Picture for Yilun Du

Yilun Du

Derek

MoE-Loco: Mixture of Experts for Multitask Locomotion

Add code
Mar 11, 2025
Viaarxiv icon

Generative Trajectory Stitching through Diffusion Composition

Add code
Mar 07, 2025
Figure 1 for Generative Trajectory Stitching through Diffusion Composition
Figure 2 for Generative Trajectory Stitching through Diffusion Composition
Figure 3 for Generative Trajectory Stitching through Diffusion Composition
Figure 4 for Generative Trajectory Stitching through Diffusion Composition
Viaarxiv icon

Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers

Add code
Feb 27, 2025
Viaarxiv icon

History-Guided Video Diffusion

Add code
Feb 10, 2025
Viaarxiv icon

Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains

Add code
Jan 10, 2025
Viaarxiv icon

Inference-Time Policy Steering through Human Interactions

Add code
Nov 25, 2024
Figure 1 for Inference-Time Policy Steering through Human Interactions
Figure 2 for Inference-Time Policy Steering through Human Interactions
Figure 3 for Inference-Time Policy Steering through Human Interactions
Figure 4 for Inference-Time Policy Steering through Human Interactions
Viaarxiv icon

SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning

Add code
Nov 23, 2024
Figure 1 for SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning
Figure 2 for SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning
Figure 3 for SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning
Figure 4 for SnapMem: Snapshot-based 3D Scene Memory for Embodied Exploration and Reasoning
Viaarxiv icon

Grounding Video Models to Actions through Goal Conditioned Exploration

Add code
Nov 11, 2024
Figure 1 for Grounding Video Models to Actions through Goal Conditioned Exploration
Figure 2 for Grounding Video Models to Actions through Goal Conditioned Exploration
Figure 3 for Grounding Video Models to Actions through Goal Conditioned Exploration
Figure 4 for Grounding Video Models to Actions through Goal Conditioned Exploration
Viaarxiv icon

Few-Shot Task Learning through Inverse Generative Modeling

Add code
Nov 07, 2024
Figure 1 for Few-Shot Task Learning through Inverse Generative Modeling
Figure 2 for Few-Shot Task Learning through Inverse Generative Modeling
Figure 3 for Few-Shot Task Learning through Inverse Generative Modeling
Figure 4 for Few-Shot Task Learning through Inverse Generative Modeling
Viaarxiv icon

Compositional Diffusion Models for Powered Descent Trajectory Generation with Flexible Constraints

Add code
Oct 05, 2024
Viaarxiv icon