Wang, Zirui
YOU?
Author Swipe
View article: Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation Open
Humans and traditional computer vision methods rely on a diverse set of monocular cues to infer 3D structure from a single image, such as shading, texture, silhouette, etc. While recent deep generative models have dramatically advanced sin…
View article: Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation Open
Humans and traditional computer vision methods rely on a diverse set of monocular cues to infer 3D structure from a single image, such as shading, texture, silhouette, etc. While recent deep generative models have dramatically advanced sin…
View article: Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation
Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation Open
Humans and traditional computer vision methods rely on a diverse set of monocular cues to infer 3D structure from a single image, such as shading, texture, silhouette, etc. While recent deep generative models have dramatically advanced sin…
View article: Unveiling the Impact of Data and Model Scaling on High-Level Control for Humanoid Robots
Unveiling the Impact of Data and Model Scaling on High-Level Control for Humanoid Robots Open
Data scaling has long remained a critical bottleneck in robot learning. For humanoid robots, human videos and motion data are abundant and widely available, offering a free and large-scale data source. Besides, the semantics related to the…
View article: Unveiling the Impact of Data and Model Scaling on High-Level Control for Humanoid Robots
Unveiling the Impact of Data and Model Scaling on High-Level Control for Humanoid Robots Open
Data scaling has long remained a critical bottleneck in robot learning. For humanoid robots, human videos and motion data are abundant and widely available, offering a free and large-scale data source. Besides, the semantics related to the…
View article: Carbon Capture and Storage (CCS)
Carbon Capture and Storage (CCS) Open
View article: Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning
Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning Open
Large language models (LLMs) exhibit complementary strengths across domains and come with varying inference costs, motivating the design of multi-agent LLM systems where specialized models collaborate efficiently. Existing approaches predo…
View article: Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning
Controlling Performance and Budget of a Centralized Multi-agent LLM System with Reinforcement Learning Open
Large language models (LLMs) exhibit complementary strengths across domains and come with varying inference costs, motivating the design of multi-agent LLM systems where specialized models collaborate efficiently. Existing approaches predo…
View article: Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model
Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model Open
View article: Milliwatt-scale 3D thermoelectric generators via additive screen printing
Milliwatt-scale 3D thermoelectric generators via additive screen printing Open
Electronic components driving digitalization, such as wearables, Internet of Things (IoT), and Industry 4.0 systems, consume a growing portion of the global primary energy, largely relying on lithium-ion batteries. To enable a sustainable …