Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action.
Jiasen LuChristopher ClarkSangho LeeZichen ZhangSavya KhoslaRyan MartenDerek HoiemAniruddha KembhaviPublished in: CoRR (2023)
Keyphrases
- autoregressive
- moving average
- random fields
- non stationary
- gaussian markov random field
- random field models
- sar images
- audio visual
- autoregressive model
- information extraction
- texture model
- spectrum analysis
- natural language
- higher order
- natural images
- co occurrence
- least squares
- prior knowledge
- autoregressive moving average