Ruihao Gong

QVGen: Pushing the Limit of Quantized Video Generative Models

Post-Training Quantization for Video Matting

Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals

DA-KD: Difficulty-Aware Knowledge Distillation for Efficient Large Language Models

HarmoniCa: Harmonizing Training and Inference for Better Feature Cache in Diffusion Transformer Acceleration

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

ME-Switch: A Memory-Efficient Expert Switching Framework for Large Language Models

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

HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration