Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
Paper
•
2510.09320
•
Published
•
2
•
2
Zhang
WenyaoZhang
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
10 days ago
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
upvoted
a
paper
2 months ago
Evaluating Gemini Robotics Policies in a Veo World Simulator
Organizations
commented
a
paper
4 months ago
[Bug] Import error when running on environment without flash_attn
5
#2 opened over 1 year ago
by
Isotr0py