STEP3-VL-10B Technical Report
Paper
•
2601.09668
•
Published
•
187
Linkangheng
Kangheng
AI & ML interests
None yet
Recent Activity
liked
a model
4 days ago
QuantTrio/Step3-VL-10B-AWQ
liked
a Space
7 days ago
stepfun-ai/Step3-VL-10B
published
a Space
7 days ago
stepfun-ai/Step3-VL-10B
Organizations
authored
a
paper
10 days ago
authored
5
papers
12 days ago
Unhackable Temporal Rewarding for Scalable Video MLLMs
Paper
•
2502.12081
•
Published
•
1
Perception-R1: Pioneering Perception Policy with Reinforcement Learning
Paper
•
2504.07954
•
Published
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
Paper
•
2507.05255
•
Published
•
75
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding
Paper
•
2507.19427
•
Published
•
19
NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
Paper
•
2508.10711
•
Published
•
145