Spiking neural networks (SNNs) have emerged as a promising paradigm for effective event-driven computation. However, CMOS-based SNN designs are limited by power consumption and complexity, while nonvolatile memory (NVM)-based SNN designs often lack biological characteristics and require active capacitive circuits to emulate neuronal dynamics. In this paper, we propose a thermally interplayed spin-orbit torque magnetic tunnel junction (TI-MTJ) macro that integrates core SNN functionalities. Our neuron array autonomously achieves leaky integrate-and-fire (LIF) model within the TI-MTJ device, thus improving power efficiency and simplifying circuit structure. Additionally, the proposed synaptic array provides adaptive in-situ responses based on a simplified spike-timing-dependent plasticity (STDP) rule. To enhance biological plausibility, our macro incorporates real-time spike monitoring and inhibition mechanisms. A comprehensive device-circuit-algorithm co-optimization framework validates the high performance of the TI-MTJ macro, achieving a synaptic energy consumption of 6.07fJ per spike, an inference accuracy of 97.76% on the MNIST dataset, and an energy efficiency of 22.8TOPS/W.

Downlink precoding in massive multiple input multiple output (MIMO) systems involves high-dimensional sparse matrix calculations, which poses challenges to existing architectures. Computing-in-memory (CIM) has significant advantages in handling large-scale parallel operations, but sparse computing for wireless communication remains underexplored. In this paper, we propose a novel CIM accelerator based on magnetic random access memory (MRAM) leveraging adaptive multi-sparse mode technology for optimized sparse matrix multiplication in MIMO communication systems. This architecture represents the first application of CIM technology for processing sparse matrices in MIMO precoding tasks, minimizing storage requirements and enhancing parallel processing speed. Experimental results demonstrate that, for a 32×256×8 MIMO downlink precoding task with 90% sparsity, the symbol error rate is reduced to 0.1% at a signal-to-noise ratio of 20dB, achieving 8.35× reduction in storage overhead, 39.4× power saving and 9.85× speedup. These results position our accelerator as a promising candidate for processing sparse data in 5G massive MIMO systems.

In this work, we explore a cost-effective framework for multilingual image generation. We find that, unlike models tuned on high-quality images with multilingual annotations, leveraging text encoders pre-trained on widely available, noisy Internet image-text pairs significantly enhances data efficiency in text-to-image (T2I) generation across multiple languages. Based on this insight, we introduce MuLan, Multi-Language adapter, a lightweight language adapter with fewer than 20M parameters, trained alongside a frozen text encoder and image diffusion model. Compared to previous multilingual T2I models, this framework offers: (1) Cost efficiency. Using readily accessible English data and off-the-shelf multilingual text encoders minimizes the training cost; (2) High performance. Achieving comparable generation capabilities in over 110 languages with CLIP similarity scores nearly matching those in English (39.57 for English vs. 39.61 for other languages); and (3) Broad applicability. Seamlessly integrating with compatible community tools like LoRA, LCM, ControlNet, and IP-Adapter, expanding its potential use cases.

Abstract Macro lens has the advantages of high resolution and large magnification, and 3D modeling of small and detailed objects can provide richer information. However, defocus blur in macrophotography is a long‐standing problem that heavily hinders the clear imaging of the captured objects and high‐quality 3D reconstruction of them. Traditional image deblurring methods require a large number of images and annotations, and there is currently no multi‐view 3D reconstruction method for macrophotography. In this work, we propose a joint deblurring and 3D reconstruction method for macrophotography. Starting from multi‐view blurry images captured, we jointly optimize the clear 3D model of the object and the defocus blur kernel of each pixel. The entire framework adopts a differentiable rendering method to self‐supervise the optimization of the 3D model and the defocus blur kernel. Extensive experiments show that from a small number of multi‐view images, our proposed method can not only achieve high‐quality image deblurring but also recover high‐fidelity 3D appearance.

This paper presents a low temporal noise, low-power, 8-Mpixel, rolling-shutter (RS)-type, back-illuminated CMOS image sensor (CIS) employing through silicon via (TSV) 3D-stack technology. To achieve temporal noise less than 1erms-, we explored auto-zero (AZ) column single-slope (SS) ADC and fast correlated multi-sampling (CMS) techniques. The pixel signal was sampled two times by the readout circuits using a 9-bits ADC, resulting in a 10-bits digital output. To enhance image quality in low light conditions, we adopted a parity column counter (PCC) for power supply stabilization and H-banding elimination, and employed row-wise noise reduction (RWNR) and dark-current non-uniformity calibration (DCNUC) techniques for reducing row-wise noise and improving image uniformity. Our CIS chip was fabricated using a 55nm 1P4M (pixel substrate) and a 55nm 1P5M (logic substrate) CIS 3D stacked process. The die area is ~3.99*3.45 mm2with 1.008-μm pixel pitch and the total energy consumption is 170mW under a 2.8V analog-VDD and a 1.2V digital-VDD. The chip achieves a temporal noise of only ~0.88erms-, fixed pattern noise (FPN) of ~25.08μVrms, row-wise noise of ~5.5μVrmsand an energy efficiency figure-of-merit (FoM) of ~0.6erms-*nJ/step at a frame rate of 60 frames per second (FPS).

Since its proposal, Neural Radiance Fields (NeRF) has achieved great success in related tasks, mainly adopting the hierarchical volume sampling (HVS) strategy for volume rendering. However, the HVS of NeRF approximates distributions using piecewise constant functions, which provides a relatively rough estimation. Based on the obser-vation that a well-trained weight function$w(t)$and the$L_{0}$distance between points and the surface have very high sim-ilarity, we propose$L_{0}$-Sampler by incorporating the$L_{0}$model into$w(t)$to guide the sampling process. Specif-ically, we propose using piecewise exponential functions rather than piecewise constant functions for interpolation, which can not only approximate quasi-$L_{0}$weight distri-butions along rays quite well but can be easily imple-mented with a few lines of code change without additional computational burden. Stable performance improvements can be achieved by applying$L_{0}$-Sampler to NeRF and re-lated tasks like 3D reconstruction. Code is available at https://ustc3dv.github.io/L0-Sampler/.

Adversarial Training (AT) has become arguably the state-of-the-art algorithm for extracting robust features. However, researchers recently notice that AT suffers from severe robust overfitting problems, particularly after learning rate (LR) decay. In this paper, we explain this phenomenon by viewing adversarial training as a dynamic minimax game between the model trainer and the attacker. Specifically, we analyze how LR decay breaks the balance between the minimax game by empowering the trainer with a stronger memorization ability, and show such imbalance induces robust overfitting as a result of memorizing non-robust features. We validate this understanding with extensive experiments, and provide a holistic view of robust overfitting from the dynamics of both the two game players. This understanding further inspires us to alleviate robust overfitting by rebalancing the two players by either regularizing the trainer's capacity or improving the attack strength. Experiments show that the proposed ReBalanced Adversarial Training (ReBAT) can attain good robustness and does not suffer from robust overfitting even after very long training. Code is available at https://github.com/PKU-ML/ReBAT.

This article concerns the problems of synchronization in a fixed time or prespecified time for memristive complex-valued neural networks (MCVNNs), in which the state variables, activation functions, rates of neuron self-inhibition, neural connection memristive weights, and external inputs are all assumed to be complex-valued. First, the more comprehensive fixed-time stability theorem and more accurate estimations on settling time (ST) are systematically established by using the comparison principle. Second, by introducing different norms of complex numbers instead of decomposing the complex-valued system into real and imaginary parts, we successfully design several simpler discontinuous controllers to acquire much improved fixed-time synchronization (FXTS) results. Third, based on similar mathematical derivations, the preassigned-time synchronization (PATS) conditions are explored by newly developed new control strategies, in which ST can be prespecified and is independent of initial values and any parameters of neural networks and controllers. Finally, numerical simulations are provided to illustrate the effectiveness and superiority of the improved synchronization methodology.