Model techniques map
Techniquesmodel architecturepositional encoding

specific method · filed under model architecture

Temporal-Modality Rotary Position Embedding

A rotary position embedding used to provide temporal awareness in multimodal inputs.

Also called TM-RoPE.

source
1
model
1
labs adopt it
0
strongest
not used

How sources treat it

One count per evidence span, weakest treatment to strongest.

not used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we apply TM-RoPE to endow the model with temporal awareness. However, we find that directly encoding absolute time through temporal position IDs can lead to excessively sparse indices for visual patches from long video with audio inputs

not usedmodel architecturein Qwen3.5-OmniQwen

Filed alongside

Other methods under model architecture :: positional encoding.