Liping Jing

Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty Quantification

Bandit-MoE: Diverse Knowledge Acquisition through Bandit Routing for Continual Learning

Learning to Generalize: An Information Perspective on Neural Processes

Beyond 2:4: Exploring V:N:M Sparsity for Efficient Transformer Inference on GPUs

1-Bit FQT: Pushing the Limit of Fully Quantized Training to 1-bit

Learning Robust Neural Processes with Risk-Averse Stochastic Optimization