journal article·2026-05Open access

Heterogeneous Integration Strategies of Beyond‐von Neumann Neuromorphic Electronics for Sensory in‐Memory Computing

Zongjie Shen, Jiadong Shen, Herong Sheng, Lixing Kang, Zhongming Zeng, Wei Chen, Alei Li, Chun Zhao

Advanced Functional Materials· Volume 36· Issue 39

Abstract

ABSTRACT This comprehensive review presents heterogeneous integration strategies for neuromorphic electronics, aiming to eliminate the von Neumann bottleneck, with a focus on enabling in‐sensor computation. It provides the evolution trajectory of memristor devices and arrays—from theoretical grounding and physical implementation to promising integration schemes. The device‐level discussion encompasses internal integration approaches that leverage multidimensional materials to modulate switching dynamics and enable artificial synaptic behaviors. At the array level, diverse paradigms of heterogeneous integration strategies are investigated, including architectures of 1D, resistive randomaccess memory, transistor‐rram, memtransistor, and 3D crossbar arrays. Each architecture is evaluated based on its functional advantages, physical significance, and neuromorphic applicability in systems that include convolutional neural networks, spiking neural networks, and reservoir computing. Emphasizing the syncretic design of materials, devices, and circuits, the review illustrates how these strategies facilitate the fusion of sensing, memory, and computation, thereby overcoming limitations of conventional computing. Representative implementations, ranging from planar wafer‐scale arrays to vertical 3D‐integrated systems, demonstrate significant innovations in energy efficiency and adaptive control for complex computational parallelism. The review concludes by identifying key challenges in material compatibility, fabrication complexity, and energy management, while highlighting effective solutions and promising pathways toward scalable, high‐performance neuromorphic hardware for artificial general intelligence.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Neural Networks and Reservoir Computing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of CHIPS Xi'an Jiaotong‐Liverpool University Suzhou China

School of Advanced Technology Xi'an Jiaotong‐Liverpool University Suzhou China

Division of Advanced Materials Suzhou Institute of Nano‐Tech and Nano‐Bionics Chinese Academy of Sciences Suzhou China

Nanofabrication Facility Suzhou Institute of Nano‐Tech and Nano‐Bionics Chinese Academy of Sciences Suzhou China

Quantum Science Center of Guangdong‐Hong Kong‐Macao Greater Bay Area (Guangdong) Shenzhen China

Funding

National Natural Science Foundation of China

References (100+)

Show source-provided references
1. 10.1038/s44287-024-00038-510.1038/s44287-024-00038-5 ↗
2. 10.1038/s41586-025-08733-510.1038/s41586-025-08733-5 ↗
3. 10.1038/s41467-025-59815-x10.1038/s41467-025-59815-x ↗
4. 10.1038/s41467-025-60854-710.1038/s41467-025-60854-7 ↗
5. 10.1038/s41467-025-58039-310.1038/s41467-025-58039-3 ↗
6. 10.3389/felec.2025.149391110.3389/felec.2025.1493911 ↗
7. 10.1021/acsphotonics.5c0113310.1021/acsphotonics.5c01133 ↗
8. H.Park J.Shin H.Kim et al. IEEE T. Circuits‐I72(2025):6640.10.1109/TCSI.2025.3573564 ↗
9. A Dynamic Adaptive Activation Neuron‐Transistor for Dynamic Sparse Neural Networks in Advanced Driving Assistance System
10. 10.1109/ACCESS.2020.298154010.1109/ACCESS.2020.2981540 ↗
11. 10.1002/adfm.20241695410.1002/adfm.202416954 ↗
12. F. C.Augusto Vega A.Ram´ırez andM.Valero 2011 International Conference on Embedded Computer Systems: Architectures Modeling and Simulation (IEEE 2011).
13. 10.1002/adfm.20242004510.1002/adfm.202420045 ↗
14. 10.1038/s41586-023-06337-510.1038/s41586-023-06337-5 ↗
15. 10.1002/adma.20241924510.1002/adma.202419245 ↗
16. 10.1109/JLT.2015.239545310.1109/JLT.2015.2395453 ↗
17. 10.1016/j.device.2025.10075710.1016/j.device.2025.100757 ↗
18. 10.1109/TBCAS.2019.293867210.1109/TBCAS.2019.2938672 ↗
19. 10.1007/s40843-025-3275-410.1007/s40843-025-3275-4 ↗
20. 10.1007/s40843-025-3524-y10.1007/s40843-025-3524-y ↗
21. Low‐Power FPGA Design Techniques for Next‐Generation Mobile Devices
22. 10.1007/s40843-025-3576-610.1007/s40843-025-3576-6 ↗
23. 10.1049/enc2.1210710.1049/enc2.12107 ↗
24. 10.1109/ACCESS.2022.315996710.1109/ACCESS.2022.3159967 ↗
25. 10.1002/smll.20250252510.1002/smll.202502525 ↗
26. 10.1109/ACCESS.2023.333628010.1109/ACCESS.2023.3336280 ↗
27. 10.3390/electronics911198010.3390/electronics9111980 ↗
28. 10.1016/j.mejo.2024.10630810.1016/j.mejo.2024.106308 ↗
29. 10.1126/science.adf553810.1126/science.adf5538 ↗
30. 10.1016/j.mser.2024.10089310.1016/j.mser.2024.100893 ↗
31. 10.1002/adma.20210802510.1002/adma.202108025 ↗
32. 10.1002/adma.20231070410.1002/adma.202310704 ↗
33. 10.1016/j.neunet.2024.10667710.1016/j.neunet.2024.106677 ↗
34. 10.3389/fnins.2024.133542210.3389/fnins.2024.1335422 ↗
35. 10.1002/aisy.20240026510.1002/aisy.202400265 ↗
36. 10.1016/j.neucom.2025.12967810.1016/j.neucom.2025.129678 ↗
37. Highly Efficient Back‐End‐of‐Line Compatible Flexible Si‐Based Optical Memristive Crossbar Array for Edge Neuromorphic Physiological Signal Processing and Bionic Machine Vision
38. 10.1038/s41928-025-01433-y10.1038/s41928-025-01433-y ↗
39. 10.1002/adma.20241391610.1002/adma.202413916 ↗
40. 10.1002/adfm.20241910410.1002/adfm.202419104 ↗
41. 10.1038/s44287-024-00037-610.1038/s44287-024-00037-6 ↗
42. 10.1038/s41586-023-06860-510.1038/s41586-023-06860-5 ↗
43. 10.1109/TCT.1971.108333710.1109/TCT.1971.1083337 ↗
44. 10.1038/nature0693210.1038/nature06932 ↗
45. 10.1038/nnano.2008.16010.1038/nnano.2008.160 ↗
46. 10.1038/nnano.2009.45610.1038/nnano.2009.456 ↗
47. 10.1109/TNANO.2005.84693610.1109/TNANO.2005.846936 ↗
48. 10.1038/nmat161410.1038/nmat1614 ↗
49. 10.1038/nmat200910.1038/nmat2009 ↗
50. 10.1088/0957-4484/22/25/25400210.1088/0957-4484/22/25/254002 ↗
51. 10.1145/338096910.1145/3380969 ↗
52. 10.1038/s41928-018-0023-210.1038/s41928-018-0023-2 ↗
53. 10.1109/TNANO.2020.298212810.1109/TNANO.2020.2982128 ↗
54. 10.1002/adma.20230721810.1002/adma.202307218 ↗
55. 10.1002/adfm.20231680210.1002/adfm.202316802 ↗
56. 10.1002/adma.20230739310.1002/adma.202307393 ↗
57. 10.1002/adom.20240172410.1002/adom.202401724 ↗
58. 10.1038/s41467-024-46323-710.1038/s41467-024-46323-7 ↗
59. 10.1038/s41467-024-48810-310.1038/s41467-024-48810-3 ↗
60. 10.1038/s41928-017-0002-z10.1038/s41928-017-0002-z ↗
61. 10.1002/adma.20170591410.1002/adma.201705914 ↗
62. 10.1038/nature1444110.1038/nature14441 ↗
63. 10.1038/ncomms1519910.1038/ncomms15199 ↗
64. 10.1038/s41928-018-0092-210.1038/s41928-018-0092-2 ↗
65. Recent Advances in in‐Memory Computing: Exploring Memristor and Memtransistor Arrays with 2D Materials
66. 10.1002/adma.20241130010.1002/adma.202411300 ↗
67. 10.1109/TED.2014.231020010.1109/TED.2014.2310200 ↗
68. 10.1109/TNANO.2015.240377210.1109/TNANO.2015.2403772 ↗
69. 10.1142/S021798491550244910.1142/S0217984915502449 ↗
70. 10.3390/nano1008143710.3390/nano10081437 ↗
71. 10.1002/aisy.20210023610.1002/aisy.202100236 ↗
72. 10.1016/j.nanoen.2022.10774410.1016/j.nanoen.2022.107744 ↗
73. S.‐S.Sheu M.‐F.Chang andK.‐F.Lin “A 4Mb Embedded SLC Resistive‐RAM Macro with 7.2ns Read‐write Random‐access Time and 160ns MLC‐access Capability ” in2011 IEEE International Solid‐State Circuits Conference (IEEE 2011).10.1109/ISSCC.2011.5746281 ↗
74. 10.3390/electronics1018222210.3390/electronics10182222 ↗
75. 10.1016/j.microrel.2018.07.06510.1016/j.microrel.2018.07.065 ↗
76. S.Tuli M.Rios A.Levisse andD. A.Esl 2020 25th Asia and South Pacific Design Automation Conference (ASP‐DAC) (IEEE 2020) 336–337.
77. Y. M. Y. L.Song X. Y.Xue andF. J.Xiao 2013 Symposium on VLSI Technology (IEEE 2013).
78. 10.1038/s41586-020-1942-410.1038/s41586-020-1942-4 ↗
79. 10.1038/s41467-018-04484-210.1038/s41467-018-04484-2 ↗
80. 10.3390/mi1104034110.3390/mi11040341 ↗
81. 10.1038/s41928-019-0221-610.1038/s41928-019-0221-6 ↗
82. 10.1007/s11432-023-3800-910.1007/s11432-023-3800-9 ↗
83. 10.1002/aisy.20210011110.1002/aisy.202100111 ↗
84. 10.1038/nmat351010.1038/nmat3510 ↗
85. 10.1002/adfm.20242380010.1002/adfm.202423800 ↗
86. 10.1038/s41565-020-0655-z10.1038/s41565-020-0655-z ↗
87. 10.1063/1.512491510.1063/1.5124915 ↗
88. 10.1126/science.ade348310.1126/science.ade3483 ↗
89. 10.1038/s41928-024-01280-310.1038/s41928-024-01280-3 ↗
90. 10.1002/smsc.20240024110.1002/smsc.202400241 ↗
91. 10.1002/adfm.20241283210.1002/adfm.202412832 ↗
92. 10.1002/adma.20250243810.1002/adma.202502438 ↗
93. 10.1002/adfm.20150352210.1002/adfm.201503522 ↗
94. 10.1021/acsnano.0c0944110.1021/acsnano.0c09441 ↗
95. 10.1002/smll.20250371610.1002/smll.202503716 ↗
96. 10.1021/acsnano.5c0668810.1021/acsnano.5c06688 ↗
97. 10.1016/j.cej.2025.16307910.1016/j.cej.2025.163079 ↗
98. 10.1002/adma.20230265810.1002/adma.202302658 ↗
99. 10.1038/s41586-024-07406-z10.1038/s41586-024-07406-z ↗
100. 10.1038/s41586-024-07438-510.1038/s41586-024-07438-5 ↗