Dancheng Liu

Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception Deficits

Introducing Accurate 4-Bit Quantization with Hyperspherical Architecture

Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data

FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks

Large Language Models have Intrinsic Self-Correction Ability

Sub-Sequential Physics-Informed Learning with State Space Model

Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability

Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices

KidSpeak: A General Multi-Purpose LLM for Kids' Speech Recognition and Screening