GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification
Paper • 2604.14258 • Published • 24
Yu qt
qiu-66
AI & ML interests
None yet
Recent Activity
upvoted a paper 6 days ago
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon upvoted a paper 6 days ago
Embodied-Navigator: Point, Think, Memorize, and Align for Efficient NavigationOrganizations
None yet
upvoted 6
papers 6 days ago
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
Paper • 2607.01804 • Published • 28
Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation
Paper • 2608.17512 • Published • 53
Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text
Paper • 2607.21072 • Published • 36
Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
Paper • 2609.23038 • Published • 63
EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks
Paper • 2609.28236 • Published • 39