DexVLG: Dexterous Vision-Language-Grasp Model at Scale
Paper • 2507.02747 • Published
AI & ML interests
None defined yet.
Recent Activity
View all activity
qizekun
authored 10
papers 19 days ago
Positional Prompt Tuning for Efficient 3D Representation Learning
Paper • 2408.11567 • Published
Switch-JustDance: Benchmarking Whole Body Motion Tracking Controllers Using a Commercial Console Game
Paper • 2511.17925 • Published
MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning
Paper • 2510.03142 • Published
RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction
Paper • 2608.28693 • Published
UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction
Paper • 2609.12898 • Published
Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policy
Paper • 2610.26848 • Published • 21
Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies
Paper • 2609.38537 • Published • 20
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
Paper • 2608.13555 • Published • 18
DeformGen: Dynamics-Based Topology Augmentation for Deformable Manipulation Policy Learning
Paper • 2606.25939 • Published
qizekun
submitted a
paper to Daily Papers 21 days ago
qizekun
submitted a
paper to Daily Papers about 1 month ago
qizekun
submitted a
paper to Daily Papers 3 months ago
xjcvcvxj
submitted a
paper to Daily Papers 3 months ago
qizekun
authored 2
papers 5 months ago
qizekun
submitted a
paper to Daily Papers 5 months ago
qizekun
authored 3
papers 5 months ago
Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
Paper • 2510.09320 • Published • 3
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
Paper • 2602.10098 • Published • 25
ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models
Paper • 2601.12428 • Published