5 papers
FlowRefiner: Flow Matching-Based Iterative Refinement for 3D Turbulent Flow Simulation
Yilong Dai, Yiming Sun, Yiheng Chen +3
Accurate autoregressive prediction of 3D turbulent flows remains challenging for neural PDE solvers, as small errors in fine-scale structures can accumulate rapidly over rollout. I…
Accelerating MHC-II Epitope Discovery via Multi-Scale Prediction in Antigen Presentation
Yue Wan, Jiayi Yuan, Zhiwei Feng +1
Antigenic epitope presented by major histocompatibility complex II (MHC-II) proteins plays an essential role in immunotherapy. However, compared to the more widely studied MHC-I in…
DriveBLIP2: Attention-Guided Explanation Generation for Complex Driving Scenarios
Shihong Ling, Yue Wan, Xiaowei Jia +1
This paper introduces a new framework, DriveBLIP2, built upon the BLIP2-OPT architecture, to generate accurate and contextually relevant explanations for emerging driving scenarios…
Unveiling Confirmation Bias in Chain-of-Thought Reasoning
Yue Wan, Xiaowei Jia, Xiang Lorraine Li
Chain-of-thought (CoT) prompting has been widely adopted to enhance the reasoning capabilities of large language models (LLMs). However, the effectiveness of CoT reasoning is incon…
Multi-channel learning for integrating structural hierarchies into context-dependent molecular representation
Yue Wan, Jialu Wu, Tingjun Hou +2
Reliable molecular property prediction is essential for various scientific endeavors and industrial applications, such as drug discovery. However, the data scarcity, combined with…