Search Results for author:
Found 6 papers, 3 papers with code
Limitations of Agents Simulated by Predictive Models
Prior work has shown theoretically that models fail to imitate agents that generated the training data if the agents relied on hidden observations: the hidden observations act as confounding variables, and the models treat actions they generate as evidence for nonexistent observations.
Mitigating the Problem of Strong Priors in LMs with Context Extrapolation
We develop a new technique for mitigating the problem of strong priors: we take the original set of instructions, produce a weakened version of the original prompt that is even more susceptible to the strong priors problem, and then extrapolate the continuation away from the weakened prompt.
Unsupervised Training for Neural TSP Solver
We use our loss function with a Graph Neural Network and design controlled experiments on both Euclidean and asymmetric TSP.
Gates Are Not What You Need in RNNs
In this paper, we propose a new recurrent cell called Residual Recurrent Unit (RRU) which beats traditional cells and does not employ a single gate.
Goal-Aware Neural SAT Solver
To demonstrate the capabilities of the query mechanism, we formulate an unsupervised (not depending on labels) loss function for Boolean Satisfiability Problem (SAT) and theoretically show that it allows the network to extract rich information about the problem.
Residual Shuffle-Exchange Networks for Fast Processing of Long Sequences
Attention is a commonly used mechanism in sequence processing, but it is of O(n^2) complexity which prevents its application to long sequences.
Ranked #1 on
Music Transcription
on MusicNet
