Jinyang Guo

MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems

AFTER: Mitigating the Object Hallucination of LVLM via Adaptive Factual-Guided Activation Editing

QuS: Towards High-Performance EfficientViT on FPGA by Quantization and Streamline Co-Design

SPEAR: Structured Pruning for Spiking Neural Networks via Synaptic Operation Estimation and Reinforcement Learning

BMAttn: Block-Aligned Mixed-Precision Attention Quantization for LLM Inference

BRENA: Brain-inspired Hierarchical Neural Alignment Framework for Visual Decoding from EEG Signals

BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models

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

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