Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation

H Qian, YD Chen, S Lou, FS Khan, X Jin… - arXiv preprint arXiv …, 2024 - arxiv.org
Dichotomous Image Segmentation (DIS) tasks require highly precise annotations, and
traditional dataset creation methods are labor intensive, costly, and require extensive …

Lico: Large language models for in-context molecular optimization

T Nguyen, A Grover - arXiv preprint arXiv:2406.18851, 2024 - arxiv.org
Optimizing black-box functions is a fundamental problem in science and engineering. To
solve this problem, many approaches learn a surrogate function that estimates the …

Latent energy-based odyssey: Black-box optimization via expanded exploration in the energy-based latent space

P Yu, D Zhang, H He, X Ma, R Miao, Y Lu… - arXiv preprint arXiv …, 2024 - arxiv.org
Offline Black-Box Optimization (BBO) aims at optimizing a black-box function using the
knowledge from a pre-collected offline dataset of function values and corresponding input …

Guided trajectory generation with diffusion models for offline model-based optimization

T Yun, S Yun, J Lee, J Park - arXiv preprint arXiv:2407.01624, 2024 - arxiv.org
Optimizing complex and high-dimensional black-box functions is ubiquitous in science and
engineering fields. Unfortunately, the online evaluation of these functions is restricted due to …

Position Paper: Leveraging Foundational Models for Black-Box Optimization: Benefits, Challenges, and Future Directions

X Song, Y Tian, RT Lange, C Lee, Y Tang… - arXiv preprint arXiv …, 2024 - arxiv.org
Undeniably, Large Language Models (LLMs) have stirred an extraordinary wave of
innovation in the machine learning research domain, resulting in substantial impact across …

Pretrained Optimization Model for Zero-Shot Black Box Optimization

X Li, K Wu, YB Li, X Zhang, H Wang… - The Thirty-eighth Annual …, 2024 - openreview.net
Zero-shot optimization involves optimizing a target task that was not seen during training,
aiming to provide the optimal solution without or with minimal adjustments to the optimizer. It …

Reinforced In-Context Black-Box Optimization

L Song, C Gao, K Xue, C Wu, D Li, J Hao… - arXiv preprint arXiv …, 2024 - arxiv.org
Black-Box Optimization (BBO) has found successful applications in many fields of science
and engineering. Recently, there has been a growing interest in meta-learning particular …

GROOT: Effective Design of Biological Sequences with Limited Experimental Data

TVT Tran, NK Ngo, VA Nguyen, TS Hy - arXiv preprint arXiv:2411.11265, 2024 - arxiv.org
Latent space optimization (LSO) is a powerful method for designing discrete, high-
dimensional biological sequences that maximize expensive black-box functions, such as …

Generative Adversarial Model-Based Optimization via Source Critic Regularization

MS Yao, Y Zeng, H Bastani, JR Gardner… - The Thirty-eighth …, 2024 - openreview.net
Offline model-based optimization seeks to optimize against a learned surrogate model
without querying the true oracle objective function during optimization. Such tasks are …

Predicting from Strings: Language Model Embeddings for Bayesian Optimization

T Nguyen, Q Zhang, B Yang, C Lee, J Bornschein… - 2024 - openreview.net
Bayesian Optimization is ubiquitous in the field of experimental design and blackbox
optimization for improving search efficiency, but has been traditionally restricted to …