tencent/Penguin-VL-8B
Text Generation • 9B • Updated • 5.83k • 70
Matteo Nulli
MatteoNulli
AI & ML interests
Vision Language Modelling, Multimodal Learning, Inference Optimization
Recent Activity
liked a model 9 days ago
tencent/Penguin-VL-8B upvoted a paper 9 days ago
Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports upvoted a paper 10 days ago
Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision EncodersOrganizations
liked a
model 9 days ago
upvoted a paper 9 days ago
upvoted a paper 10 days ago
upvoted an article 16 days ago
Article
Demystifying Multimodal Learning: The Hidden Inefficiency in Vision Language Modelling
•
4
published an article 16 days ago
Article
Demystifying Multimodal Learning: The Hidden Inefficiency in Vision Language Modelling
•
4
upvoted an article about 1 month ago
Article
Demystifying Multimodal Learning: Enabling Vision in Language Models
•
4
published an article about 1 month ago
Article
Demystifying Multimodal Learning: Enabling Vision in Language Models
•
4
authored a
paper about 1 month ago
commented 2
papers about 1 month ago
upvoted a paper about 1 month ago
submitted a
paper to Daily Papers about 1 month ago
authored 4
papers about 1 month ago
In-Context Learning Improves Compositional Understanding of Vision-Language Models
Paper • 2407.15487 • Published
Meeting SLOs, Slashing Hours: Automated Enterprise LLM Optimization with OptiKIT
Paper • 2601.20408 • Published • 1
Dynamic Vocabulary Pruning in Early-Exit LLMs
Paper • 2410.18952 • Published
'Explaining RL Decisions with Trajectories': A Reproducibility Study
Paper • 2411.07200 • Published
upvoted 2
papers about 1 month ago
upvoted a collection about 2 months ago
upvoted a paper 5 months ago