10 papers
Has GPT-6-Astra Achieved Embodied Intelligence?
SenseNova, Joint Research Team, : +60
GPT-6-Astra demonstrates a level of competence in robotic manipulation and navigation that challenges the conventional paradigm of building specialized models for individual tasks…
SenseNova-U1.5: Towards Native Unified Visual Intelligence
Haiwen Diao, Jiahao Wang, Chenjing Ding +62
We launch SenseNova-U1.5, an 8B-MoT native unified multimodal model that understands, reasons about, and generates visual content within an encoder-free and VAE-free architecture.…
InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation
Zhuoran Yang, Xi Guo, Chenjing Ding +3
Autonomous driving relies on robust models trained on high-quality, large-scale multi-view driving videos. While world models offer a cost-effective solution for generating realist…
CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving
Tianrui Zhang, Yichen Liu, Zilin Guo +6
Generative models have been widely applied to world modeling for environment simulation and future state prediction. With advancements in autonomous driving, there is a growing dem…
Physical Informed Driving World Model
Zhuoran Yang, Xi Guo, Chenjing Ding +2
Autonomous driving requires robust perception models trained on high-quality, large-scale multi-view driving videos for tasks like 3D object detection, segmentation and trajectory…
InfinityDrive: Breaking Time Limits in Driving World Models
Xi Guo, Chenjing Ding, Haoxuan Dou +3
Autonomous driving systems struggle with complex scenarios due to limited access to diverse, extensive, and out-of-distribution driving data which are critical for safe navigation.…
DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation
Wei Wu, Xi Guo, Weixuan Tang +4
Recent advancements in generative models have provided promising solutions for synthesizing realistic driving videos, which are crucial for training autonomous driving perception m…
MyGo: Consistent and Controllable Multi-View Driving Video Generation with Camera Control
Yining Yao, Xi Guo, Chenjing Ding +1
High-quality driving video generation is crucial for providing training data for autonomous driving models. However, current generative models rarely focus on enhancing camera moti…
SGC-VQGAN: Towards Complex Scene Representation via Semantic Guided Clustering Codebook
Chenjing Ding, Chiyu Wang, Boshi Liu +3
Vector quantization (VQ) is a method for deterministically learning features through discrete codebook representations. Recent works have utilized visual tokenizers to discretize v…
PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitation
Yunze Liu, Changxi Chen, Chenjing Ding +1
Humanoid Reaction Synthesis is pivotal for creating highly interactive and empathetic robots that can seamlessly integrate into human environments, enhancing the way we live, work,…