Weisi Lin

Image Quality Assessment for Embodied AI

BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion

Skeleton-to-Image Encoding: Enabling Skeleton Representation Learning via Vision-Pretrained Models

AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment

OmniQuality-R: Advancing Reward Models through All-Encompassing Quality Assessment

Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression

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

BADiff: Bandwidth Adaptive Diffusion Model

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

Distribution-Aware Diffusion Model Quantization via Distortion Minimization

Robust-PIFu: Robust Pixel-aligned Implicit Function for 3D Human Digitalization from a Single Image

Q-Adapt: Adapting LMM for Visual Quality Perceiver with Progressive Instruction Tuning

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

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

DM3D: Parameter-Efficient and Lossless 3D Object Detection via Distortion Minimization