Physical AI – Selected Works

Overview

Explores the evolution of AI from purely digital, data-driven abstraction toward physically grounded intelligence aligned with the laws of nature. Advances in guided generative models illustrate how AI can not only simulate and predict, but also plan and create within real-world physical constraints—bridging digital representations with physical reality.

Keynotes

• Ong, Y. S., Closing the Gap: From Digital AI to Physically Grounded intelligence (Keynote, 32nd International Conference on Neural Information Processing, Okinawa Institute of Science and Technology (OIST), Japan, ICONIP2025, November 20-24, 2025. Details.
• Ong, Y. S., Physically Grounded AI for Scientific Discovery: From Prediction to Generative Design (Invited Speaker, 34th International Joint Conference on Artificial Intelligence (IJCAI'2025), Montreal, Canada, 16 - 22 August, 2025 and Guangzhou, China, 29 - 31 August, 2025). Details.
• Ong, Y. S., AI in Science. (Keynote, Next Generation of Artificial Intelligence Academic Forum, 23rd Conference on International Exchange of Professionals, May 23-24, 2025, Guangzhou, China).

Generative AI for Optimization and Design (Selected Publications)

• 2025
  KY Tan, Y Lyu, I Tsang, YS Ong.
  Distributional Multi-objective Black-box Optimization for Diffusion-model Inference-time Multi-Target Generation (arXiv preprint arXiv:2510.26278)


• 2025
  Wei, Z , Ooi, C C , Gupta, A , Chiu, P -H , YS Ong.
  Evolvable Conditional Diffusion (International Joint Conference on Artificial Intelligence, 2025)


• 2025
  KY Tan, Y Lyu, I Tsang, YS Ong.
  Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation (International Conference on Learning Representation, 2025)


• 2025
  F Wang, Q Xu, YS Ong, M Pollefeys.
  Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model (IEEE Transactions on Pattern Analysis and Machine Intelligence)


• 2025
  M Wong, Y Lyu, T Rios, S Menzel, YS Ong.
  LLM-to-Phy3D: Physically Conform Online 3D Object Generation with LLMs (arXiv preprint arXiv:2506.11148)


• 2025
  Q Xu, J Liu, M Wong, C Chen, YS Ong.
  Looks great, functions better: Physics compliance text-to-3D shape generation (International Joint Conference on Neural Networks)


• 2025
  Y Sun, Z Sun, Y Du, J Zhang, YS Ong.
  Model-agnostic social network refinement with diffusion models for robust social recommendation (Proceedings of the ACM on Web Conference 2025, 370-378)


• 2025
  J Xie, W Li, X Li, Z Liu, YS Ong, CC Loy.
  Mosaicfusion: Diffusion models as data augmenters for large vocabulary instance segmentation (International Journal of Computer Vision 133 (4), 1456-1475)


• 2025
  T Wei, J Liu, A Gupta, CC Ooi, PS Tan, YS Ong.
  Parametric Expensive Multi-Objective Optimization via Generative Solution Modeling (arXiv preprint arXiv:2511.09598)


• 2024
  Y Lyu, KY Tan, YS Ong, IW Tsang.
  Covariance-adaptive sequential black-box optimization for diffusion targeted generation (arXiv preprint arXiv:2406.00812)


• 2024
  J Han, S Feng, M Zhou, X Zhang, YS Ong, X Li.
  Diffusion model in normal gathering latent space for time series anomaly detection (Joint European Conference on Machine Learning and Knowledge Discovery in …)


• 2024
  H Yu, Y Hou, W Pei, YS Ong, Q Zhang.
  Divdiff: A conditional diffusion model for diverse human motion prediction (IEEE Transactions on Multimedia)


• 2024
  Q Xu, J Liu, M Wong, C Chen, YS Ong.
  Precise-physics driven text-to-3d generation (arXiv preprint arXiv:2403.12438)


• 2024
  M Wong, T Rios, S Menzel, YS Ong.
  Generative ai-based prompt evolution engineering design optimization with vision-language model (arXiv preprint arXiv:2406.09143)


• 2024
  J Liu, A Gupta, YS Ong, PS Tan.
  Inverse multiobjective optimization by generative model prompting (2024 IEEE Conference on Artificial Intelligence (CAI), 737-740)


• 2024
  S Liu, C Chen, X Qu, K Tang, YS Ong.
  Large language models as evolutionary optimizers (IEEE Congress on Evolutionary Computation (CEC), 1–8)


• 2024
  M Wong, T Rios, S Menzel, YS Ong.
  Prompt evolutionary design optimization with generative shape and vision-language models (IEEE Congress on Evolutionary Computation (CEC), 1–8)


• 2023
  M Wong, YS Ong, A Gupta, KK Bali, C Chen.
  Prompt evolution for generative ai: A classifier-guided approach (2023 IEEE Conference on Artificial Intelligence (CAI), 226-229)


• 2022
  Z Guo, H Liu, YS Ong, X Qu, Y Zhang, J Zheng.
  Generative multiform Bayesian optimization (IEEE Transactions on Cybernetics 53 (7), 4347-4360)