53 citations · 98 across the 7 of their papers we have counts for
8 papers
PhysWAM: Physically Consistent World Action Model for Autonomous Driving
Dhruv Parikh, Fengcheng Yu, Quankai Gao +11
World-action models (WAMs) jointly predict how a scene will evolve and how an agent should act, however joint generation alone does not necessarily impose a shared geometric constr…
DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models
Fengcheng Yu, Dhruv Parikh, Junjie Ye +5
Generative world-action models (WAMs) jointly generate future video and vehicle actions, while their action branches remain primarily optimized by expert imitation. Yet imitation p…
DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning
Thanh Nguyen, Trung Pham, Chaoning Zhang +3
Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role. However, the recent development of new non-CL frameworks has ach…
Scalable SoftGroup for 3D Instance Segmentation on Point Clouds
Thang Vu, Kookhoi Kim, Tung M. Luu +3
This paper considers a network referred to as SoftGroup for accurate and scalable 3D instance segmentation. Existing state-of-the-art methods produce hard semantic predictions foll…
SoftGroup for 3D Instance Segmentation on Point Clouds
Thang Vu, Kookhoi Kim, Tung M. Luu +2
Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation followed by grouping. The hard predictions are made when performing semantic segmentation s…
Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model
Thanh Nguyen, Tung M. Luu, Thang Vu +1
Developing an agent in reinforcement learning (RL) that is capable of performing complex control tasks directly from high-dimensional observation such as raw pixels is yet a challe…
SCNet: Training Inference Sample Consistency for Instance Segmentation
Thang Vu, Haeyong Kang, Chang D. Yoo
Cascaded architectures have brought significant performance improvement in object detection and instance segmentation. However, there are lingering issues regarding the disparity i…
Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution
Thang Vu, Hyunjun Jang, Trung X. Pham +1
This paper considers an architecture referred to as Cascade Region Proposal Network (Cascade RPN) for improving the region-proposal quality and detection performance by \textit{sys…