We propose Reinforcement Learning from Contrast Distillation (RLCD), a m...
We propose Prefix-Adaptive Decoding (PREADD), a flexible method for
cont...
We present a framework that formulates visual question answering as modu...
We propose the Detailed Outline Control (DOC) framework for improving
lo...
We consider the problem of automatically generating longer stories of ov...
We present the Berkeley Crossword Solver, a state-of-the-art approach fo...
We introduce a novel setup for low-resource task-oriented semantic parsi...
In contrast to single-objective optimization (SOO), multi-objective
opti...
Path planning, the problem of efficiently discovering high-reward
trajec...
We propose Future Discriminators for Generation (FUDGE), a flexible and
...
We propose an efficient batching strategy for variable-length decoding o...
Uncertainty quantification (UQ) is an important component of molecular
p...
Generative models in molecular design tend to be richly parameterized,
d...
Advancements in neural machinery have led to a wide range of algorithmic...
We view molecular optimization as a graph-to-graph translation problem. ...