10 papers
OPTScientist: Multi-Agent Discovery of Typed Optimizer Programs for Transformer Pretraining
Zhongzheng Li, Tiancan Feng, Wenhao Li +5
Designing optimizers for modern deep learning remains a challenging scientific problem, requiring the joint consideration of optimization geometry, state dynamics, numerical stabil…
OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
Feilong Tang, Xiang An, Yunyao Yan +16
Hypothesis. Artificial general intelligence is, at its core, a compression problem. Effective compression demands resonance: deep learning scales best when its architecture aligns…
MCCE: A Framework for Multi-LLM Collaborative Co-Evolution
Nian Ran, Zhongzheng Li, Yue Wang +5
Multi-objective discrete optimization problems, such as molecular design, pose significant challenges due to their vast and unstructured combinatorial spaces. Traditional evolution…
Revisiting Sampling Strategies for Molecular Generation
Yuyan Ni, Shikun Feng, Wei-Ying Ma +2
Sampling strategies in diffusion models are critical to molecular generation yet remain relatively underexplored. In this work, we investigate a broad spectrum of sampling methods…
Straight-Line Diffusion Model for Efficient 3D Molecular Generation
Yuyan Ni, Shikun Feng, Haohan Chi +5
Diffusion-based models have shown great promise in molecular generation but often require a large number of sampling steps to generate valid samples. In this paper, we introduce a…
UniGEM: A Unified Approach to Generation and Property Prediction for Molecules
Shikun Feng, Yuyan Ni, Yan Lu +3
Molecular generation and molecular property prediction are both crucial for drug discovery, but they are often developed independently. Inspired by recent studies, which demonstrat…