World models [1, 2] are designed to predict future scenes and facilitate motion planning for agents. These models first construct lower-dimensional representations of the scenes, which serve as a foundation for learning the patterns of environmental dynamics. This capability supports the identification of potential dangers, the determination of traffic participants' intentions, and ultimately leads to improved decision-making. This paper focuses on world models for autonomous driving [3, 4, 5, 6, 7], where accurately predicting the future behavior of traffic participants is essential for the agent's planning. Existing methods [8, 6, 7, 9] mainly provide instance-level predictions for traffic participants from a Bird's Eye View (BEV) perspective, or directly utilize diffusion models [10, 11, 12, 13, 14] to generate future pixel-level driving views. However, these methods have difficulty in establishing fine-grained, 3D associations between changes in the scene and the agent's motion planning. Recent advancements in 3D occupancy technologies [15, 16, 17, 18, 19] have gained significant attention from both academia and industry [20, 21].

Accurate sign language understanding serves as a crucial communication channel for individuals with disabilities. Current sign language translation algorithms predominantly rely on RGB frames, which may be limited by fixed frame rates, variable lighting conditions, and motion blur caused by rapid hand movements. Inspired by the recent successful application of event cameras in other fields, we propose to leverage event streams to assist RGB cameras in capturing gesture data, addressing the various challenges mentioned above. Specifically, we first collect a large-scale RGB-Event sign language translation dataset using the DVS346 camera, termed VECSL, which contains 15,676 RGB-Event samples, 15,191 glosses, and covers 2,568 Chinese characters. These samples were gathered across a diverse range of indoor and outdoor environments, capturing multiple viewing angles, varying light intensities, and different camera motions. Due to the absence of benchmark algorithms for comparison in this new task, we retrained and evaluated multiple state-of-the-art SLT algorithms, and believe that this benchmark can effectively support subsequent related research. Additionally, we propose a novel RGB-Event sign language translation framework (i.e., M$^2$-SLT) that incorporates fine-grained micro-sign and coarse-grained macro-sign retrieval, achieving state-of-the-art results on the proposed dataset. Both the source code and dataset will be released on https://github.com/Event-AHU/OpenESL.

We then introduce a novel hierarchical knowledge distillation strategy that incorporates the similarity matrix, feature representation, and response map-based distillation to guide the learning of the student Transformer network. We also enhance the model's ability to capture temporal dependencies by applying the temporal Fourier transform to establish temporal relationships between video frames. We adapt the network model to specific target objects during testing via a newly proposed test-time tuning strategy to achieve high performance and flexibility in target tracking. Recognizing the limitations of existing event-based tracking datasets, which are predominantly low-resolution, we propose EventVOT, the first large-scale high-resolution event-based tracking dataset. It comprises 1141 videos spanning diverse categories such as pedestrians, vehicles, UAVs, ping pong, etc. Extensive experiments on both low-resolution (FE240hz, VisEvent, FELT), and our newly proposed high-resolution EventVOT dataset fully validated the effectiveness of our proposed method. Both the benchmark dataset and source code have been released on https://github.com/Event-AHU/EventVOT_Benchmark

Abstract--X-ray image based medical report generation achieves significant progress in recent years with the help of the large language model, however, these models have not fully exploited the effective information in visual image regions, resulting in reports that are linguistically sound but insufficient in describing key diseases. In this paper, we propose a novel associative memory-enhanced X-ray report generation model that effectively mimics the process of professional doctors writing medical reports. It considers both the mining of global and local visual information and associates historical report information to better complete the writing of the current report. Some researchers already exploit the effectiveness of LLM in the X-ray based medical report generation, such as R2Gen-GPT [1], R2Gen-I. This task can greatly alleviate the work pressure on high-quality text at the linguistic level, but they struggle to doctors and reduce the waiting time for patients, providing accurately identify abnormal conditions, diseases, and other a feasible method for empowering artificial intelligence in critical information in clinical diagnostic indicators. Although the task has made considerable result, although the obtained medical reports may appear to be progress in recent years, there are still many issues, such well-structured, they are actually difficult to address the practical as the difficulty in detecting key diseases and the challenge problems. In MRG, models typically need to process two shown in Figure 1, our framework contains two stages, i.e., the primary sources of information: visual information from medical disease-aware visual token mining and the associative memory images and linguistic information from existing medical augmented X-ray medical report generation. R2Gen [9] introduces a memory-driven the first stage, we extract the vision features of a given X-Transformer for radiology report generation, using relational ray image using the Swin Transformer network [4].

There is a growing necessity for edge training to adapt to dynamically changing environment. Neuromorphic computing represents a significant pathway for high-efficiency intelligent computation in energy-constrained edges, but existing neuromorphic architectures lack the ability of directly training spiking neural networks (SNNs) based on backpropagation. We develop a multi-core neuromorphic architecture with Feedforward-Propagation, Back-Propagation, and Weight-Gradient engines in each core, supporting high efficient parallel computing at both the engine and core levels. It combines various data flows and sparse computation optimization by fully leveraging the sparsity in SNN training, obtaining a high energy efficiency of 1.05TFLOPS/W@ FP16 @ 28nm, 55 ~ 85% reduction of DRAM access compared to A100 GPU in SNN trainings, and a 20-core deep SNN training and a 5-worker federated learning on FPGAs. Our study develops the first multi-core neuromorphic architecture supporting the direct SNN training, facilitating the neuromorphic computing in edge-learnable applications.

Pattern recognition leveraging both RGB and Event cameras can significantly enhance performance by deploying deep neural networks that utilize a fine-tuning strategy. Inspired by the successful application of large models, the introduction of such large models can also be considered to further enhance the performance of multi-modal tasks. However, fully fine-tuning these models leads to inefficiency and lightweight fine-tuning methods such as LoRA and Adapter have been proposed to achieve a better balance between efficiency and performance. To our knowledge, there is currently no work that has conducted parameter-efficient fine-tuning (PEFT) for RGB-Event recognition based on pre-trained foundation models. To address this issue, this paper proposes a novel PEFT strategy to adapt the pre-trained foundation vision models for the RGB-Event-based classification. Specifically, given the RGB frames and event streams, we extract the RGB and event features based on the vision foundation model ViT with a modality-specific LoRA tuning strategy. The frame difference of the dual modalities is also considered to capture the motion cues via the frame difference backbone network. These features are concatenated and fed into high-level Transformer layers for efficient multi-modal feature learning via modality-shared LoRA tuning. Finally, we concatenate these features and feed them into a classification head to achieve efficient fine-tuning. The source code and pre-trained models will be released on \url{https://github.com/Event-AHU/VELoRA}.

We introduce Open-Sora Plan, an open-source project that aims to contribute a large generation model for generating desired high-resolution videos with long durations based on various user inputs. Our project comprises multiple components for the entire video generation process, including a Wavelet-Flow Variational Autoencoder, a Joint Image-Video Skiparse Denoiser, and various condition controllers. Moreover, many assistant strategies for efficient training and inference are designed, and a multi-dimensional data curation pipeline is proposed for obtaining desired high-quality data. Benefiting from efficient thoughts, our Open-Sora Plan achieves impressive video generation results in both qualitative and quantitative evaluations. We hope our careful design and practical experience can inspire the video generation research community. All our codes and model weights are publicly available at \url{https://github.com/PKU-YuanGroup/Open-Sora-Plan}.

Recent improvements in visual synthesis have significantly enhanced the depiction of generated human photos, which are pivotal due to their wide applicability and demand. Nonetheless, the existing text-to-image or text-to-video models often generate low-quality human photos that might differ considerably from real-world body structures, referred to as "abnormal human bodies". Such abnormalities, typically deemed unacceptable, pose considerable challenges in the detection and repair of them within human photos. These challenges require precise abnormality recognition capabilities, which entail pinpointing both the location and the abnormality type. Intuitively, Visual Language Models (VLMs) that have obtained remarkable performance on various visual tasks are quite suitable for this task. However, their performance on abnormality detection in human photos is quite poor. Hence, it is quite important to highlight this task for the research community. In this paper, we first introduce a simple yet challenging task, i.e., \textbf{F}ine-grained \textbf{H}uman-body \textbf{A}bnormality \textbf{D}etection \textbf{(FHAD)}, and construct two high-quality datasets for evaluation. Then, we propose a meticulous framework, named HumanCalibrator, which identifies and repairs abnormalities in human body structures while preserving the other content. Experiments indicate that our HumanCalibrator achieves high accuracy in abnormality detection and accomplishes an increase in visual comparisons while preserving the other visual content.

Existing event stream-based pattern recognition models usually represent the event stream as the point cloud, voxel, image, etc., and design various deep neural networks to learn their features. Although considerable results can be achieved in simple cases, however, the model performance may be limited by monotonous modality expressions, sub-optimal fusion, and readout mechanisms. In this paper, we propose a novel dual-stream framework for event stream-based pattern recognition via differentiated fusion, termed EFV++. It models two common event representations simultaneously, i.e., event images and event voxels. The spatial and three-dimensional stereo information can be learned separately by utilizing Transformer and Graph Neural Network (GNN). We believe the features of each representation still contain both efficient and redundant features and a sub-optimal solution may be obtained if we directly fuse them without differentiation. Thus, we divide each feature into three levels and retain high-quality features, blend medium-quality features, and exchange low-quality features. The enhanced dual features will be fed into the fusion Transformer together with bottleneck features. In addition, we introduce a novel hybrid interaction readout mechanism to enhance the diversity of features as final representations. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art performance on multiple widely used event stream-based classification datasets. Specifically, we achieve new state-of-the-art performance on the Bullying10k dataset, i.e., $90.51\%$, which exceeds the second place by $+2.21\%$. The source code of this paper has been released on \url{https://github.com/Event-AHU/EFV_event_classification/tree/EFVpp}.

With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevailing methods only focus on learning a mapping from the compressed image to the original one but ignore the intrinsic attributes of the given compressed images, which greatly harms the performance of downstream parsing tasks. Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction,ie, the compression-insensitive features to regularize the high-level semantic representations during training and the compression-sensitive features to be aware of the compression degree. To achieve this, we first employ adversarial training to regularize the compressed and original encoded features for retaining high-level semantics, and we then develop the compression quality-aware feature encoder for compression-sensitive features. Based on these dual complementary features, we propose a Dual Awareness Guidance Network (DAGN) to utilize these awareness features as transformation guidance during the decoding phase. In our proposed DAGN, we develop a cross-feature fusion module to maintain the consistency of compression-insensitive features by fusing compression-insensitive features into the artifacts reduction baseline. Our method achieves an average 2.06 dB PSNR gains on BSD500, outperforming state-of-the-art methods, and only requires 29.7 ms to process one image on BSD500. Besides, the experimental results on LIVE1 and LIU4K also demonstrate the efficiency, effectiveness, and superiority of the proposed method in terms of quantitative metrics, visual quality, and downstream machine vision tasks.