Connecting Language to Actions & the World @ CMU



WebQA Benchmark

WebQA, is a new benchmark for multimodal multihop reasoning in which systems are presented with the same style of data as humans when searching the web: Snippets and Images. The system must then identify which information is relevant across modalities and combine it with reasoning to answer the query. Systems will be evaluated on both the correctness of their answers and their sources.

VLC Checkpoints

Training Vision-language Transformers from Captions Alone. An MAE based Vision-Language Transformer that doesn't rely on supervised class labels.


ALFRED (Action Learning From Realistic Environments and Directives), is a new benchmark for learning a mapping from natural language instructions and egocentric vision to sequences of actions for household tasks. Long composition rollouts with non-reversible state changes are among the phenomena we include to shrink the gap between research benchmarks and real-world applications.