Experimental results show that MetaSchedule can cover the search space used in the state-of-the-art tensor program optimization frameworks in a modular way.
If only provided with the table, it is hard for existing models to produce controllable and high-fidelity logical generations.
We introduce HULK, a multi-task energy efficiency benchmarking platform for responsible natural language processing.
To this end, we construct a large-scale dataset called TabFact with 16k Wikipedia tables as the evidence for 118k human-annotated natural language statements, which are labeled as either ENTAILED or REFUTED.
Ranked #5 on Table-based Fact Verification on TabFact
Time series forecasting is an important problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation.
Ranked #27 on Image Generation on ImageNet 64x64 (Bits per dim metric)
In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb.