Upload README.md with huggingface_hub

README.md

@@ -10,42 +10,42 @@ tags:
 
 # NimCritic
 
-NimCritic 根据机器人视频和任务指令，逐帧估计任务进度与是否完成。
+NimCritic estimates per-frame task progress and completion from a robot video and a task instruction.
 
-[Project page](https://rimbot.com/en/research/nimcritic/) · [Paper](https://arxiv.org/abs/2610.32776)
+[Project page](https://rimbot.com/en/research/nimcritic/) · [Paper](https://arxiv.org/abs/2610.32776) · [Benchmark][hf-benchmark] · [Demo](https://critic.rimbot.com/)
 
-## 目录里有什么
+## Contents
 
-| 路径 | 内容 |
+| Path | Contents |
 |---|---|
-| `infer_nimcritic.py` | 读帧、滑窗和命令行参数。 |
-| `nimcritic_model.py` | 模型：video DiT、value DiT、VAE、文本编码器。 |
-| `nimcritic_step_128000.pt` | step 128000。video expert 5.00B，value expert 1.02B，bfloat16。 |
-| `base/` | Wan2.2 VAE、UMT5-XXL 编码器和分词器。不含 Wan2.2 DiT：video expert 的完整权重已经在 `.pt` 里。 |
+| `infer_nimcritic.py` | Frame loading, the sliding window, and the command-line arguments. |
+| `nimcritic_model.py` | The model: video DiT, value DiT, VAE, and text encoder. |
+| `nimcritic_step_128000.pt` | Step 128000. Video expert 5.00B, value expert 1.02B, bfloat16. |
+| `base/` | Wan2.2 VAE, UMT5-XXL encoder, and tokenizer. The Wan2.2 DiT is not included: the full video-expert weights are already in the `.pt`. |
 
-`base/` 包含：
+`base/` contains:
 
 - `DiffSynth-Studio/Wan-Series-Converted-Safetensors/Wan2.2_VAE.safetensors`
 - `DiffSynth-Studio/Wan-Series-Converted-Safetensors/models_t5_umt5-xxl-enc-bf16.safetensors`
-- `Wan-AI/Wan2.1-T2V-1.3B/google/umt5-xxl/`（分词器）
+- `Wan-AI/Wan2.1-T2V-1.3B/google/umt5-xxl/` (tokenizer)
 
-许可见 Apache-2.0。
+License: Apache-2.0.
 
-## 环境
+## Environment
 
-Python 3.12+。在本目录安装推理依赖：
+Python 3.12+. Install the inference dependencies in this directory:
 
 ```bash
 uv sync
 ```
 
-依赖写在 `pyproject.toml`：PyTorch、`transformers`（4.57，低于 4.58）、`safetensors`、`einops`、`opencv-python-headless`、`Pillow`、`numpy`、`tqdm`。
+Dependencies are listed in `pyproject.toml`: PyTorch, `transformers` (4.57, below 4.58), `safetensors`, `einops`, `opencv-python-headless`, `Pillow`, `numpy`, and `tqdm`.
 
-模型代码在 `nimcritic_model.py`，权重与 `base/` 在同目录。推理不访问其他路径，也不下载额外文件。
+The model code is `nimcritic_model.py`. The checkpoint and `base/` are in the same directory. Inference does not read any other path and does not download extra files.
 
-## 推理
+## Inference
 
-在本目录执行。默认读取同目录的 `nimcritic_step_128000.pt` 与 `base/`。
+Run from this directory. The defaults are `nimcritic_step_128000.pt` and `base/` next to the script.
 
 ```bash
 uv run python infer_nimcritic.py \
@@ -54,7 +54,7 @@ uv run python infer_nimcritic.py \
   --output result.json
 ```
 
-输入为视频文件时，按容器帧率采样至 2Hz（`--sample-hz`，默认 2），并保留最后一帧。输入已是 2Hz 帧序列时使用 `--frames`，不再按 2Hz 重采样：
+A video file is sampled to 2 Hz from the container frame rate (`--sample-hz`, default 2), and the last frame is kept. A frame sequence that is already 2 Hz uses `--frames` and is not resampled:
 
 ```bash
 uv run python infer_nimcritic.py \
@@ -63,27 +63,27 @@ uv run python infer_nimcritic.py \
   --output result.json
 ```
 
-`--base` 指向 `base/` 这一层，不是里面的 `DiffSynth-Studio/`。
+`--base` is the `base/` directory, not the `DiffSynth-Studio/` directory inside it.
 
-默认口径：帧拉到 256×448（`stretch`），progress 是相对当前窗口条件帧的增量，写回前还原成 0–1，`rollout_stride=1`，`distance` 聚合，20 步，seed 42。和论文短任务表同一口径时加上 `--rollout-stride 2`。
+Defaults: frames are resized to 256×448 (`stretch`); progress is a delta relative to the condition frame of the current window and is mapped back to 0–1 before it is written; `rollout_stride=1`; `distance` aggregation; 20 steps; seed 42. Add `--rollout-stride 2` to match the short-task table in the paper.
 
-每个参数的含义、可选项和默认值：
+Arguments, choices, and defaults:
 
 ```bash
 uv run python infer_nimcritic.py --help
 ```
 
-不加载权重、只检查抽帧和参数：
+Check frame sampling and arguments without loading weights:
 
 ```bash
 uv run python infer_nimcritic.py --self-check
 ```
 
-GPU 推理建议预留不少于 24 GB 显存。CPU 推理通过 `--device cpu` 指定，耗时高于 GPU。
+Reserve at least 24 GB of GPU memory. CPU inference is `--device cpu` and is slower than the GPU.
 
-结果 JSON 中，`progress` 与 `success` 为逐帧的 0–1 数值。`sampling` 记录所采用的帧下标。
+In the result JSON, `progress` and `success` are per-frame values in 0–1. `sampling` records the frame indices that were used.
 
-## 引用
+## Citation
 
 ```bibtex
 @article{xu2026nimcritic,
@@ -95,10 +95,6 @@ GPU 推理建议预留不少于 24 GB 显存。CPU 推理通过 `--device cpu`
 }
 ```
 
-基准请同时引用 [LOOM][hf-benchmark]。
+Cite [LOOM][hf-benchmark] as well when reporting benchmark numbers.
 
-[hf-model]: https://huggingface.co/RimbotAI/NimCritic
 [hf-benchmark]: https://huggingface.co/datasets/RimbotAI/LOOM
-[arxiv]: https://arxiv.org/abs/2610.32776
-[project]: https://rimbot.com/en/research/nimcritic/
-[demo]: https://critic.rimbot.com/