Picture for Hongyang Li

Hongyang Li

Learning Manipulation by Predicting Interaction

Add code
Jun 01, 2024
Viaarxiv icon

Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability

Add code
May 27, 2024
Viaarxiv icon

TAPTR: Tracking Any Point with Transformers as Detection

Add code
Mar 19, 2024
Figure 1 for TAPTR: Tracking Any Point with Transformers as Detection
Figure 2 for TAPTR: Tracking Any Point with Transformers as Detection
Figure 3 for TAPTR: Tracking Any Point with Transformers as Detection
Figure 4 for TAPTR: Tracking Any Point with Transformers as Detection
Viaarxiv icon

SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception

Mar 15, 2024
Figure 1 for SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception
Figure 2 for SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception
Figure 3 for SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception
Figure 4 for SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception
Viaarxiv icon

Generalized Predictive Model for Autonomous Driving

Add code
Mar 14, 2024
Figure 1 for Generalized Predictive Model for Autonomous Driving
Figure 2 for Generalized Predictive Model for Autonomous Driving
Figure 3 for Generalized Predictive Model for Autonomous Driving
Figure 4 for Generalized Predictive Model for Autonomous Driving
Viaarxiv icon

FastMAC: Stochastic Spectral Sampling of Correspondence Graph

Add code
Mar 13, 2024
Figure 1 for FastMAC: Stochastic Spectral Sampling of Correspondence Graph
Figure 2 for FastMAC: Stochastic Spectral Sampling of Correspondence Graph
Figure 3 for FastMAC: Stochastic Spectral Sampling of Correspondence Graph
Figure 4 for FastMAC: Stochastic Spectral Sampling of Correspondence Graph
Viaarxiv icon

Embodied Understanding of Driving Scenarios

Add code
Mar 07, 2024
Figure 1 for Embodied Understanding of Driving Scenarios
Figure 2 for Embodied Understanding of Driving Scenarios
Figure 3 for Embodied Understanding of Driving Scenarios
Figure 4 for Embodied Understanding of Driving Scenarios
Viaarxiv icon

Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation

Mar 05, 2024
Figure 1 for Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation
Figure 2 for Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation
Figure 3 for Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation
Figure 4 for Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation
Viaarxiv icon

Translating Images to Road Network:A Non-Autoregressive Sequence-to-Sequence Approach

Add code
Feb 13, 2024
Viaarxiv icon

Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks

Add code
Jan 25, 2024
Viaarxiv icon