Tianyi Zhang

4 papers Rice University

• 70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
• Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
• Building 3D Representations and Generating Motions From a Single Image via Video-Generation
• One Filters All: A Generalist Filter For State Estimation