EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training
Paper • 2604.20012 • Published • 3
Yiyang Du PRO
yiyangd
·
AI & ML interests
None yet
Recent Activity
submitted a paper about 23 hours ago
EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training updated a bucket 5 days ago
yiyangd/vlm4vla-qwen3vl-2b-mix_base_embodied_5_0221_proximity-libero10-50k-ckpt-lr5e-5Organizations
upvoted a paper about 24 hours ago