mad-bot
/

cortex

@@ -18,7 +18,7 @@ base_model_relation: adapter
 Cortex is a compact specialist game policy: **11M trainable parameters** (10.98M exactly) over frozen [DINOv3 ViT-S+/16](https://huggingface.co/facebook/dinov3-vits16plus-pretrain-lvd1689m) features. Trained with pure behavior cloning on the ≈475-hour Quake subset of the public [Pixels2Play corpus](https://huggingface.co/datasets/elefantai/p2p-full-data) on a single consumer GPU (RTX 5080, 16 GB), it reaches deeper engine-verified route progress on Quake E1M1 than the released [P2P-150M](https://huggingface.co/elefantai/open-p2p) and [NitroGen](https://huggingface.co/nvidia/NitroGen) (≈500M) generalist gaming agents evaluated under the same protocol.
-The Video Preview on this page shows the checkpoint playing E1M1 from a fresh spawn ([full run on YouTube](https://youtu.be/Ou9NAmFoCOM)).
 In one sentence: 4 frames × 41 frozen DINOv3 tokens → a 6-layer 384-d transformer → 36 held-state logits (sampled at temperature 1) plus continuous mouse dx/dy, at 10 Hz. The full architecture, action-schema contract, and design rationale live in the [cortex-actor repository](https://github.com/kvark/cortex-actor); complete results, evaluation protocol, and negative results are in the [paper](https://github.com/kvark/cortex-actor/blob/main/paper/cortex_quake_bc.md).

 Cortex is a compact specialist game policy: **11M trainable parameters** (10.98M exactly) over frozen [DINOv3 ViT-S+/16](https://huggingface.co/facebook/dinov3-vits16plus-pretrain-lvd1689m) features. Trained with pure behavior cloning on the ≈475-hour Quake subset of the public [Pixels2Play corpus](https://huggingface.co/datasets/elefantai/p2p-full-data) on a single consumer GPU (RTX 5080, 16 GB), it reaches deeper engine-verified route progress on Quake E1M1 than the released [P2P-150M](https://huggingface.co/elefantai/open-p2p) and [NitroGen](https://huggingface.co/nvidia/NitroGen) (≈500M) generalist gaming agents evaluated under the same protocol.
+The Video Preview on this page shows a rollout of this checkpoint on E1M1 from a fresh spawn; there is [another run on YouTube](https://youtu.be/Ou9NAmFoCOM).
 In one sentence: 4 frames × 41 frozen DINOv3 tokens → a 6-layer 384-d transformer → 36 held-state logits (sampled at temperature 1) plus continuous mouse dx/dy, at 10 Hz. The full architecture, action-schema contract, and design rationale live in the [cortex-actor repository](https://github.com/kvark/cortex-actor); complete results, evaluation protocol, and negative results are in the [paper](https://github.com/kvark/cortex-actor/blob/main/paper/cortex_quake_bc.md).

replay.mp4 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f142651c1008d205c307a6ec6b5f467ab17758197f00af32285cf0ff373253
-size 17135374

 version https://git-lfs.github.com/spec/v1
+oid sha256:ae68d08d6bb8facac3d570b409ad5ebcd7984dafc566ee2efc655d40a9060463
+size 21394993