Xiaohong Liu

Image Quality Assessment for Embodied AI

Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment

DIVA: Discrete Diffusion Vision-Language-Action Models for Parallelized Action Generation

Realtime Video Frame Interpolation using One-Step Diffusion Sampling

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning

RectiWeather: Photo-Realistic Adverse Weather Removal via Zero-shot Soft Weather Perception and Rectified Flow

RoboMonster: Compositional Generalization of Heterogeneous Multi-End Effector Embodied Agents

MLLM-Pruner: Efficient Activation-aware Pruning for Multimodal LLMs

CL-Gen: An Inference-Time Iterative Optimization Framework for Reference-Consistent Image Generation Based on Closed-Loop Control

LLM-IQA: Standard-guided MLLM for Mix-grained Image Quality Assessment

FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing

AnimateQR: Bridging Aesthetics and Functionality in Dynamic QR Code Generation

Improving Video Generation with Human Feedback

CMC-Bench: Towards a New Paradigm of Visual Signal Compression

AttentionNCE: Contrastive Learning with Instance Attention

A-Bench: Are LMMs Masters at Evaluating AI-generated Images?

Q-Bench-Video: Benchmarking the Video Quality Understanding of LMMs

R-Bench: Are your Large Multimodel Model Robust to Real-world Corruption?

Low-bit Quantization for Seeing in the Dark

Dog-IQA: Standard-guided Zero-shot MLLM for Mix-grained Image Quality Assessment

Exploring the Design Space of Autoregressive Models for Efficient and Scalable Image Generation

VT-PLUG: Integrating Visual Task Plugins with Unified Instruction Tuning