emanuelevivoli (Emanuele Vivoli)

upvoted a paper 5 days ago

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss

Paper • 2410.17243 • Published 9 days ago • 81

upvoted a paper 7 days ago

xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs

Paper • 2410.16267 • Published 10 days ago • 14

upvoted a paper 9 days ago

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

Paper • 2410.16153 • Published 10 days ago • 42

upvoted 6 collections 11 days ago

upvoted 2 papers 15 days ago

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

Paper • 2410.10563 • Published 17 days ago • 35

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Paper • 2410.10306 • Published 17 days ago • 49

upvoted a paper 16 days ago

Baichuan-Omni Technical Report

Paper • 2410.08565 • Published 20 days ago • 82

upvoted 2 papers 20 days ago

Personalized Visual Instruction Tuning

Paper • 2410.07113 • Published 22 days ago • 69

Falcon Mamba: The First Competitive Attention-free 7B Language Model

Paper • 2410.05355 • Published 24 days ago • 26

upvoted a paper 29 days ago

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Paper • 2409.20566 • Published about 1 month ago • 51

upvoted a paper about 1 month ago

ComiCap: A VLMs pipeline for dense captioning of Comic Panels

Paper • 2409.16159 • Published Sep 24 • 1

upvoted 3 articles about 1 month ago

Article

Deprecation of Git Authentication using password

Aug 25, 2023

• 17

Article

Llama can now see and run on your device - welcome Llama 3.2

Sep 25

• 157

Article

Scaling robotics datasets with video encoding

Aug 27

• 34

upvoted a paper about 1 month ago

Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models

Paper • 2408.02442 • Published Aug 5 • 19

Emanuele Vivoli

AI & ML interests

Organizations

emanuelevivoli's activity

Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss

xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs

Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages

Comics Understanding

LLaVA-Video

🍷 FineWeb datasets

Phi-3

NVLM 1.0

Molmo

MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks

Animate-X: Universal Character Image Animation with Enhanced Motion Representation

Baichuan-Omni Technical Report

Personalized Visual Instruction Tuning

Falcon Mamba: The First Competitive Attention-free 7B Language Model

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

ComiCap: A VLMs pipeline for dense captioning of Comic Panels

Deprecation of Git Authentication using password

Llama can now see and run on your device - welcome Llama 3.2

Scaling robotics datasets with video encoding

Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models