Simplify the model card

README.md

@@ -25,20 +25,16 @@ footage. The same first frame plus a different key sequence produces a different
 | File | Description |
 |---|---|
 | `step-10000.safetensors` | LoRA checkpoint, step 10,000 of the released training run |
-| `teaser.png` | Figure shown above |
 
 ## Method
 
+A pretrained video model already carries a language-to-motion prior from its training data, so
+rather than learning action control from scratch, we ground keyboard input in that existing prior.
 Key presses are converted into one short English sentence per latent video frame (e.g. *"the man
 walks forward, camera pans left sharply"*) and injected through MiniMax-H3's native text channel —
-the same channel the model was already pretrained on. A **directed attention mask** binds annotation
-*k* to video frame *k* only: frame *k* can read annotation *k*, but annotation *k* cannot read any
-other annotation, which closes a bypass a symmetric mask would leave open. Removing the annotation
-rows recovers the base model exactly.
-
-This checkpoint is a **rank-32 LoRA on `qkv_proj`/`out_proj`** across the 50 DiT blocks and 2
-token-refiner layers (104 modules, 208 tensors, 65.6M parameters — 0.198% of the 33.1B-parameter
-DiT). No action-specific module is added; the condition path itself carries zero extra weights.
+the same channel it was already pretrained on. A directed attention mask binds each sentence to its
+own video frame so the model knows which instruction applies when. The only thing trained is a
+rank-32 LoRA on `qkv_proj`/`out_proj` (65.6M parameters, 0.198% of the 33.1B-parameter DiT).
 
 Trained on 7,872 clips (832x480, 124 frames / 5.2s @ 24fps) from ABot-World-Explorer-500h.
 
@@ -46,8 +42,7 @@ Trained on 7,872 clips (832x480, 124 frames / 5.2s @ 24fps) from ABot-World-Expl
 
 This checkpoint is a LoRA delta for MiniMax-H3 and requires the base model plus a directed-mask
 attention patch to run (the mask is what binds each sentence to its frame; without it the LoRA
-weights alone don't reproduce the reported behavior). Code, the framework patch, and a minimal
-inference script are not published alongside this checkpoint yet.
+weights alone don't reproduce the reported behavior).
 
 ```python
 from safetensors.torch import load_file