检索结果-内蒙古大学图书馆

Fast Peer Adaptation with Context-aware Exploration 41

学校读者我要写书评

暂无评论

Fast Peer Adaptation with Context-aware Exploration

41st International Conference on Machine Learning, ICML 2024

作者： Ma, Long Wang, Yuanfei Zhong, Fangwei Zhu, Song-Chun Wang, Yizhou Academy for Advanced Interdisciplinary Studies Peking University China Nat'l Key Laboratory of General Artificial Intelligence BIGAI&PKU China Center on Frontiers of Computing Studies School of Computer Science Peking University China School of Intelligence Science and Technology Peking University China Inst. for Artificial Intelligence Peking University China Nat'l Eng. Research Center of Visual Technology Peking University China

Fast adapting to unknown peers (partners or opponents) with different strategies is a key challenge in multi-agent games. To do so, it is crucial for the agent to probe and identify the peer's strategy efficiently, as this is the prerequisite for carrying out the best response in adaptation. However, exploring the strategies of unknown peers is difficult, especially when the games are partially observable and have a long horizon. In this paper, we propose a peer identification reward, which rewards the learning agent based on how well it can identify the behavior pattern of the peer over the historical context, such as the observation over multiple episodes. This reward motivates the agent to learn a context-aware policy for effective exploration and fast adaptation, i.e., to actively seek and collect informative feedback from peers when uncertain about their policies and to exploit the context to perform the best response when confident. We evaluate our method on diverse testbeds that involve competitive (Kuhn Poker), cooperative (PO-Overcooked), or mixed (Predator-Prey-W) games with peer agents. We demonstrate that our method induces more active exploration behavior, achieving faster adaptation and better outcomes than existing methods1 Copyright 2024 by the author(s)

关键词： Adversarial machine learning

Language models represent beliefs of self and others 24

学校读者我要写书评

暂无评论

Language models represent beliefs of self and others

Proceedings of the 41st International Conference on Machine Learning

作者： Wentao Zhu Zhining Zhang Yizhou Wang Center on Frontiers of Computing Studies School of Compter Science Peking University Center on Frontiers of Computing Studies School of Compter Science and Inst. for Artificial Intelligence and Nat'l Eng. Research Center of Visual Technology and Nat'l Key Lab of General Artificial Intelligence Peking University

Understanding and attributing mental states, known as Theory of Mind (ToM), emerges as a fundamental capability for human social reasoning. While Large Language Models (LLMs) appear to possess certain ToM abilities, the mechanisms underlying these capabilities remain elusive. In this study, we discover that it is possible to linearly decode the belief status from the perspectives of various agents through neural activations of language models, indicating the existence of internal representations of self and others' beliefs. By manipulating these representations, we observe dramatic changes in the models' ToM performance, underscoring their pivotal role in the social reasoning process. Additionally, our findings extend to diverse social reasoning tasks that involve different causal inference patterns, suggesting the potential generalizability of these representations.

关键词：

3D Human Mesh Estimation from Virtual Markers

学校读者我要写书评

暂无评论

3D Human Mesh Estimation from Virtual Markers

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Xiaoxuan Ma Jiajun Su Chunyu Wang Wentao Zhu Yizhou Wang School of Computer Science Center on Frontiers of Computing Studies Peking University Microsoft Research Asia Inst. for Artificial Intelligence Peking University Nat'l Eng. Research Center of Visual Technology

Inspired by the success of volumetric 3D pose estimation, some recent human mesh estimators propose to estimate 3D skeletons as intermediate representations, from which, the dense 3D meshes are regressed by exploiting the mesh topology. However, body shape information is lost in extracting skeletons, leading to mediocre performance. The advanced motion capture systems solve the problem by placing dense physical markers on the body surface, which allows to extract realistic meshes from their non-rigid motions. However, they cannot be applied to wild images without markers. In this work, we present an intermediate representation, named virtual markers, which learns 64 landmark keypoints on the body surface based on the large-scale mocap data in a generative style, mimicking the effects of physical markers. The virtual markers can be accurately detected from wild images and can reconstruct the intact meshes with realistic shapes by simple interpolation. Our approach outperforms the state-of-the-art methods on three datasets. In particular, it surpasses the existing methods by a notable margin on the SURREAL dataset, which has diverse body shapes. Code is available at https://***/ShirleyMaxx/VirtualMarker

关键词：

Autoregressive Sequence Modeling for 3D Medical Image Representation 39

学校读者我要写书评

暂无评论

Autoregressive Sequence Modeling for 3D Medical Image Repres...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Siwen Wang, Churan Gao, Fei Su, Lixian Zhang, Fandong Wang, Yizhou Yu, Yizhou School of Computing and Data Science The University of Hong Kong Hong Kong Center on Frontiers of Computing Studies School of Computer Science Nat'l Eng. Research Center of Visual Technology Peking University China Deepwise AI Lab China State Key Lab of General Artificial Intelligence Inst. for Artificial Intelligence Peking University China

ISBN: (纸本)157735897X

Three-dimensional (3D) medical images, such as Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), are essential for clinical applications. However, the need for diverse and comprehensive representations is particularly pronounced when considering the variability across different organs, diagnostic tasks, and imaging modalities. How to effectively interpret the intricate contextual information and extract meaningful insights from these images remains an open challenge to the community. While current self-supervised learning methods have shown potential, they often consider an image as a whole thereby overlooking the extensive, complex relationships among local regions from one or multiple images. In this work, we introduce a pioneering method for learning 3D medical image representations through an autoregressive pre-training framework. Our approach sequences various 3D medical images based on spatial, contrast, and semantic correlations, treating them as interconnected visual tokens within a token sequence. By employing an autoregressive sequence modeling task, we predict the next visual token in the sequence, which allows our model to deeply understand and integrate the contextual information inherent in 3D medical images. Additionally, we implement a random startup strategy to avoid overestimating token relationships and to enhance the robustness of learning. The effectiveness of our approach is demonstrated by the superior performance over others on nine downstream tasks in public datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Supervised learning

FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ye, Hang Ma, Xiaoxuan Ci, Hai Zhu, Wentao Wang, Yizhou Center on Frontiers of Computing Studies School of Computer Science Peking University China Inst. for Artificial Intelligence Peking University China Nat’l Eng. Research Center of Visual Technology China State Key Laboratory of General Artificial Intelligence Peking University China

Achieving realistic animated human avatars requires accurate modeling of pose-dependent clothing deformations. Existing learning-based methods heavily rely on the Linear Blend Skinning (LBS) of minimally-clothed human models like SMPL to model deformation. However, they struggle to handle loose clothing, such as long dresses, where the canonicalization process becomes ill-defined when the clothing is far from the body, leading to disjointed and fragmented results. To overcome this limitation, we propose FreeCloth, a novel hybrid framework to model challenging clothed humans. Our core idea is to use dedicated strategies to model different regions, depending on whether they are close to or distant from the body. Specifically, we segment the human body into three categories: unclothed, deformed, and generated. We simply replicate unclothed regions that require no deformation. For deformed regions close to the body, we leverage LBS to handle the deformation. As for the generated regions, which correspond to loose clothing areas, we introduce a novel free-form, part-aware generator to model them, as they are less affected by movements. This free-form generation paradigm brings enhanced flexibility and expressiveness to our hybrid framework, enabling it to capture the intricate geometric details of challenging loose clothing, such as skirts and dresses. Experimental results on the benchmark dataset featuring loose clothing demonstrate that FreeCloth achieves state-of-the-art performance with superior visual fidelity and realism, particularly in the most challenging cases. Copyright © 2024, The Authors. All rights reserved.

关键词： Human form models

3D Human Mesh Estimation from Virtual Markers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Xiaoxuan Su, Jiajun Wang, Chunyu Zhu, Wentao Wang, Yizhou School of Computer Science Center on Frontiers of Computing Studies Peking University China Inst. for Artificial Intelligence Peking University China Microsoft Research Asia China Nat’l Eng. Research Center of Visual Technology China

关键词： Mesh generation

Language Models Represent Beliefs of Self and Others

学校读者我要写书评

暂无评论

arXiv 2024年

关键词： Computational linguistics

ADAMANIP: ADAPTIVE ARTICULATED OBJECT MANIPULATION ENVIRONMENTS AND POLICY LEARNING

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Yuanfei Zhang, Xiaojie Wu, Ruihai Li, Yu Shen, Yan Wu, Mingdong He, Zhaofeng Wang, Yizhou Dong, Hao Center on Frontiers of Computing Studies School of Computer Science Peking University China Beijing University of Posts and Telecommunications China Inst. for Artificial Intelligence Peking University China Nat’l Eng. Research Center of Visual Technology Peking University China State Key Laboratory of General Artificial Intelligence Peking University China

Articulated object manipulation is a critical capability for robots to perform various tasks in real-world scenarios. Composed of multiple parts connected by joints, articulated objects are endowed with diverse functional mechanisms through complex relative motions. For example, a safe consists of a door, a handle, and a lock, where the door can only be opened when the latch is unlocked. The internal structure, such as the state of a lock or joint angle constraints, cannot be directly observed from visual observation. Consequently, successful manipulation of these objects requires adaptive adjustment based on trial and error rather than a one-time visual inference. However, previous datasets and simulation environments for articulated objects have primarily focused on simple manipulation mechanisms where the complete manipulation process can be inferred from the object’s appearance. To enhance the diversity and complexity of adaptive manipulation mechanisms, we build a novel articulated object manipulation environment and equip it with 9 categories of objects. Based on the environment and objects, we further propose an adaptive demonstration collection and 3D visual diffusion-based imitation learning pipeline that learns the adaptive manipulation policy. The effectiveness of our designs and proposed method is validated through both simulation and real-world experiments. Our project page is available at: https://*** Copyright © 2025, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

Causal discovery via conditional independence testing with proxy variables 24

学校读者我要写书评

暂无评论

Causal discovery via conditional independence testing with p...

Proceedings of the 41st International Conference on Machine Learning

作者： Mingzhou Liu Xinwei Sun Yu Qiao Yizhou Wang School of Computer Science and Center on Frontiers of Computing Studies (CFCS) Peking University Sch. of Data Science Fudan University Dep. of Automation Shanghai Jiao Tong University Center on Frontiers of Computing Studies (CFCS) and School of Computer Science and Inst. for Artificial Intelligence and Nat'l Eng. Research Center of Visual Technology and Nat'l Key Lab of General Artificial Intelligence Peking University

Distinguishing causal connections from correlations is important in many scenarios. However, the presence of unobserved variables, such as the latent confounder, can introduce bias in conditional independence testing commonly employed in constraint-based causal discovery for identifying causal relations. To address this issue, existing methods introduced proxy variables to adjust for the bias caused by unobserveness. However, these methods were either limited to categorical variables or relied on strong parametric assumptions for identification. In this paper, we propose a novel hypothesis-testing procedure that can effectively examine the existence of the causal relationship over continuous variables, without any parametric constraint. Our procedure is based on discretization, which under completeness conditions, is able to asymptotically establish a linear equation whose coefficient vector is identifiable under the causal null hypothesis. Based on this, we introduce our test statistic and demonstrate its asymptotic level and power. We validate the effectiveness of our procedure using both synthetic and real-world data. Code is publicly available at https://***/lmz123321/proxy_causal_discovery.

关键词：