Shengyu Zhang

InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners

FlowMM: Cross-Modal Information Flow Guided KV Cache Merging for Efficient Multimodal Context Inference

CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration

FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets

GAMBIT: A Graph-structured and Decision-Aware Benchmark for MoBile GUI Tasks

ETC: training-free diffusion models acceleration with Error-aware Trend Consistency

PureKV: Plug-and-Play KV Cache Optimization with Spatial-Temporal Sparse Attention for Vision-Language Large Models

ACDC: Adaptive Cloud-Device Collaboration for Efficient and Accurate Semantic Segmentation

GAIR : GUI Automation via Information-Joint Reasoning and Group Reflection

GUI-PRA: Process Reward Agent for GUI Tasks

EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation

Cuff-KT: Tackling Learners' Real-time Learning Pattern Adjustment via Tuning-Free Knowledge State-Guided Model Updating

LLM-Assisted Fast and Customized Model Generation: A Preliminary Exploration

LAST: Latent Structure guided Gaussian Splatting from Monocular Human Videos