Why do LLaVA Vision-Language Models Reply to Images in English?
Paper
•
2407.02333
•
Published
Flo Schneider
floschne
AI & ML interests
Large Vision-Language Models, Cross-modal Retrieval
Recent Activity
authored
a paper
about 15 hours ago
Why do LLaVA Vision-Language Models Reply to Images in English?
authored
a paper
about 15 hours ago
M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal
Models Across Multilingual and Multicultural Vision-Language Tasks
authored
a paper
about 15 hours ago
Multilingual and Explainable Text Detoxification with Parallel Corpora
Organizations
floschne's activity
authored
4
papers
about 15 hours ago
M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks
Paper
•
2407.03791
•
Published
•
1
Multilingual and Explainable Text Detoxification with Parallel Corpora
Paper
•
2412.11691
•
Published
Centurio: On Drivers of Multilingual Ability of Large Vision-Language Model
Paper
•
2501.05122
•
Published
•
15
liked
a
model
3 days ago
upvoted
a
collection
3 days ago
liked
a
Space
3 days ago
upvoted
a
paper
3 days ago
A bunch. of CUDA errors appearing in the wild
1
#5 opened 5 days ago
by
floschne
liked
a
model
5 days ago
liked
a
dataset
6 days ago
upvoted
a
paper
6 days ago
upvoted
a
collection
6 days ago
liked
a
model
10 days ago
upvoted
3
papers
23 days ago
File missing
2
#1 opened about 1 month ago
by
floschne
liked
a
dataset
about 1 month ago
reacted to
merve's
post with ❤️
about 1 month ago
Post
5600
This week in open-source AI was insane 🤠 A small recap🕺🏻
merve/dec-6-releases-67545caebe9fc4776faac0a3
Multimodal 🖼️
> Google shipped a PaliGemma 2, new iteration of PaliGemma with more sizes: 3B, 10B and 28B, with pre-trained and captioning variants 👏
> OpenGVLab released InternVL2, seven new vision LMs in different sizes, with sota checkpoint with MIT license ✨
> Qwen team at Alibaba released the base models of Qwen2VL models with 2B, 7B and 72B ckpts
LLMs 💬
> Meta released a new iteration of Llama 70B, Llama3.2-70B trained further
> EuroLLM-9B-Instruct is a new multilingual LLM for European languages with Apache 2.0 license 🔥
> Dataset: CohereForAI released GlobalMMLU, multilingual version of MMLU with 42 languages with Apache 2.0 license
> Dataset: QwQ-LongCoT-130K is a new dataset to train reasoning models
> Dataset: FineWeb2 just landed with multilinguality update! 🔥 nearly 8TB pretraining data in many languages!
Image/Video Generation 🖼️
> Tencent released HunyuanVideo, a new photorealistic video generation model
> OminiControl is a new editing/control framework for image generation models like Flux
Audio 🔊
> Indic-Parler-TTS is a new text2speech model made by community
Multimodal 🖼️
> Google shipped a PaliGemma 2, new iteration of PaliGemma with more sizes: 3B, 10B and 28B, with pre-trained and captioning variants 👏
> OpenGVLab released InternVL2, seven new vision LMs in different sizes, with sota checkpoint with MIT license ✨
> Qwen team at Alibaba released the base models of Qwen2VL models with 2B, 7B and 72B ckpts
LLMs 💬
> Meta released a new iteration of Llama 70B, Llama3.2-70B trained further
> EuroLLM-9B-Instruct is a new multilingual LLM for European languages with Apache 2.0 license 🔥
> Dataset: CohereForAI released GlobalMMLU, multilingual version of MMLU with 42 languages with Apache 2.0 license
> Dataset: QwQ-LongCoT-130K is a new dataset to train reasoning models
> Dataset: FineWeb2 just landed with multilinguality update! 🔥 nearly 8TB pretraining data in many languages!
Image/Video Generation 🖼️
> Tencent released HunyuanVideo, a new photorealistic video generation model
> OminiControl is a new editing/control framework for image generation models like Flux
Audio 🔊
> Indic-Parler-TTS is a new text2speech model made by community