Update README.md

README.md

@@ -27,8 +27,8 @@ tags:
 
 The world model follows the architecture and two-stage training recipe of [Dreamer 4](https://arxiv.org/abs/2509.24527), adapted for large-scale multi-task continuous control, and is trained on **MMBench2** — a 427-hour, 210-task dataset for visual world modeling (see the [dataset repository](https://huggingface.co/datasets/nicklashansen/mmbench2)). Each variant is a `(tokenizer.pt, dynamics.pt)` pair at 224×224 resolution:
 
-- **tokenizer** — a causal video tokenizer (≈50M-parameter encoder + ≈50M-parameter decoder, projecting to a 64-dim tanh-bounded latent).
-- **dynamics** — a ≈250M-parameter block-causal Transformer trained on the frozen tokenizer with a shortcut flow-matching objective, with reward prediction and behavior cloning heads.
+- **tokenizer** — a causal video tokenizer (50M-parameter encoder + 50M-parameter decoder, projecting to a 64-dim continuous latent).
+- **dynamics** — a 250M-parameter block-causal Transformer trained on the frozen tokenizer with a shortcut flow-matching objective.
 
 ## Variants