Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

This paper introduces Goku, a state-of-the-art family of joint image-and-video generation models leveraging rectified flow Transformers to achieve industry-leading performance. We detail the foundational elements enabling high-quality visual generation, including the data curation pipeline, model architecture design, flow formulation, and advanced infrastructure for efficient and robust large-scale training. The Goku models demonstrate superior performance in both qualitative and quantitative evaluations, setting new benchmarks across major tasks. Specifically, Goku achieves 0.76 on GenEval and 83.65 on DPG-Bench for text-to-image generation, and 84.85 on VBench for text-to-video tasks. We believe that this work provides valuable insights and practical advancements for the research community in developing joint image-and-video generation models.

Using pruning techniques to prune redundant weights in large language models (LLMs) for model size reduction, enabling deployment on devices to deliver high-quality services, has garnered significant attention from industry and academia. However, most existing pruning methods suffer from two major problems: (1) they rely on operations with high computational complexity, such as Hessian matrix calculation, and (2) high pruning rate leads to a significant decrease in model accuracy. To this end, this paper proposes a low resource requirement and low accuracy loss post-training pruning approach, namely the compensated post-training pruning method (CPP) for on-device LLM services. First, CPP employs singular value decomposition on weight matrices, sorting the decomposed singular values in descending order. Based on the pruning ratio, it retains the principal eigenvector corresponding to the larger singular values. To maintain consistent output feature distributions, CPP applies orthogonal transformations to input data and weight matrices, leveraging the principle of matrix orthogonality invariance. Compared with pruning approaches based on the Hessian matrix, CPP does not need to iteratively calculate the second derivative, thereby avoiding a high computational overhead. Second, the CPP incorporates bias compensation to use valuable information in pruned weights to improve the accuracy of the model. It constructs mapping relationships between input features and pruned weights through tensor decomposition techniques to generate bias compensation terms. These terms fine-tune the output of each layer, reducing pruning-induced errors from ratio-based pruning, and consequently improving model accuracy. Finally, CPP is validated through comprehensive experiments on nine benchmark datasets (e.g., WikiText-2 and PIQA) using large language models (i.e., LLaMA and OPT). Specifically, compared with the FLAP, CPP demonstrates 6.68% reduction in average pruning time. At pruning ratios of 10% and 20%, CPP achieves 2. 14% and 1.45% reductions in perplexity, respectively, along with 1.22% to 3.43% improvement in zeroshot inference accuracy.

Meal preparation is an important instrumental activity of daily living (IADL). While existing research has explored robotic assistance in meal preparation tasks such as cutting and cooking, the crucial task of peeling has received less attention. Robot-assisted peeling, conventionally a bimanual task, is challenging to deploy in the homes of care recipients using two wheelchair-mounted robot arms due to ergonomic and transferring challenges. This paper introduces a robot-assisted peeling system utilizing a single robotic arm and an assistive cutting board, inspired by the way individuals with one functional hand prepare meals. Our system incorporates a multimodal active perception module to determine whether an area on the food is peeled, a human-in-the-loop long-horizon planner to perform task planning while catering to a user’s preference for peeling coverage, and a compliant controller to peel the food items. We demonstrate the system on 12 food items representing the extremes of different shapes, sizes, skin thickness, surface textures, skin vs flesh colors, and deformability. Check out the Morpheus project at https://emprise.cs.cornell.edu/morpheus/.

Limited by the scarcity of synthetic aperture radar (SAR) systems, image augmentation is of great significance to SAR image detection, target recognition, and other application fields. However, traditional image augmentation methods rarely consider the SAR imaging mechanism, resulting in the inability to accurately reflect the anisotropic characteristics of target scattering. This paper introduces a novel SAR image augmentation method based on rebooting auxiliary classifier generative adversarial networks (Re-ACGAN), named IAM-ACGAN (Integrating Attention Mechanism with ACGAN). In this scheme, IAM-ACGAN integrates two attention mechanisms, channel attention (CA) and spatial attention (SA), into the discriminator of the GAN backbone to enhance classification accuracy. These two mechanisms can enhance the channel and spatial features of the input SAR images respectively. A self-constructed simulation ship dataset and a MSTAR real dataset both demonstrate the effectiveness of IAM-ACGAN. Compared with ACGAN and Re-ACGAN augmentation methods, IAM-ACGAN can provide higher image generation accuracy.

Non-line-of-sight (NLOS) moving target imaging is an emerging and challenging technology with potential applications in autonomous driving, security detection, disaster response, and more. In this article, a novel algorithm dubbed NLOS detail recovery via alternating direction method of multipliers (NDR-ADMMs) is proposed for NLOS moving target imaging. In our scheme, the static clutter filter (SCF) we proposed is utilized for NLOS clutter suppression, which facilitates hidden motion target echo extraction. To address the sparsity of echoes caused by scene complexity and target motion, we introduce a regularization constraint termed detail-aware regularization (DAR), which enhances details and suppresses noise in NLOS scenes by incorporating information from neighboring cells and expanding the receptive field of the image. Then, we propose the NDR-ADMM that combines DAR,$\ell _{1}$-norm, and ADMM to reconstruct high-resolution NLOS moving target images. Further, the corresponding fast version, NDR-ADMM+, is derived by mapping the NDR-ADMM to the adaptive parameter learning network for improving robustness and convergence. Finally, the proposed NDR-ADMM and NDR-ADMM+ are verified by simulated data and measured data we collected via millimeter-wave (MMW) radar in various NLOS scenarios. Compared to other state-of-the-art methods, NDR-ADMM+ demonstrates superior performance, robustness, and noise immunity, with NDR-ADMM following closely behind. This is attributed to DAR’s ability to capture details and suppress interference. Additionally, NDR-ADMM+ and AF-AMPnet offer the fastest processing speeds.

Spaceborne Synthetic Aperture Radar(SAR) can be mounted on space vehicles to collect information on the entire planet with all-day and all-weather imaging capacity. However, the spaceborne SAR sensor may suffer from severe interferences resulting in image degradation, which puts forward an urgent need for interference identification and mitigation. This paper proposes a high-precision interference identification method for spaceborne SAR images, named HPII-NET. The network is trained with simulation and real measurement data, and the effectiveness of the proposed method is verified by both simulation and the Setinel-1 satellite SAR images. Compared with the traditional identification networks, experimental results show that the HPII-NET can achieve more than 97% interference identification accuracy and thus improve the interference identification performance.

Preterm newborns are vulnerable and easily infected due to the immature immune system. Late-onset neonatal sepsis occurring 48 hours after birth is a widespread disease among preterm newborns leading to high mortality and morbidity rates. The diagnosis is primarily based on biochemistry test, and the prescribed treatment is to use antibiotics. Risk averse clinicians, often applied overdose to reduce the mortality. A non-invasive method on monitoring vital sign signals deterioration to predict late-onset neonatal sepsis is proposed in this paper. First, we set up collectors within the local networks in Neonatal Intensive Care Units (NICUs) where bedside monitoring machines locate to capture the necessary data. Then they were transformed to images according to specific rules. Finally, a convolutional neural network was built to predict the onset of sepsis. Pilot experiments conducted on data we have collected demonstrated the feasibility of this deep learning model. This method could be incorporated into the current clinical workflow as a decision support system and provide useful information for clinicians.

On-road risk assessment is one of the important topics for intelligent vehicles research. Efficiency of risk assessment is affected by lack of on-road vehicles information, which should be solved by The Vehicular Ad-Hoc Network (VANET). In this paper, a regional vehicles hazard level estimation method, which employs Ising model to explain the inter-vehicles relationship, is proposed, an inter-vehicles relationship model is constructed, and corresponding parameters mapping relationship is studied. Then Ising model's energy formula is used to illustrate regional hazard level. Moreover, based on the inter-vehicles relationship, we present an approach to build a regional threat distribution map, which indicates the passing threat of a certain ego-car. A series of experiments are done to examine the efficiency of the proposed method. Experiment results show that the proposed method can produce a reasonable danger evaluation for an ego-car.