GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
Paper • 2609.39600 • Published • 97
Shuchang Zhou
zsc
AI & ML interests
MLLM Pretrain @XPengMotors ; Step1-Audio, Step2 MoE @StepFun_ai ; https://shorturl.at/v6982
Recent Activity
authored a paper 7 days ago
AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding authored a paper 7 days ago
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed authored a paper 7 days ago
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual PrimitivesOrganizations
None yet