6 accepted papers
Modern deep-learning models have achieved remarkable success in time-series forecasting. Yet, their performance degrades in long-term prediction due to error accumulation in autoregressive inference, where predictions are recursively used as inputs. While classical error correction mechanisms (ECMs)…
The specification and validation of robotics applications require bridging the gap between formulating requirements and systematic testing. This often involves manual and error-prone tasks that become more complex as requirements, design, and implementation evolve. To address this challenge systemat
Macro placement is a vital step in digital circuit design that defines the physical location of large collections of components, known as macros, on a 2D chip. Because key performance metrics of the chip are determined by the placement, optimizing it is crucial. Existing learning-based methods typic…
In recent years, there have been significant advancements in semantic parsing tasks, thanks to the introduction of pre-trained language models. However, a substantial gap persists between English and other languages due to the scarcity of annotated data. One promising strategy to bridge this gap inv…
Machine learning models will often fail when deployed in an environment with a data distribution that is different than the training distribution. When multiple environments are available during training, many methods exist that learn representations which are invariant across the different distribu…
We have investigated methods utilizing hierarchical structure information representation in the semantic parsing task and have devised a method that reinforces the semantic awareness of a pre-trained language model via a two-step fine-tuning mechanism: hierarchical structure information strengthenin…