Upload README.md with huggingface_hub

README.md

@@ -33,9 +33,8 @@ on the BEAT2 (BEATX) dataset.
 ## How the model works
 
 RAG-Gesture denoises a body-part-factored latent sequence conditioned on
-text (BERT), audio (wav2vec2), and a speaker embedding. At inference, three
-retrieval strategies — **discourse-relation**, **gesture-type**, and
-**LLM-extracted** — pull semantically-matched motion clips from a database
+text (BERT), audio (wav2vec2), and a speaker embedding. At inference,
+retrieval strategies — **discourse-relation** & **gesture-type** — pull semantically-matched motion clips from a database
 of training samples. The retrieved latents are injected into the diffusion
 process through *DDIM inversion + per-step insertion guidance*, biasing the
 denoiser toward the retrieved semantics without sacrificing the base model's