Humans constantly interact with their surrounding environments. Current human-centric generative models mainly focus on synthesizing humans plausibly interacting with static scenes and objects, while the dynamic human action-reaction synthesis for ubiquitous causal human-human interactions is less explored. Human-human interactions can be regarded as asymmetric with actors and reactors in atomic interaction periods. In this paper, we comprehensively analyze the asymmetric, dynamic, synchronous, and detailed nature of human-human interactions and propose the first multi-setting human action-reaction synthesis benchmark to generate human reactions conditioned on given human actions. To begin with, we propose to annotate the actor-reactor order of the interaction sequences for the NTU120, InterHuman, and Chi3D datasets. Based on them, a diffusion-based generative model with a Transformer decoder architecture called ReGenNet together with an explicit distance-based interaction loss is proposed to predict human reactions in an online manner, where the future states of actors are unavailable to reactors. Quantitative and qualitative results show that our method can generate instant and plausible human reactions compared to the baselines, and can generalize to unseen actor motions and viewpoint changes.
Deep neural networks (DNN) are increasingly being used to learn controllers due to their excellent approximation capabilities. However, their black-box nature poses significant challenges to closed-loop stability guarantees and performance analysis. In this paper, we introduce a structured DNN-based controller for the trajectory tracking control of Lagrangian systems using backing techniques. By properly designing neural network structures, the proposed controller can ensure closed-loop stability for any compatible neural network parameters. In addition, improved control performance can be achieved by further optimizing neural network parameters. Besides, we provide explicit upper bounds on tracking errors in terms of controller parameters, which allows us to achieve the desired tracking performance by properly selecting the controller parameters. Furthermore, when system models are unknown, we propose an improved Lagrangian neural network (LNN) structure to learn the system dynamics and design the controller. We show that in the presence of model approximation errors and external disturbances, the closed-loop stability and tracking control performance can still be guaranteed. The effectiveness of the proposed approach is demonstrated through simulations.
We introduce SuperCLUE-Math6(SC-Math6), a new benchmark dataset to evaluate the mathematical reasoning abilities of Chinese language models. SC-Math6 is designed as an upgraded Chinese version of the GSM8K dataset with enhanced difficulty, diversity, and application scope. It consists of over 2000 mathematical word problems requiring multi-step reasoning and providing natural language solutions. We propose an innovative scheme to quantify the reasoning capability of large models based on performance over problems with different reasoning steps. Experiments on 13 representative Chinese models demonstrate a clear stratification of reasoning levels, with top models like GPT-4 showing superior performance. SC-Math6 fills the gap in Chinese mathematical reasoning benchmarks and provides a comprehensive testbed to advance the intelligence of Chinese language models.
The analysis of the ubiquitous human-human interactions is pivotal for understanding humans as social beings. Existing human-human interaction datasets typically suffer from inaccurate body motions, lack of hand gestures and fine-grained textual descriptions. To better perceive and generate human-human interactions, we propose Inter-X, a currently largest human-human interaction dataset with accurate body movements and diverse interaction patterns, together with detailed hand gestures. The dataset includes ~11K interaction sequences and more than 8.1M frames. We also equip Inter-X with versatile annotations of more than 34K fine-grained human part-level textual descriptions, semantic interaction categories, interaction order, and the relationship and personality of the subjects. Based on the elaborate annotations, we propose a unified benchmark composed of 4 categories of downstream tasks from both the perceptual and generative directions. Extensive experiments and comprehensive analysis show that Inter-X serves as a testbed for promoting the development of versatile human-human interaction analysis. Our dataset and benchmark will be publicly available for research purposes.
Large language models (LLMs), like ChatGPT and GPT-4, have demonstrated remarkable abilities in natural language understanding and generation. However, alongside their positive impact on our daily tasks, they can also produce harmful content that negatively affects societal perceptions. To systematically assess the safety of Chinese LLMs, we introduce SuperCLUE-Safety (SC-Safety) - a multi-round adversarial benchmark with 4912 open-ended questions covering more than 20 safety sub-dimensions. Adversarial human-model interactions and conversations significantly increase the challenges compared to existing methods. Experiments on 13 major LLMs supporting Chinese yield the following insights: 1) Closed-source models outperform open-sourced ones in terms of safety; 2) Models released from China demonstrate comparable safety levels to LLMs like GPT-3.5-turbo; 3) Some smaller models with 6B-13B parameters can compete effectively in terms of safety. By introducing SC-Safety, we aim to promote collaborative efforts to create safer and more trustworthy LLMs. The benchmark and findings provide guidance on model selection. Our benchmark can be found at https://www.CLUEbenchmarks.com
Video traffic in vehicular communication networks (VCNs) faces exponential growth. However, different segments of most videos reveal various attractiveness for viewers, and the pre-caching decision is greatly affected by the dynamic service duration that edge nodes can provide services for mobile vehicles driving along a road. In this paper, we propose an efficient video highlight pre-caching scheme in the vehicular communication network, adapting to the service duration. Specifically, a highlight entropy model is devised with the consideration of the segments' popularity and continuity between segments within a period of time, based on which, an optimization problem of video highlight pre-caching is formulated. As this problem is non-convex and lacks a closed-form expression of the objective function, we decouple multiple variables by deriving candidate highlight segmentations of videos through wavelet transform, which can significantly reduce the complexity of highlight pre-caching. Then the problem is solved iteratively by a highlight-direction trimming algorithm, which is proven to be locally optimal. Simulation results based on real-world video datasets demonstrate significant improvement in highlight entropy and jitter compared to benchmark schemes.
Multimodal data, which can comprehensively perceive and recognize the physical world, has become an essential path towards general artificial intelligence. However, multimodal large models trained on public datasets often underperform in specific industrial domains. This paper proposes a multimodal federated learning framework that enables multiple enterprises to utilize private domain data to collaboratively train large models for vertical domains, achieving intelligent services across scenarios. The authors discuss in-depth the strategic transformation of federated learning in terms of intelligence foundation and objectives in the era of big model, as well as the new challenges faced in heterogeneous data, model aggregation, performance and cost trade-off, data privacy, and incentive mechanism. The paper elaborates a case study of leading enterprises contributing multimodal data and expert knowledge to city safety operation management , including distributed deployment and efficient coordination of the federated learning platform, technical innovations on data quality improvement based on large model capabilities and efficient joint fine-tuning approaches. Preliminary experiments show that enterprises can enhance and accumulate intelligent capabilities through multimodal model federated learning, thereby jointly creating an smart city model that provides high-quality intelligent services covering energy infrastructure safety, residential community security, and urban operation management. The established federated learning cooperation ecosystem is expected to further aggregate industry, academia, and research resources, realize large models in multiple vertical domains, and promote the large-scale industrial application of artificial intelligence and cutting-edge research on multimodal federated learning.
Large language models (LLMs) have shown the potential to be integrated into human daily lives. Therefore, user preference is the most critical criterion for assessing LLMs' performance in real-world scenarios. However, existing benchmarks mainly focus on measuring models' accuracy using multi-choice questions, which limits the understanding of their capabilities in real applications. We fill this gap by proposing a comprehensive Chinese benchmark SuperCLUE, named after another popular Chinese LLM benchmark CLUE. SuperCLUE encompasses three sub-tasks: actual users' queries and ratings derived from an LLM battle platform (CArena), open-ended questions with single and multiple-turn dialogues (OPEN), and closed-ended questions with the same stems as open-ended single-turn ones (CLOSE). Our study shows that accuracy on closed-ended questions is insufficient to reflect human preferences achieved on open-ended ones. At the same time, they can complement each other to predict actual user preferences. We also demonstrate that GPT-4 is a reliable judge to automatically evaluate human preferences on open-ended questions in a Chinese context. Our benchmark will be released at https://www.CLUEbenchmarks.com
The UNet architecture, based on Convolutional Neural Networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive fields and inherent bias of convolutional operations. Recently, numerous transformer-based techniques have been incorporated into the UNet architecture to overcome this limitation by effectively capturing global feature correlations. However, the integration of the Transformer modules may result in the loss of local contextual information during the global feature fusion process. To overcome these challenges, we propose a 2D medical image segmentation model called Multi-scale Cross Perceptron Attention Network (MCPA). The MCPA consists of three main components: an encoder, a decoder, and a Cross Perceptron. The Cross Perceptron first captures the local correlations using multiple Multi-scale Cross Perceptron modules, facilitating the fusion of features across scales. The resulting multi-scale feature vectors are then spatially unfolded, concatenated, and fed through a Global Perceptron module to model global dependencies. Furthermore, we introduce a Progressive Dual-branch Structure to address the semantic segmentation of the image involving finer tissue structures. This structure gradually shifts the segmentation focus of MCPA network training from large-scale structural features to more sophisticated pixel-level features. We evaluate our proposed MCPA model on several publicly available medical image datasets from different tasks and devices, including the open large-scale dataset of CT (Synapse), MRI (ACDC), fundus camera (DRIVE, CHASE_DB1, HRF), and OCTA (ROSE). The experimental results show that our MCPA model achieves state-of-the-art performance. The code is available at https://github.com/simonustc/MCPA-for-2D-Medical-Image-Segmentation.