four general-domain benchmarks and three mathematical benchmarks demonstrate that ICPO steadily boosts reasoning compared to GRPO.

Rui Guo, Ronghua Liu, Na Li et al.

Current VHR(Very High Resolution) satellite images enable the detailed monitoring of the earth and can capture the ongoing works of railway construction. In this paper, we present an integrated framework applied to monitoring the railway construction in China, using QuickBird, GF-2 and Google Earth VHR satellite images. We also construct a novel DCNNs-based (Deep Convolutional Neural Networks) semantic segmentation network to label the temporary works such as borrow & spoil area, camp, beam yard and ESAs(Environmental Sensitive Areas) such as resident houses throughout the whole railway construction project using VHR satellite images. In addition, we employ HED edge detection sub-network to refine the boundary details and attention cross entropy loss function to fit the sample class disequilibrium problem. Our semantic segmentation network is trained on 572 VHR true color images, and tested on the 15 QuickBird true color images along Ruichang-Jiujiang railway during 2015-2017. The experiment results show that compared with the existing state-of-the-art approach, our approach has obvious improvements with an overall accuracy of more than 80%.