Update README.md (#4)

- Update README.md (9895fa5fbcdfb3aee161b3c33b75d4213edf7ab7)


Co-authored-by: Charles Norton <[email protected]>

README.md

@@ -209,7 +209,7 @@ In addition to the text-related preprocessing, we mainly undertake the following
 
 * UI Grounding and Navigation Data: For each UI screenshot, we extract the bounding boxes for the UI elements, and apply [Set-of-Mark Prompting](https://arxiv.org/abs/2310.11441) to overlay numeric marks on the raw image. The model is trained to generate the UI grounding text based on the image and the Set-of-Mark prompts.
 
-* Instruction Video Data: For each video clip, we apply [Co-Tracker](https://co-tracker.github.io/) to extract the grid traces and then apply filtering algorithm to remove the noisy or staic points. For videos that bear camera motion, we further apply homography transformation to stabilize the video clips. In tne end, we assign a numeric mark for each trace which gives us a set of trace-of-mark. The model is trained to generate the trace-of-mark given the video clips and instructional text.
+* Instruction Video Data: For each video clip, we apply [Co-Tracker](https://co-tracker.github.io/) to extract the grid traces and then apply filtering algorithm to remove the noisy or static points. For videos that bear camera motion, we further apply homography transformation to stabilize the video clips. In the end, we assign a numeric mark for each trace which gives us a set of trace-of-mark. The model is trained to generate the trace-of-mark given the video clips and instructional text.
 
 * Robotics Manipulation Data: For robotics data in Open-X Embodiment, we extract the 7 DoF robot gripper state and also extract the trace-of-mark from the video clips. Similar filtering and stabilization steps are applied to the video clips. The model is trained to generate the robot manipulation action as well as the trace-of-mark given the video clips and instructional text.
 
@@ -309,7 +309,7 @@ Zero-shot evaluation on agentic intelligence. We report the results for pretrain
 * Language Model: We use [Meta LLama-3](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as the backbone LLM.
 * Vision Encoder: We use [CLIP-ConvneXt-XXLarge](https://huggingface.co/laion/CLIP-convnext_xxlarge-laion2B-s34B-b82K-augreg) trained by LAION team as the vision encoder to tokenize the images and videos.
 
-The whole pipeline follows the common practice in the multimodal LLMs, where the vision encoder is used to tokenize the images and videos, and then the visual tokens are fed into the LLM along with the textal tokens to generate the text outputs.
+The whole pipeline follows the common practice in the multimodal LLMs, where the vision encoder is used to tokenize the images and videos, and then the visual tokens are fed into the LLM along with the textual tokens to generate the text outputs.
 
 
 ### Compute Infrastructure
@@ -337,14 +337,14 @@ Our model is built based on:
 * [Transformers](https://huggingface.co/transformers/)
 * [TorchVision](https://pytorch.org/vision/stable/index.html)
 * [DeepSpeed](https://www.deepspeed.ai/)
-* [FlashAttenton](https://github.com/HazyResearch/flash-attention)
+* [FlashAttention](https://github.com/HazyResearch/flash-attention)
 
 
 ## Intended Uses
 
 <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
-This model is intended for broad research use in English. It is designed only for research purposes and aimed at knowledge-sharing and accelerating research in multimodal AI, particularly in mutimodal agentic AI. It is intended to be used by domain experts who are independently capable of evaluating the quality of outputs before acting on them.
+This model is intended for broad research use in English. It is designed only for research purposes and aimed at knowledge-sharing and accelerating research in multimodal AI, particularly in multimodal agentic AI. It is intended to be used by domain experts who are independently capable of evaluating the quality of outputs before acting on them.
 
 ### Direct Use
 
@@ -352,7 +352,7 @@ This model is intended for broad research use in English. It is designed only fo
 
 The model takes images and text as inputs, and produces the textual outputs for the following uses:
 
-* **Image/Video-Conditoned Text Generation:** The model can generate text (e.g., descriptions, answers) based on the input text and image.
+* **Image/Video-Conditioned Text Generation:** The model can generate text (e.g., descriptions, answers) based on the input text and image.
 
 * **Visual Planning Capabilities:** The model can also produce the visual trace as the future planning to accomplish a task (e.g., move object from one place to another).
 
@@ -380,7 +380,7 @@ The model can be further finetuned for different downstream tasks, such as:
 
 * **UI Navigation:** We can finetune this model for specific UI navigation tasks, such as web navigation or mobile navigation. The model can achieve superior performance on these tasks.
 
-* **Robotics Manipulation:** Our model can be further finetuned for robotics tasks given its general agentic capabilities as a vision-language-action model. After finetuning, our model significantly outperms the state-of-the-art models such as OpenVLA on robotics manipulation tasks.
+* **Robotics Manipulation:** Our model can be further finetuned for robotics tasks given its general agentic capabilities as a vision-language-action model. After finetuning, our model significantly outperforms the state-of-the-art models such as OpenVLA on robotics manipulation tasks.
 
 
 ## Bias, Risks, and Limitations