Lihao Liu

UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis

CorBenchX: Large-Scale Chest X-Ray Error Dataset and Vision–Language Model Benchmark for Report Error Correction

HiST: Spatial Transcriptomics Prediction via Multi-Level Hyperbolic Representation Learning

MedQ-Bench: Evaluating and Exploring Medical Low-level Visual Abilities in MLLMs

AGPD: Adaptive Guidance policy distillation for Imitation Learning

GeoSplat: A Deep Dive into Geometry-Constrained Gaussian Splatting

THE-Tree: Can Tracing Historical Evolution Enhance Scientific Verification and Reasoning?

MedITok: A Unified Tokenizer for Medical Image Synthesis and Interpretation

MORE: Multi-Frame Outdoor Point Cloud Registration with Temporal Memory Buffer

DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis

Farther Than Mirror: Explore Pattern-Compensated Depth of Mirror with Temporal Changes for Video Mirror Detection