Issue Ebook
cover story
Current Issue
lssue 1, 2026
Editors-in-Chief
Yunhe Pan, Aiguo Fei
Advisor Xicheng Lu
ISSN 3069-8928
CN 33-1439/TP
IF (2024 JCR) 2.9
| Submit Now |
- Current Issue
- Cover Articles
- Archive
- Virtual Issues
- Online First
Volume 27 Issue 2，2026
Regular Papers
A comprehensive review on humanoid robots: perspectives from academia and industry Enhanced Publication AI Introduction
“Humanoid robotics is a rapidly evolving field that integrates artificial intelligence and robotics. This paper introduces its research progress by establishing a comprehensive taxonomic framework and conducting a systematic review of key enabling technologies. It examines research progress across diverse applications and performs a detailed comparative analysis of commercial products from leading companies. The study identifies six major challenge categories and outlines seven promising research directions, providing valuable guidance for researchers, engineers, and policymakers.”Abstract：Humanoid robotics represents a rapidly evolving research domain that integrates artificial intelligence and robotics. Despite significant advances, existing reviews have predominantly focused on narrow technical aspects and lack comprehensive analysis from academic and industrial perspectives. This paper presents a systematic dual-perspective survey, in which academic literature, commercial products, and industry reports are extensively analyzed. A comprehensive taxonomic framework and systematic review of key enabling technologies are established, including ontological structures, perception systems, locomotion control, intelligent decision-making algorithms, foundation model integration, and human–robot interaction (HRI) technologies. From academic and industrial perspectives, research progress across diverse applications is examined, and a detailed comparative analysis of commercial products from leading companies, including Tesla, Boston Dynamics, and UBTECH, is performed. Six major challenge categories are identified: hardware design limitations, control system complexities, perception constraints, HRI difficulties, application-specific requirements, and ethical considerations. In addition, the transformative impact and integration challenges of large language models are particularly discussed. Seven promising research directions are outlined, and a systematic academic–industrial gap analysis is conducted. Consequently, significant disparities and technology transfer bottlenecks are identified, and successful collaboration models are examined. This comprehensive survey provides the first systematic examination combining academic research insights with industrial development analysis. It thus offers valuable guidance for researchers, engineers, and policymakers working toward more capable, affordable, and socially integrated humanoid robots.Keywords：Humanoid robots;Dual-perspective analysis;Industrial applications;Technical challenges;Future directions5|2|0Updated：2026-02-11Regular Papers
FastCheck: fast checkpointing and recovery for DNN training via parallel transmission and compression Enhanced Publication AI Introduction
“Training large-scale deep neural networks (DNNs) is prone to software and hardware failures, with critical failures often requiring full-machine reboots that substantially prolong training. In this paper, we propose FastCheck, a checkpoint–recovery framework that accelerates checkpointing and recovery through parallel transmission and tailored compression.”Abstract：Training large-scale deep neural networks (DNNs) is prone to software and hardware failures, with critical failures often requiring full-machine reboots that substantially prolong training. Existing checkpoint–recovery solutions either cannot tolerate such critical failures or suffer from slow checkpointing and recovery due to constrained input/output bandwidth. In this paper, we propose FastCheck, a checkpoint–recovery framework that accelerates checkpointing and recovery through parallel transmission and tailored compression. First, FastCheck partitions checkpoints into shards and leverages multiple nodes for parallel checkpointing and recovery. Second, it further reduces checkpoint size and overhead with delta compression for weights and index compression for momentum. Third, FastCheck employs lightweight and consistent health status maintenance that accurately tracks node health, preventing checkpoint transmission to failed nodes. We implement FastCheck in PyTorch and evaluate it on multiple DNN models against two baselines. Experimental results show that FastCheck reduces the checkpointing time by up to 78.42% and the recovery time by up to 77.41%, while consistently improving efficiency across different training stages.Keywords：Deep neural network models;Critical failures;Parallel transmission;Data compression;Checkpointing and recovery4|2|0Updated：2026-02-11Regular Papers
GC bypass: decoupling GC from the flash translation layer to eliminate GC-induced long-tail latency inside SSD Enhanced Publication AI Introduction
“NAND flash-based SSDs are widely used in data centers for their high performance and low power consumption. However, garbage collection (GC) operations are necessary due to the physical characteristics of flash memory, which can lead to latency overhead and path conflicts. The Venice scheme provides path diversity but lacks priority differentiation. A new approach, GC bypass, leverages Venice’s path diversity and enforces GC request transmission through dedicated controllers. This reduces long-tail latency by up to 25% compared to Venice, effectively mitigating interference between critical I/O operations and background maintenance tasks.”Abstract：NAND flash-based solid-state drives (SSDs) have been adopted by many data centers due to their high performance and low power consumption. However, the physical characteristics of the underlying flash memory necessitate garbage collection (GC) operations. Valid page migration during GC contributes significantly to latency overhead while competing for flash channel bandwidth and controller resources with user I/O requests through shared physical paths, leading to path conflicts and elevated long-tail latency. The existing Venice scheme introduces a low-cost interconnected network with path reservation mechanisms to provide substantial path diversity for SSDs. Nevertheless, its fair scheduling policy lacks priority differentiation between I/O and GC requests. In this paper, we propose GC bypass, which leverages Venice’s path diversity while enforcing GC request transmission through dedicated controllers. GC bypass decomposes GC requests into sub-requests and assigns low priority to valid page writes, enabling high-priority operations including user I/O, valid page reads, and block erases, to preempt paths reserved by low-priority requests. Valid pages failing to secure reserved paths are temporarily buffered for retry. Experimental results demonstrate that GC bypass reduces the 99.99th percentile long-tail latency by up to 25% compared to Venice. GC bypass effectively mitigates interference between critical I/O operations and background maintenance tasks while maintaining the architectural benefits of path diversity.Keywords：Solid-state drive (SSD);NAND flash;Garbage collection (GC);Interconnected network;Flash channel4|2|0Updated：2026-02-11Regular Papers
CdualTAL: multi-domain tool wear prediction using a dual-channel Transformer and cross-attention network Enhanced Publication AI Introduction
“In the field of manufacturing efficiency, a new study introduces significant research progress. Experts have developed CdualTAL, an advanced algorithm that enhances tool wear prediction. This innovative system leverages a dual-channel Transformer encoder and a custom cross-attention mechanism to effectively integrate strong and weak features, achieving superior prediction stability and accuracy.”Abstract：Accurate tool wear prediction is crucial for manufacturing efficiency, yet effectively using multi-domain sensor features is difficult due to redundant noise. There is a critical need to strategically leverage highly predictive strong features and potentially informative weak features. To address this issue, we propose CdualTAL, an improved Transformer-based encoder–attention–decoder algorithm. Its name represents the model’s key components: a correlation-adaptive feature selection algorithm module, a dual-channel Transformer encoder, an attention mechanism, and a long short-term memory (LSTM) decoder. CdualTAL employs a dual-channel encoder to independently process the full set of multi-domain features, along with a subset of strong features selected using a designed correlation-adaptive feature selection algorithm. A custom cross-attention mechanism is then used to fuse these representations, sharpening focus on strong features while judiciously integrating information from weak ones. Finally, a hierarchical LSTM decoder captures deep temporal dependencies. Validated on tool wear datasets, CdualTAL outperforms 11 state-of-the-art methods, achieving superior prediction stability and accuracy with an average R2 of 0.983 and a root mean square error (RMSE) of 4.373.Keywords：Multi-domain features;Dual-channel;Feature fusion;Tool wear;Attention mechanism;Feature enhancement4|2|0Updated：2026-02-11Regular Papers
An attention mechanism-based multi-domain feature fusion approach for active sonar target recognition Enhanced Publication AI Introduction
“In the field of underwater acoustics, researchers have made significant progress in active sonar target recognition. They proposed an attention mechanism-based multi-domain feature fusion approach, using 1DCNN-LSTM and 2DCNN with channel attention to extract deep features. This method effectively eliminates redundant information and enhances feature representation, showing superior performance and stable generalization ability in low signal-clutter ratio scenarios.”Abstract：Due to the complex and changeable marine environment, the active sonar target recognition problem has always been difficult in the field of underwater acoustics. Deep learning-based fusion recognition technology provides an effective way to solve this problem, but relying on simple concatenation strategies to fuse multi-domain features can cause information redundancy, and it is not easy to effectively mine correlation information between domains. Therefore, this paper proposes an attention mechanism-based multi-domain feature fusion approach for active sonar target recognition. By preprocessing active sonar echo signals and constructing a multi-domain feature extraction and fusion network, this method uses a one-dimensional convolutional neural network with long short-term memory (1DCNN-LSTM) and a two-dimensional convolutional neural network (2DCNN) with channel attention introduced to extract deep features from different domains. Subsequently, combining feature concatenation and constructing multi-domain cross-attention, intra- and cross-domain feature fusion is performed, which can effectively eliminate redundant information and promote inter-domain information interaction, while maximizing the retention of target features. Experimental results show that compared with single-domain methods, the network using an attention mechanism for multi-domain feature fusion strengthens cross-domain information interaction and significantly improves feature representation capability. Compared with other methods, the proposed method has obvious advantages in performance and maintains stable generalization ability in scenarios with low signal-clutter ratios.Keywords：Acoustic target recognition;Neural network;Attention mechanism;Multi-domain feature fusion4|2|0Updated：2026-02-11Regular Papers
A dual-band filtering push‒pull power amplifier with a large frequency ratio employing a hybrid-mode bandpass response balun Enhanced Publication AI Introduction
“Researchers have made significant strides in the development of a dual-band filtering push‒pull power amplifier. The team designed a filtering power dividing/combining network using a hybrid-mode filtering balun with microstrip line and substrate integrated waveguide. This innovative approach enables the amplifier to achieve a large frequency ratio and effective second-harmonic suppression. The prototype demonstrates excellent performance, with a peak output power of 36.8 dBm at low frequencies and 36 dBm at high frequencies, while maintaining out-of-band spurious rejection.”Abstract：A dual-band filtering push‒pull power amplifier (PA) with a large frequency ratio is presented in this paper. The proposed filtering power dividing/combining network is based on a hybrid-mode filtering balun using microstrip line (MSL) and substrate integrated waveguide (SIW). The MSL filtering balun operates in the S-band, with a frequency range of 2.6‒2.86 GHz. Meanwhile, the SIW filtering balun is designed for Ku-band operation, covering a frequency range of 13‒13.65 GHz. Under these conditions, the prototype is capable of attaining a frequency ratio as high as five times the original value. Due to the inherent differential characteristic of the hybrid-mode filtering balun with a large frequency ratio, the proposed push‒pull PA not only realizes filtering functionality but also achieves second-harmonic suppression. To validate the designed concept, the proposed prototype has been designed, fabricated, and measured. Measurement results demonstrate that the proposed PA achieves a 7 dB small-signal gain while maintaining out-of-band spurious rejection during active testing. The developed dual-band filtering push‒pull PA delivers excellent performance, with a peak output power of 36.8 dBm at low frequencies and 36 dBm at high frequencies. Moreover, by employing dual-band filtering baluns, the PA inherently suppresses even-order harmonics while simultaneously providing filtering characteristics in both operational bands, which effectively suppresses near-band spurious signals.Keywords：Large frequency ratio;Dual-band filtering balun;Harmonic suppression;Push‒pull power amplifier5|2|0Updated：2026-02-11
SEE MORE
0 1 Hybrid-augmented intelligence: collaboration and cognition
0 4 Applications of artificial intelligence in intelligent manufacturing: a review*
0 5 Challenges and opportunities: from big data to knowledge in AI 2.0
0 6 Current trends in the development of intelligent unmanned autonomous systems
0 7 Recent advances in efficient computation of deep convolutional neural networks
0 8 Terahertz time-domain spectroscopy and micro-cavity components for probing samples: a review
0 9 Cross-media analysis and reasoning: advances and directions
SEE MORE
Videos
-
00:02:512023 Issue 1 | Scalability and efficiency challenges for the exascale supercomputing system: practice of a parallel supporting environment on the Sunway exascale prototype system
2023-12-30Play Total： 24 - 00:02:30
2023 Issue 6 | Model division multiple access for semantic communications
2023-12-30Play Total： 15 - 00:02:15
2022 Issue 10 | Discussion on a new paradigm of endogenous security towards 6G networks
2023-12-30Play Total： 3 - 00:02:22
2022 Issue 12 | Technology trends in large-scale high-efficiency network computing
2023-12-30Play Total： 3 - 00:02:48
2022 Issue 6 | Self-deployed execution environment for high performance computing
2022-08-03Play Total： 9 - 00:02:24
2022 Issue 2 | A full-process intelligent trial system for smart court
2022-05-17Play Total： 9 - 00:02:37
2022 Issue 3 | Automatic protocol reverse engineering for industrial control systems with dynamic taint analysis
2022-05-17Play Total： 5 - 00:05:36
P1 Speech by Academician Baoyan Duan
2022-04-17Play Total： 13 - 00:02:27
P2 Speech by Professor Min Sheng, Xidian University
2022-04-17Play Total： 8 - 00:02:37
P3 Speech by Professor Yunsong Li, Xidian University
2022-04-17Play Total： 12
SEE MORE
- Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
- Tel：+86-571-88273162 Email：fitee@zju.edu.cn
- Copyright © 2000 - 2025, Zhejiang University Press 京ICP备09064830号-19
京公网安备11010802024621 - It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
- Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
0