arxiv:2404.06212
Maxim Kurkin
dondosss
AI & ML interests
Multimodal AI, CV, NLP
Recent Activity
upvoted
a
paper
17 days ago
PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance
upvoted
a
paper
17 days ago
Inference Optimal VLMs Need Only One Visual Token but Larger Models
Organizations
Papers
1
models
9
dondosss/minicpm-ground
Updated
dondosss/mit-b0-scene-parse-135-lora
Updated
dondosss/tiny-random-idefics2
Feature Extraction
•
Updated
•
1
dondosss/rubert-finetuned-ner
Token Classification
•
Updated
•
38
dondosss/mit-b0-scene-parse-1800-lora
Updated
dondosss/segformer-b0-finetuned-ade-512-512-scene-parse-1800-lora
Updated
dondosss/segformer-b0-finetuned-ade-512-512-scene-parse-450-lora
Updated
dondosss/segformer-b0-finetuned-ade-512-512-scene-parse-4500-lora
Updated
dondosss/segformer-b5-finetuned-ade-640-640-scene-parse-4500-lora
Updated
datasets
None public yet