Yong Liu

LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment

GDI-Bench: A Benchmark for General Document Intelligence with Vision and Reasoning Decoupling

M3CoTBench: Benchmark Chain-of-Thought of MLLMs in Medical Image Understanding

MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments

RE-Searcher: Robust Agentic Search via Goal-oriented Planning and Self-reflection

Stochastic Gaussian Zeroth-Order Optimization: Improved Convergence Analysis under Skewed Hessian Spectra

Data-free VFX Self-Mining

X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible Controllability

AdaVideoRAG: Omni-Contextual Adaptive Retrieval-Augmented Efficient Long Video Understanding

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving

DuaRot: Dual Rotation for Advanced Outlier Mitigation in Rotated LLMs

A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection

DynaMind: Reasoning over Abstract Video Dynamics for Embodied Decision-Making

SparsitySolver: Efficient Reinforcement Learning-based Pruning for LLMs

The Advancement in Stochastic Zeroth-Order Optimization: Mechanism of Accelerated Convergence of Gaussian Direction on Objectives with Skewed Hessian Eigenvalues