Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight
Paper
•
2511.16175
•
Published
•
12
Yi Yang (SII)
Yysrc
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding
upvoted
a
paper
7 days ago
Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
updated
a dataset
17 days ago
Yysrc/mantis_libero_lerobot
Organizations
authored
a
paper
28 days ago
authored
a
paper
7 months ago