haoning-wu

A-Bench

[LMM + AIGC] What do we expect from LMMs as AIGI evaluators and how do they perform?

Co-Instruct

④[ECCV 2024, Comparison among Multiple Images!] A study on open-ended multi-image quality comparison: a dataset, a model and a benchmark.

haoning-wu.github.io

LongVideoBench

Official Dataloader and Evaluation Scripts for LongVideoBench.

Q-Align

③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.

haoning-wu/A-Bench

[LMM + AIGC] What do we expect from LMMs as AIGI evaluators and how do they perform?

haoning-wu/Co-Instruct

④[ECCV 2024, Comparison among Multiple Images!] A study on open-ended multi-image quality comparison: a dataset, a model and a benchmark.

haoning-wu/haoning-wu.github.io

haoning-wu/LongVideoBench

Official Dataloader and Evaluation Scripts for LongVideoBench.

haoning-wu/Q-Align

③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.