specific method · filed under model architecture
Joint vision-language pre-training
Visual and text embeddings are trained together from the start of language-model pre-training.
- sources
- 2
- model
- 1
- lab adopt it
- 1
- strongest
- core
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1core 1
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
visual and text embeddings trained jointly from the start of pre-training rather than added afterward
coreotherin DeepSeek-V4.1-FlashDeepSeek
processed jointly with text embeddings from the start of language-model pre-training
usedotherin DeepSeek-V4.1-FlashDeepSeek
Filed alongside
Other methods under model architecture :: multimodal architecture.
Encoder-free multimodal architectureEarly fusion multimodal trainingDiscrete token encoding for audioHierarchical patch encoderMixed-modality trainingConfigurable visual token budgetJoint multimodal decoding in a shared hidden spaceNative multimodal understanding3×3 pixel-unshuffle downsamplingRaw audio projection into the LLM embedding spaceVision Transformer (ViT)2×2 pixel-shuffle downsamplingAudio encoder initialized from MiMo-AudioAudio Transformer (AuT)Causal streaming ConvNet codec decoderData-parallel-first multimodal encodingDecoupled Encoder Process (DEP)Dedicated multimodal encodersDisaggregated encoder trainingDiscarding the LLM after vision-encoder trainingDual-format coordinate supervisionExplicit text-string timestampsFour-frame audio patches with within-patch bidirectional self-attentionFrom-scratch vision-encoder training with next-token prediction