Lin Yang

12 papers UCLA

• Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
• CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic
• Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms
• Deployment Efficient Reward-Free Exploration with Linear Function Approximation
• Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks
• Federated Multi-armed Bandits with Efficient Bit-Level Communications
• LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data
• Near-Optimal Sample Complexity for Online Constrained MDPs
• PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization
• SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
• Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design
• VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers