Related papers: Self-Improvement for Fast, High-Quality Plan Gener…
Feature transformation aims to extract a good representation (feature) space by mathematically transforming existing features. It is crucial to address the curse of dimensionality, enhance model generalization, overcome data sparsity, and…
Autonomous multi-finger grasping is a fundamental capability in robotic manipulation. Optimization-based approaches show strong performance, but tend to be sensitive to initialization and are potentially time-consuming. As an alternative,…
In this paper we describe SYNERGY, which is a highly parallelizable, linear planning system that is based on the genetic programming paradigm. Rather than reasoning about the world it is planning for, SYNERGY uses artificial selection,…
Making sense of the world and acting in it relies on building simplified mental representations that abstract away aspects of reality. This principle of cognitive mapping is universal to agents with limited resources. Living organisms,…
Recent advances in generative models have made it increasingly difficult to distinguish real data from model-generated synthetic data. Using synthetic data for successive training of future model generations creates "self-consuming loops",…
AI image generators based on diffusion models have recently garnered attention for their capability to create images from simple text prompts. However, for practical use in civil engineering they need to be able to create specific…
Gene finding is the task of identifying the locations of coding sequences within the vast amount of genetic code contained in the genome. With an ever increasing quantity of raw genome sequences, gene finding is an important avenue towards…
Recent progress in material data mining has been driven by high-capacity models trained on large datasets. However, collecting experimental data (real data) has been extremely costly since the amount of human effort and expertise required.…
Generative Adversarial Networks (GANs) have significantly advanced image synthesis, however, the synthesis quality drops significantly given a limited amount of training data. To improve the data efficiency of GAN training, prior work…
In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…
Diffusion models, which iteratively denoise data samples to synthesize high-quality outputs, have achieved empirical success across domains. However, optimizing these models for downstream tasks often involves nested bilevel structures,…
Data availability is a bottleneck during early stages of development of new capabilities for intelligent artificial agents. We investigate the use of text generation techniques to augment the training data of a popular commercial artificial…
Synthetic data augmentation has emerged as a promising solution when pre-training is constrained by data rather than compute. We study how to design synthetic data algorithms that achieve better loss scaling: not only lowering loss at…
Generative modeling aims at producing new datapoints whose statistical properties resemble the ones in a training dataset. In recent years, there has been a burst of machine learning techniques and settings that can achieve this goal with…
Recent generative adversarial networks (GANs) are able to generate impressive photo-realistic images. However, controllable generation with GANs remains a challenging research problem. Achieving controllable generation requires semantically…
As AI workloads proliferate, optimizing arithmetic units is becoming increasingly important for reducing the footprint of digital systems. Conventional design flows, which often rely on manual or heuristic-based optimization, are limited in…
When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is…
This paper aims to improve the path quality and computational efficiency of kinodynamic planners used for vehicular systems. It proposes a learning framework for identifying promising controls during the expansion process of sampling-based…
Trajectory data generation is an important domain that characterizes the generative process of mobility data. Traditional methods heavily rely on predefined heuristics and distributions and are weak in learning unknown mechanisms. Inspired…
Despite the recent progress in hyperparameter optimization (HPO), available benchmarks that resemble real-world scenarios consist of a few and very large problem instances that are expensive to solve. This blocks researchers and…