Ling Li

Code Driven Planning with Domain-Adaptive Selector

Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation

One for all: Zero-Shot Cross-Hardware Performance Modeling with LLMs for Tensor Program Tuning

Transfer-Controllable Policy for Model Protection in Deep Reinforcement Learning

EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization

QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation

Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers