Yue Wu

6 papers Princeton University

• DISC: Dynamic Decomposition Improves LLM Inference Scaling
• Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval
• FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning
• Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering
• PointTruss: K-Truss for Point Cloud Registration
• SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models