检索结果-内蒙古大学图书馆

HUMAN SIMULACRA: BENCHMARKING THE PERSONIFICATION OF LARGE LANGUAGE MODELS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Qiujie Feng, Qiming Zhang, Tianqi Li, Qingqiu Yang, Linyi Zhang, Yuejie Feng, Rui He, Liang Gao, Shang Zhang, Yue School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Tongji University China University College London United Kingdom Huawei Noah’s Ark Lab Canada Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention China Deakin University Australia Westlake University China Westlake Institute for Advanced Study China

Large Language Models (LLMs) are recognized as systems that closely mimic aspects of human intelligence. This capability has attracted the attention of the social science community, who see the potential in leveraging LLMs to replace human participants in experiments, thereby reducing research costs and complexity. In this paper, we introduce a benchmark for LLMs personification, including a strategy for constructing virtual characters’ life stories from the ground up, a Multi-Agent Cognitive Mechanism capable of simulating human cognitive processes, and a psychology-guided evaluation method to assess human simulations from both self and observational perspectives. Experimental results demonstrate that our constructed simulacra can produce personified responses that align with their target characters. We hope this work will serve as a benchmark in the field of human simulation, paving the way for future research. © 2024, CC BY-NC-SA.

关键词： Digital elevation model

Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Tianying Zhang, Lu Wang, Yang Guan, Jihong Fu, Yanwei Zhao, Jiajia Zhou, Shuigeng Department of Computer Science and Technology Tongji University Shanghai201804 China The Project Management Office of China National Scientific Seafloor Observatory Tongji University Shanghai200092 China Shanghai Key Lab of Intelligent Information Processing The School of Computer Science Fudan University Shanghai200438 China Shanghai Key Lab of Intelligent Information Processing The School of Data Science Fudan University Shanghai200433 China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to generalize these object detectors to the novel long-tailed object classes, which have only few labeled training samples. To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes. Especially, the research in this emerging field has been flourishing in recent years with various benchmarks, backbones, and methodologies proposed. To review these FSOD works, there are several insightful FSOD survey articles [58, 59, 74, 78] that systematically study and compare them as the groups of fine-tuning/transfer learning, and meta-learning methods. In contrast, we review the existing FSOD algorithms from a new perspective under a new taxonomy based on their contributions, i.e., data-oriented, model-oriented, and algorithm-oriented. Thus, a comprehensive survey with performance comparison is conducted on recent achievements of FSOD. Furthermore, we also analyze the technical challenges, the merits and demerits of these methods, and envision the future directions of FSOD. Specifically, we give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols. The taxonomy is then proposed that groups FSOD methods into three types. Following this taxonomy, we provide a systematic review of the advances in FSOD. Finally, further discussions on performance, challenges, and future directions are presented. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Yangji Liang, Weihan Zhao, Dongyang Zhou, Hong-Yu Ge, Weifeng Yu, Yizhou Zhang, Wenqiang Nebula AI Group School of Computer Science Fudan University China Shanghai Key Lab of Intelligent Information Processing China Department of Computer Science The University of Hong Kong Hong Kong

This paper presents new hierarchically cascaded transformers that can improve data efficiency through attribute surrogates learning and spectral tokens pooling. Vision transformers have recently been thought of as a promising alternative to convolutional neural networks for visual recognition. But when there is no sufficient data, it gets stuck in overfitting and shows inferior performance. To improve data efficiency, we propose hierarchically cascaded transformers that exploit intrinsic image structures through spectral tokens pooling and optimize the learnable parameters through latent attribute surrogates. The intrinsic image structure is utilized to reduce the ambiguity between foreground content and background noise by spectral tokens pooling. And the attribute surrogate learning scheme is designed to benefit from the rich visual information in image-label pairs instead of simple visual concepts assigned by their labels. Our Hierarchically Cascaded Transformers, called HCTransformers, is built upon a self-supervised learning framework DINO and is tested on several popular few-shot learning benchmarks. In the inductive setting, HCTransformers surpass the DINO baseline by a large margin of 9.7% 5-way 1-shot accuracy and 9.17% 5-way 5-shot accuracy on miniImageNet, which demonstrates HCTransformers are efficient to extract discriminative features. Also, HCTransformers show clear advantages over SOTA few-shot classification methods in both 5-way 1-shot and 5-way 5-shot settings on four popular benchmark datasets, including miniImageNet, tieredImageNet, FC100, and CIFAR-FS. The trained weights and codes are available at https://***/StomachCold/HCTransformers. Copyright © 2022, The Authors. All rights reserved.

关键词： Efficiency

FLAT: Chinese NER using flat-lattice transformer 58

学校读者我要写书评

暂无评论

FLAT: Chinese NER using flat-lattice transformer

58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

作者： Li, Xiaonan Yan, Hang Qiu, Xipeng Huang, Xuanjing Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University

ISBN: (纸本)9781952148255

Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information. However, since the lattice structure is complex and dynamic, most existing lattice-based models are hard to fully utilize the parallel computation of GPUs and usually have a low inference-speed. In this paper, we propose FLAT: Flat-LAttice Transformer for Chinese NER, which converts the lattice structure into a flat structure consisting of spans. Each span corresponds to a character or latent word and its position in the original lattice. With the power of Transformer and well-designed position encoding, FLAT can fully leverage the lattice information and has an excellent parallelization ability. Experiments on four datasets show FLAT outperforms other lexicon-based models in performance and efficiency. © 2020 Association for Computational Linguistics

关键词： Program processors

S2KAN-SLAM: Elastic Neural LiDAR SLAM with SDF Submaps and Kolmogorov-Arnold Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wang, Zhong Zhang, Lin Wang, Hesheng Shanghai Jiao Tong University State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China Tongji University School of Computer Science and Technology National Pilot Software Engineering School with Chinese Characteristics Shanghai201804 China

Traditional LiDAR SLAM approaches prioritize localization over mapping, yet high-precision dense maps are essential for numerous applications involving intelligent agents. Recent advancements have introduced methods leveraging neural fields to enhance mapping capabilities;however, these approaches still face several limitations. Firstly, concerning scene representation, they typically employ neural fields with high-dimensional features and multi-layer perceptron decoders utilizing non-continuous activation functions. This results in low learning efficiency and challenges in capturing high-frequency signals. Secondly, in terms of scene organization, these methods often treat the entire scene as a singular neural field, leading to inefficiencies, inflexibility, and difficulties in rectifying accumulated errors when mapping large-scale environments over extended periods. To tackle the first issue, we propose a lightweight continuous SDF regression approach by encoding the scene in single-valued embeddings and decoding SDF values from a Kolmogorov-Arnold Network. By minimizing discrepancies in measuring range, sampling distance, and decoded SDF values, we facilitate iterative frame-to-model tracking and bundle adjustment neural mapping. To mitigate the second challenge, we propose structuring the whole scene into multiple neural SDF submaps. By establishing node-node, node-submap, and loop closure constraints into a global pose graph, the system can create dense neural maps with global consistency across large-scale scenes. Experimental evaluations in both real-world and simulated settings indicate that our system achieves superior mapping completeness and accuracy, enhanced learning efficiency, reduced memory consumption, and greater flexibility compared to its counterparts. © 2025 IEEE.

关键词： Mapping

SLC2-SLAM: Semantic-guided Loop Closure using Shared Latent Code for NeRF SLAM

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ming, Yuhang Ma, Di Dai, Weichen Yang, Han Fan, Rui Zhang, Guofeng Kong, Wanzeng School of Computer Science Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province Hangzhou Dianzi University Hangzhou310018 China College of Electronics & Information Engineering Shanghai Institute of Intelligent Science and Technology Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China State Key Lab of CAD&CG Zhejiang University Hangzhou310058 China

Targeting the notorious cumulative drift errors in NeRF SLAM, we propose a Semantic-guided Loop Closure using Shared Latent Code, dubbed SLC2-SLAM. We argue that latent codes stored in many NeRF SLAM systems are not fully exploited, as they are only used for better reconstruction. In this paper, we propose a simple yet effective way to detect potential loops using the same latent codes as local features. To further improve the loop detection performance, we use the semantic information, which are also decoded from the same latent codes to guide the aggregation of local features. Finally, with the potential loops detected, we close them with a graph optimization followed by bundle adjustment to refine both the estimated poses and the reconstructed scene. To evaluate the performance of our SLC2-SLAM, we conduct extensive experiments on Replica and ScanNet datasets. Our proposed semantic-guided loop closure significantly outperforms the pre-trained NetVLAD and ORB combined with Bag-of-Words, which are used in all the other NeRF SLAM with loop closure. As a result, our SLC2-SLAM also demonstrated better tracking and reconstruction performance, especially in larger scenes with more loops, like ScanNet. Copyright © 2025, The Authors. All rights reserved.

关键词： SLAM robotics

EEG-based Emotion Recognition in Immersive Virtual Reality: Meeting the Requirement of Accuracy and Computational Efficiency 23

学校读者我要写书评

暂无评论

EEG-based Emotion Recognition in Immersive Virtual Reality: ...

7th International Conference on Digital Signal processing, ICDSP 2023

作者： Pei, Guanxiong Fan, Cunhang Li, Taihao Jin, Jia Wang, Rui Research Institute of Artificial Intelligence Zhejiang Lab China School of Computer Science and Technology Anhui University China Laboratory of Applied Brain and Cognitive Sciences Shanghai International Studies University China School of Business and Management Shanghai International Studies University China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences China

ISBN: (纸本)9781450398626

Virtual reality technology provides a strong sense of immersion and interactivity. It is widely used in the fields of anxiety relief, fear therapy, and depression regulation. However, objectively evaluating the emotional intervention effect of virtual reality technology is a difficult problem. The main purpose of this paper is to explore the use of EEG signals to identify individual emotional states in virtual reality scenarios and to improve the computational efficiency and recognition accuracy of emotional valence. To induce the target emotional state of the participants, we established a relatively standard emotion-induced virtual reality video library. The EEG data of the participants were collected synchronously as they watched the virtual reality video. The results show that the emotion recognition performance of multiple features (energy spectrum, differential entropy, differential asymmetry, and rational asymmetry) is better than that of a single feature. The radial basis function neural network (RBFNN) performed better than the deep belief network (DBN). RBFNN achieves the highest average classification accuracy of 91.1%. By combining the feature selection (F-test) method with the RBFNN, an ideal classification performance can be maintained with computational efficiency improvements. Furthermore, it is demonstrated that the features extracted from the theta band outperform features extracted from other bands in emotional valence decoding. These results may contribute to the application of EEG-based affective computing technology in the field of psychological rehabilitation and assessment. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Virtual reality

Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration 3

学校读者我要写书评

暂无评论

Efficiently Training On-Policy Actor-Critic Networks in Robo...

3rd International Symposium on Robotics and intelligent Manufacturing Technology, ISRIMT 2021

作者： Chen, Zhaorun Chen, Binhao Xie, Shenghan Gong, Liang Liu, Chengliang Zhang, Zhengfeng Zhang, Junping Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering China Shanghai Jiao Tong University School of Mechanical Engineering China Fudan University Shanghai Key Lab of Intelligent Information Processing China

ISBN: (纸本)9781665437189

In complex environments with high dimension, training a reinforcement learning (RL) model from scratch often suffers from lengthy and tedious collection of agent-environment interactions. Instead, leveraging expert demonstration to guide RL agent can boost sample efficiency and improve final convergence. In order to better integrate expert prior with on-policy RL models, we propose a generic framework for Learning from Demonstration (LfD) based on actor-critic algorithms. Technically, we first employ K-Means clustering to evaluate the similarity of sampled exploration with demonstration data. Then we increase the likelihood of actions in similar frames by modifying the gradient update strategy to leverage demonstration. We conduct experiments on 4 standard benchmark environments in Mujoco and 2 self-designed robotic environments. Results show that, under certain condition, our algorithm can improve sample efficiency by 20% 40%. By combining our framework with on-policy algorithms, RL models can accelerate convergence and obtain better final mean episode rewards especially in complex robotic context where interactions are expensive. © 2021 IEEE.

关键词： Reinforcement learning

DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Hui Wang, Zheng Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China School of Computer Science Zhejiang University of Technology China

Anomaly detection has garnered extensive applications in real industrial manufacturing due to its remarkable effectiveness and efficiency. However, previous generative-based models have been limited by suboptimal reconstruction quality, hampering their overall performance. We introduce DiffusionAD, a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network. A fundamental enhancement lies in our reformulation of the reconstruction process using a diffusion model into a noise-to-norm paradigm. Here, anomalous regions are perturbed with Gaussian noise and reconstructed as normal, overcoming the limitations of previous models by facilitating anomaly-free restoration. Additionally, we propose a rapid one-step denoising paradigm, significantly faster than the traditional iterative denoising in diffusion models. Furthermore, the introduction of the norm-guided paradigm elevates the accuracy and fidelity of reconstructions. The segmentation sub-network predicts pixel-level anomaly scores using the input image and its anomaly-free restoration. Comprehensive evaluations on four standard and challenging benchmarks reveal that DiffusionAD outperforms current state-of-the-art approaches, demonstrating the effectiveness and broad applicability of the proposed pipeline. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection