Sinusoid position encoding table

Computes spatio-temporal features from given features. Parameters: features (torch.Tensor): Input features to process. Return

Creates a dictionary of task objects from either a name of task, config, or prepared Task object. :param task_name_list: List[Union[str, Dict, Ta

Validate the format of the line. If the line is not valid an exception will be raised. If maxWidth and maxHeight are specified, all points mu

result_brief: [{'title', 'text','screenshot_path'}]

Whether the task has a training set

Check if there is change in the response in the form of *change me*.

Judge if `asw` is equivalent to `gt_asw`. This function checks if the given answers are equivalent, considering various scenarios such a

Whether the pair of stresses is a valid iambic pair.

Lemmatizes a phrase (multiple words).

Converts HTML tree to the format required by apted

Exact match between targets and responses.

Whether two LaTeX expressions are equal.

Get maximum possible value

Normalize the LaTeX expression.

Parse a 2D point encoded in XML as <point>x, y</point>.

Parse the prediction from the generated response. Return the predicted index e.g., A, B, C, D. https://github.com/MMMU-Benchmark/MMMU/blo

Parse the prediction from the generated response. Return the predicted index e.g., A, B, C, D.

Parse an (x, y) point from XML formatted like this: <point>x, y</point>

Returns a Polygon object to use with the Polygon2 class from a list of 8 points: x1,y1,x2,y2,x3,y3,x4,y4

Processes a sample for evaluation.

Take a single document and the LMM results and evaluates, returning a dict where keys are the names of submetrics and values are the values of

Removes LaTeX math mode delimiters (\( ... \) and \[ ... \]) from a string while preserving the contents inside the delimiters. If no suc

Removes LaTeX \text{...} tags while keeping their content. :param latex_str: A string containing LaTeX expressions :return: The processe