Flo Schneider's picture

Flo Schneider

floschne

·

https://www.inf.uni-hamburg.de/en/inst/ab/lt/people/florian-schneider.html

AI & ML interests

Large Vision-Language Models, Cross-modal Retrieval

Recent Activity

authored a paper 1 day ago

Why do LLaVA Vision-Language Models Reply to Images in English?

authored a paper 1 day ago

M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks

authored a paper 1 day ago

Multilingual and Explainable Text Detoxification with Parallel Corpora

View all activity

Organizations

floschne's activity

New activity in google/paligemma2-3b-pt-896 6 days ago

A bunch. of CUDA errors appearing in the wild

#5 opened 6 days ago by

New activity in maya-multimodal/maya about 1 month ago

File missing

#1 opened about 1 month ago by

New activity in neulab/PangeaBench-xmmmu 3 months ago

Issues when downloading the dataset

#1 opened 3 months ago by

New activity in MBZUAI/PALO-13B 7 months ago

Question regarding the Stage 1 training procedure

#1 opened 7 months ago by

New activity in floschne/xgqa 8 months ago

Librarian Bot: Add language metadata for dataset

#1 opened 8 months ago by

New activity in HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit 9 months ago

What processor to use?

#4 opened 9 months ago by

New activity in OpenGVLab/InternVL-Chat-V1-1 9 months ago

Which exact version of Llama 2 was used?

#1 opened 9 months ago by

New activity in llava-hf/bakLlava-v1-hf 10 months ago

Which Vision Encoder was used here?

#9 opened 10 months ago by

Training data details

#8 opened 10 months ago by

New activity in llava-hf/vip-llava-7b-hf 11 months ago

What does VIP stand for?

#1 opened 11 months ago by

RuntimeError: Error(s) in loading state_dict for LlavaForConditionalGeneration

#2 opened 11 months ago by

New activity in llava-hf/llava-1.5-7b-hf about 1 year ago

Why is `beam_search` not enabled in the samples?

#10 opened about 1 year ago by

New activity in M-CLIP/XLM-Roberta-Large-Vit-B-16Plus almost 2 years ago

Slow inference

#3 opened almost 2 years ago by