model
Channel-wise Autoregressive (CAR)
modelactiveprovisional
channel-wise-autoregressive-car--58376924·1 events·first seen 22d agoAliases: Channel-wise Autoregressive (CAR)
Co-occurring entities
More like this (12)
autoregressive transformercanonical correlation analysisCARV8B autoregressive language modelFeature Auto-EncoderCVaR (Conditional Value at Risk)multivariate time series representation learningChannel-wise Vector QuantizationSparse AutoencodersautoresearchCross-Annotator Preference Optimization (CAPO)Sparse Autoencoder
Recent events (1)
Channel-wise Vector Quantization (CVQ): A New Image Tokenization Paradigm with Next-Channel Prediction
Researchers introduce Channel-wise Vector Quantization (CVQ), which replaces conventional patch-wise discrete tokens with channel-wise tokens that represent an image as discrete levels of visual detail. Built on CVQ, the Channel-wise Autoregressive (CAR) model uses a 'next-channel prediction' objective, generating images by progressively refining from global structure to fine-grained attributes. CVQ achieves 100% codebook utilization with a 16K+ codebook and the CAR model scores 86.7 on DPG and 0.79 on GenEval for text-to-image generation. The approach offers a structural alternative to raster-order patch-based autoregressive image generation.