Many real-world applications of language models (LMs), such as code
auto...
Generating a chain of thought (CoT) can increase large language model (L...
Prior work has identified a resilient phenomenon that threatens the
perf...
Modern multi-agent reinforcement learning frameworks rely on centralized...
Over the last decade, Computer Vision, the branch of Artificial Intellig...
With the emergence of conversational artificial intelligence (AI) agents...
Typical active learning strategies are designed for tasks, such as
class...
Scene graph prediction --- classifying the set of objects and predicates...
Visual knowledge bases such as Visual Genome power numerous applications...
Though image-to-sequence generation models have become overwhelmingly po...
Images are not simply sets of objects: each image represents a web of
in...
Today's conversational agents are restricted to simple standalone comman...
Visual relationships capture a wide variety of interactions between pair...
Human language is colored by a broad range of topics, but existing text
...
From smart homes that prepare coffee when we wake, to phones that know n...
We have seen great progress in basic perceptual tasks such as object
rec...
The ImageNet Large Scale Visual Recognition Challenge is a benchmark in
...