Research
My research centers on generative models, agentic AI, and AI for science. Below are my papers and manuscripts in progress; code lives on GitHub.
Conference Papers
Published in International Conference on Machine Learning (ICML), 2026
SPADE casts forward surrogate modeling as a calibrated conditional diffusion problem and adds a kNN support-proximity prior, so an offline optimizer stays expressive without exploiting unsupported, out-of-distribution regions. We prove the regularizer is equivalent to Bayesian inference under a valid design prior, and it tops Design-Bench and LLM-optimization tasks.
Recommended citation: Yonghan Yang*, Ye Yuan*, Zipeng Sun, Linfeng Du, Bowei He, Haolun Wu, Can Chen, and Xue Liu. (2026). "Support-Proximity Augmented Diffusion Estimation for Offline Black-Box Optimization." International Conference on Machine Learning (ICML 2026). (* equal contribution)
Download Paper
Preprints & Works in Progress
Manuscript in preparation, 2026
Optimizing what an autonomous agent recalls: we train memory retrieval offline with a learned surrogate that scores which past experiences most improve downstream task success, rather than relying on raw semantic similarity.
Recommended citation: Yonghan Yang*, Ye Yuan*, et al. Surrogate-Guided Memory Retrieval for Autonomous Agents. Manuscript in preparation, 2026. (* equal contribution)
Survey · manuscript in preparation, 2026
A comprehensive review of the formulation, training, and applications of discrete diffusion models — unifying notation across masked, uniform, and absorbing-state processes and surveying their use in language, biology, and combinatorial design.
Recommended citation: Yonghan Yang, et al. A Survey on Discrete Diffusion Models. Manuscript in preparation, 2026.
Manuscript in preparation, 2026
Predicting and analyzing higher-order drug-combination-disease relationships from a comprehensive dataset, using semi-supervised learning to exploit the large space of unlabeled combinations.
Recommended citation: Yonghan Yang, et al. Semi-Supervised High-Order Relation Learning for Drug–Combination–Disease Prediction. Manuscript in preparation, 2026.
Benchmark · manuscript in preparation, 2026
A benchmark that evaluates LLM agents on realistic financial workflows — trading, hedging, market-insight generation, and auditing — measuring not just final answers but the quality of the reasoning and tool use along the way.
Recommended citation: Yonghan Yang, et al. An Agentic Benchmark for Financial Intelligence. Manuscript in preparation, 2026.
Benchmark · manuscript in preparation, 2025
An AI-agent framework and curated benchmark that evaluate whether agents can generate correct, runnable code for real biological research tasks across multiple data modalities.
Recommended citation: Yonghan Yang, et al. A Multi-Modal Benchmark for Biomedical Machine-Learning Agents. Manuscript in preparation, 2025–2026.
