Recent breakthroughs in training techniques for state space models (SSMs) specifically geared toward dynamical systems (DS) reconstruction (DSR) enable to recover the underlying system including its geometrical (attractor) and long-term statistical invariants from even short time series. These techniques are based on control-theoretic ideas, like modern variants of teacher forcing (TF), to ensure stable loss gradient propagation while training.

Obtaining effective representations of DNA sequences is crucial for genome analysis.

Multi-task reinforcement learning endeavors to efficiently leverage shared information across various tasks, facilitating the simultaneous learning of multiple tasks.

However, the design of methods for learning credal set predictors remains a challenging problem. In this paper, we make use of conformal prediction for this purpose.

When applied to medium-size language models (e.g., GPT2-large), Ctrl-G also beats its counterparts on standard benchmarks by large margins.

Multi-label active learning is a crucial yet challenging area in contemporary machine learning, often complicated by a large and sparse label space.

Recent work demonstrates that, post-training large language models with open-domain instruction following data have achieved colossal success.

We propose a novel preference modeling approach that utilizes AI feedback and only requires a small amount of human data.

However, it was recently shown that gradient inversion attacks can reconstruct this data from the shared gradients.