Dongfu Jiang's picture

Dongfu Jiang

DongfuJiang

·

https://jdf-prog.github.io/

AI & ML interests

Large Language Model, Modality Reasoning and their evaluation

Recent Activity

updated a Space about 12 hours ago

TIGER-Lab/GenAI-Arena

updated a dataset 3 days ago

DongfuJiang/Big-Math-RL-Verified-CT

published a dataset 4 days ago

DongfuJiang/Big-Math-RL-Verified-CT

View all activity

Organizations

DongfuJiang's activity

New activity in TIGER-Lab/Mantis-Instruct 3 months ago

Dreamsim: "Here are there images"

#4 opened 4 months ago by

New activity in TIGER-Lab/Mantis-Instruct 5 months ago

fix typo

#3 opened 5 months ago by

New activity in mistral-community/pixtral-12b-240910 6 months ago

Any Inference code?

#6 opened 6 months ago by

New activity in TIGER-Lab/Mantis-8B-Idefics2 6 months ago

No Chat Template

#1 opened 8 months ago by

New activity in TIGER-Lab/Mantis-Instruct 7 months ago

No images in dvqa subset

#2 opened 7 months ago by

New activity in zero-gpu-explorers/README 9 months ago

Error initializing ZeroGPU: Unknown

#80 opened 9 months ago by

commented 3 papers 9 months ago

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

Paper • 2406.11833 • Published Jun 17, 2024 • 63 •

Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning

Paper • 2406.12742 • Published Jun 18, 2024 • 15 •

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

Paper • 2406.11833 • Published Jun 17, 2024 • 63 •

New activity in TIGER-Lab/Mantis-8B-siglip-llama3 10 months ago

GGUF Quants?

#1 opened 10 months ago by

commented a paper 10 months ago

MANTIS: Interleaved Multi-Image Instruction Tuning

Paper • 2405.01483 • Published May 2, 2024 • 6 •

New activity in Mantis-VL/llava_next_mistral_7b_4096 11 months ago

How to fine tune this model?

#1 opened 11 months ago by

New activity in TIGER-Lab/Mantis-llava-7b 11 months ago

Newer llava versions 1.6 with multi image training!

#1 opened 11 months ago by

New activity in Mantis-VL/MIQA_sample 11 months ago

How about considering Q-Bench-Pair?

#2 opened 11 months ago by

New activity in TIGER-Lab/TIGERScore-13B 12 months ago

Adding Evaluation Results

#4 opened about 1 year ago by

leaderboard-pr-bot

New activity in llava-hf/llava-v1.6-mistral-7b-hf 12 months ago

Will larger llava 1.6 version be also converted here?

#3 opened 12 months ago by

New activity in llm-blender/PairRM about 1 year ago

I wonder if there is any possibility that you can make your collected pairwise dataset open-source ?

#4 opened about 1 year ago by

Run model with transformers?

#2 opened about 1 year ago by

What's the difference between llm-blender/PairRM and llm-blender/pair-ranker?

#3 opened about 1 year ago by

New activity in TIGER-Lab/TIGERScore over 1 year ago

Update utils.py

#2 opened over 1 year ago by