Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs
Paper
•
2509.25779
•
Published
•
16
Jason Wang
jasonzwang
·
AI & ML interests
Machine Learning/Deep Learning Accelerations and Compression, Computer Vision, Vision Language Models, Multimodal Learning
Recent Activity
authored
a paper
8 days ago
LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical
Image Understanding
authored
a paper
8 days ago
Local2Global query Alignment for Video Instance Segmentation
authored
a paper
8 days ago
Reasoning Models Can be Accurately Pruned Via Chain-of-Thought
Reconstruction
Organizations
upvoted
a
paper
10 days ago