Changsheng Li

Learning for Highly Faithful Explainability

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

Towards Multi-Table Learning: A Novel Paradigm for Complementarity Quantification and Integration

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

NoisyTraj: Robust Trajectory Prediction with Noisy Observations

Remember, Retrieve and Generate: Understanding Infinite Visual Concepts as Your Personalized Assistant