Picture for Haoxiang Wang

Haoxiang Wang

Department of ECE, Cornell University, NY, USA, GoPerception Laboratory, NY, USA

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Add code
Mar 18, 2025
Viaarxiv icon

ImViD: Immersive Volumetric Videos for Enhanced VR Engagement

Add code
Mar 18, 2025
Viaarxiv icon

Cosmos World Foundation Model Platform for Physical AI

Add code
Jan 07, 2025
Figure 1 for Cosmos World Foundation Model Platform for Physical AI
Figure 2 for Cosmos World Foundation Model Platform for Physical AI
Figure 3 for Cosmos World Foundation Model Platform for Physical AI
Figure 4 for Cosmos World Foundation Model Platform for Physical AI
Viaarxiv icon

Semi-Supervised Reward Modeling via Iterative Self-Training

Add code
Sep 10, 2024
Viaarxiv icon

Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts

Add code
Jun 18, 2024
Figure 1 for Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
Figure 2 for Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts
Viaarxiv icon

RLHF Workflow: From Reward Modeling to Online RLHF

Add code
May 13, 2024
Figure 1 for RLHF Workflow: From Reward Modeling to Online RLHF
Figure 2 for RLHF Workflow: From Reward Modeling to Online RLHF
Figure 3 for RLHF Workflow: From Reward Modeling to Online RLHF
Figure 4 for RLHF Workflow: From Reward Modeling to Online RLHF
Viaarxiv icon

Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience

Add code
Mar 15, 2024
Figure 1 for Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience
Figure 2 for Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience
Figure 3 for Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience
Figure 4 for Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience
Viaarxiv icon

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards

Add code
Mar 06, 2024
Viaarxiv icon

Enhancing Compositional Generalization via Compositional Feature Alignment

Add code
Feb 05, 2024
Viaarxiv icon

Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms

Add code
Nov 02, 2023
Viaarxiv icon