Ningyi Xu

Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback

SentKVCompress: Sentence-Level Dynamic KVCache Compression for Efficient Long-Context LLM Inference

DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale

Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM

OmniBal: Towards Fast Instruction-Tuning for Vision-Language Models via Omniverse Computation Balance

OMNIBAL: TOWARDS FAST INSTRUCT-TUNING FOR VISION-LANGUAGE MODELS VIA OMNIVERSE COMPUTATION BALANCE