THE well-known ancient Chinese philosopher Lao Tzu(老子)or Laozi(6th~4th century BC during the Spring and Autumn period)started his classic Tao Teh Ching《道德经》or Dao De Jing(see Fig.1)with six Chinese characters:&...THE well-known ancient Chinese philosopher Lao Tzu(老子)or Laozi(6th~4th century BC during the Spring and Autumn period)started his classic Tao Teh Ching《道德经》or Dao De Jing(see Fig.1)with six Chinese characters:"道(Dao)可(Ke)道(Dao)非(Fei)常(Chang)道(Dao)",which has been traditionally interpreted as“道可道,非常道”or"The Dao that can be spoken is not the eternal Dao".展开更多
Robustness and generalization are two challenging problems for learning point cloud representation.To tackle these problems,we first design a novel geometry coding model,which can effectively use an invariant eigengra...Robustness and generalization are two challenging problems for learning point cloud representation.To tackle these problems,we first design a novel geometry coding model,which can effectively use an invariant eigengraph to group points with similar geometric information,even when such points are far from each other.We also introduce a large-scale point cloud dataset,PCNet184.It consists of 184 categories and 51,915 synthetic objects,which brings new challenges for point cloud classification,and provides a new benchmark to assess point cloud cross-domain generalization.Finally,we perform extensive experiments on point cloud classification,using ModelNet40,ScanObjectNN,and our PCNet184,and segmentation,using ShapeNetPart and S3DIS.Our method achieves comparable performance to state-of-the-art methods on these datasets,for both supervised and unsupervised learning.Code and our dataset are available at https://github.com/MingyeXu/PCNet184.展开更多
Large language models(LLMs)have made unprecedented progress,demonstrating human-like language proficiency and an extraordinary ability to encode complex knowledge.The emergence of high-level cognitive capabilities in ...Large language models(LLMs)have made unprecedented progress,demonstrating human-like language proficiency and an extraordinary ability to encode complex knowledge.The emergence of high-level cognitive capabilities in LLMs,such as in-context learning and complex reasoning,suggests a path toward the realization of artificial general intelligence(AGI).However,we lack scientific theories and tools to assess and interpret such an emergence of the advanced intelligence of LLMs.Artificial intelligence(AI)has been extensively applied in various areas of fundamental science to accelerate scientific research.展开更多
Transformers have recently lead to encouraging progress in computer vision.In this work,we present new baselines by improving the original Pyramid Vision Transformer(PVT v1)by adding three designs:(i)a linear complexi...Transformers have recently lead to encouraging progress in computer vision.In this work,we present new baselines by improving the original Pyramid Vision Transformer(PVT v1)by adding three designs:(i)a linear complexity attention layer,(ii)an overlapping patch embedding,and(iii)a convolutional feed-forward network.With these modifications,PVT v2 reduces the computational complexity of PVT v1 to linearity and provides significant improvements on fundamental vision tasks such as classification,detection,and segmentation.In particular,PVT v2 achieves comparable or better performance than recent work such as the Swin transformer.We hope this work will facilitate state-ofthe-art transformer research in computer vision.Code is available at https://github.com/whai362/PVT.展开更多
Traffic signal control is shifting from passive control to proactive control, which enables the controller to direct current traffic flow to reach its expected destinations. To this end, an effective prediction model ...Traffic signal control is shifting from passive control to proactive control, which enables the controller to direct current traffic flow to reach its expected destinations. To this end, an effective prediction model is needed for signal controllers. What to predict, how to predict, and how to leverage the prediction for control policy optimization are critical problems for proactive traffic signal control. In this paper, we use an image that contains vehicle positions to describe intersection traffic states. Then, inspired by a model-based reinforcement learning method, DreamerV2,we introduce a novel learning-based traffic world model. The traffic world model that describes traffic dynamics in image form is used as an abstract alternative to the traffic environment to generate multi-step planning data for control policy optimization. In the execution phase, the optimized traffic controller directly outputs actions in real time based on abstract representations of traffic states, and the world model can also predict the impact of different control behaviors on future traffic conditions. Experimental results indicate that the traffic world model enables the optimized real-time control policy to outperform common baselines, and the model achieves accurate image-based prediction, showing promising applications in futuristic traffic signal control.展开更多
In this paper,we investigate a class of nonlinear backward stochastic differential equations(BSDEs)arising from financial economics,and give the sign of corresponding solution.Furthermore,we are able to obtain explici...In this paper,we investigate a class of nonlinear backward stochastic differential equations(BSDEs)arising from financial economics,and give the sign of corresponding solution.Furthermore,we are able to obtain explicit solutions to an interesting class of nonlinear BSDEs,including the k-ignorance BSDE arising from the modeling of ambiguity of asset pricing.Moreover,we show its applications in PDEs and contingent pricing in an incomplete market.展开更多
基金partially supported by the National Key R&D Program of China(2020YFB2104001)the National Natural Science Foundation of China(62271485,61903363,62203250,U1811463)。
文摘THE well-known ancient Chinese philosopher Lao Tzu(老子)or Laozi(6th~4th century BC during the Spring and Autumn period)started his classic Tao Teh Ching《道德经》or Dao De Jing(see Fig.1)with six Chinese characters:"道(Dao)可(Ke)道(Dao)非(Fei)常(Chang)道(Dao)",which has been traditionally interpreted as“道可道,非常道”or"The Dao that can be spoken is not the eternal Dao".
基金supported by the National Key Research and Development Program of China[grant number 2020YFA0608000]the National Natural Science Foundation of China[grant number 42030605].
基金This work was partially supported by the National Natural Science Foundation of China(Grant Nos.61876176 and U1813218)the Joint Lab of CAS–HK,the Shenzhen Research Program(Grant No.RCJC20200714114557087)+1 种基金the Shanghai Committee of Science and Technology(Grant No.21DZ1100100)Shenzhen Institute of Artificial Intelligence and Robotics for Society.
文摘Robustness and generalization are two challenging problems for learning point cloud representation.To tackle these problems,we first design a novel geometry coding model,which can effectively use an invariant eigengraph to group points with similar geometric information,even when such points are far from each other.We also introduce a large-scale point cloud dataset,PCNet184.It consists of 184 categories and 51,915 synthetic objects,which brings new challenges for point cloud classification,and provides a new benchmark to assess point cloud cross-domain generalization.Finally,we perform extensive experiments on point cloud classification,using ModelNet40,ScanObjectNN,and our PCNet184,and segmentation,using ShapeNetPart and S3DIS.Our method achieves comparable performance to state-of-the-art methods on these datasets,for both supervised and unsupervised learning.Code and our dataset are available at https://github.com/MingyeXu/PCNet184.
基金This work was funded by National Natural Science Foundation of China(62001205)National Key R&D Program of China(2021YFF1200804)Shenzhen Science and Technology Innovation Committee(2022410129,KCXFZ20201221173400001,and SGDX2020110309280100).
文摘Large language models(LLMs)have made unprecedented progress,demonstrating human-like language proficiency and an extraordinary ability to encode complex knowledge.The emergence of high-level cognitive capabilities in LLMs,such as in-context learning and complex reasoning,suggests a path toward the realization of artificial general intelligence(AGI).However,we lack scientific theories and tools to assess and interpret such an emergence of the advanced intelligence of LLMs.Artificial intelligence(AI)has been extensively applied in various areas of fundamental science to accelerate scientific research.
基金National Natural Science Foundation of China under Grant Nos.61672273 and 61832008Science Foundation for Distinguished Young Scholars of Jiangsu under Grant No.BK20160021+1 种基金Postdoctoral Innovative Talent Support Program of China under Grant Nos.BX20200168,2020M681608General Research Fund of Hong Kong under Grant No.27208720。
文摘Transformers have recently lead to encouraging progress in computer vision.In this work,we present new baselines by improving the original Pyramid Vision Transformer(PVT v1)by adding three designs:(i)a linear complexity attention layer,(ii)an overlapping patch embedding,and(iii)a convolutional feed-forward network.With these modifications,PVT v2 reduces the computational complexity of PVT v1 to linearity and provides significant improvements on fundamental vision tasks such as classification,detection,and segmentation.In particular,PVT v2 achieves comparable or better performance than recent work such as the Swin transformer.We hope this work will facilitate state-ofthe-art transformer research in computer vision.Code is available at https://github.com/whai362/PVT.
基金supported by the National Natural Science Foundation of China (Nos. 62173329 and U1811463)。
文摘Traffic signal control is shifting from passive control to proactive control, which enables the controller to direct current traffic flow to reach its expected destinations. To this end, an effective prediction model is needed for signal controllers. What to predict, how to predict, and how to leverage the prediction for control policy optimization are critical problems for proactive traffic signal control. In this paper, we use an image that contains vehicle positions to describe intersection traffic states. Then, inspired by a model-based reinforcement learning method, DreamerV2,we introduce a novel learning-based traffic world model. The traffic world model that describes traffic dynamics in image form is used as an abstract alternative to the traffic environment to generate multi-step planning data for control policy optimization. In the execution phase, the optimized traffic controller directly outputs actions in real time based on abstract representations of traffic states, and the world model can also predict the impact of different control behaviors on future traffic conditions. Experimental results indicate that the traffic world model enables the optimized real-time control policy to outperform common baselines, and the model achieves accurate image-based prediction, showing promising applications in futuristic traffic signal control.
基金This paper was originally exhibited in 2020(arXiv:2006.00222)。
文摘In this paper,we investigate a class of nonlinear backward stochastic differential equations(BSDEs)arising from financial economics,and give the sign of corresponding solution.Furthermore,we are able to obtain explicit solutions to an interesting class of nonlinear BSDEs,including the k-ignorance BSDE arising from the modeling of ambiguity of asset pricing.Moreover,we show its applications in PDEs and contingent pricing in an incomplete market.
