4 49

Maxim Kurkin

dondosss

Fr0do

AI & ML interests

Multimodal AI, CV, NLP

Recent Activity

upvoted a paper 2 days ago

The Differences Between Direct Alignment Algorithms are a Blur

upvoted a collection 12 days ago

Qwen2.5-VL

upvoted a paper 27 days ago

Scaling Laws for Floating Point Quantization Training

View all activity

Organizations

dondosss's activity

upvoted a paper 2 days ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published 4 days ago • 108

upvoted a collection 12 days ago

Qwen2.5-VL

Collection

Vision-language model series based on Qwen2.5 • 3 items • Updated 11 days ago • 324

upvoted a paper 27 days ago

Scaling Laws for Floating Point Quantization Training

Paper • 2501.02423 • Published Jan 5 • 26

upvoted a paper about 1 month ago

3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding

Paper • 2412.18450 • Published Dec 24, 2024 • 33

upvoted 2 papers 2 months ago

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published Dec 4, 2024 • 126

ChatRex: Taming Multimodal LLM for Joint Perception and Understanding

Paper • 2411.18363 • Published Nov 27, 2024 • 10

upvoted 3 papers 3 months ago

PPLLaVA: Varied Video Sequence Understanding With Prompt Guidance

Paper • 2411.02327 • Published Nov 4, 2024 • 11

WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

Paper • 2411.02337 • Published Nov 4, 2024 • 35

Inference Optimal VLMs Need Only One Visual Token but Larger Models

Paper • 2411.03312 • Published Nov 5, 2024 • 6

updated a model 4 months ago

dondosss/minicpm-ground

Updated Sep 26, 2024

New activity in Salesforce/blip3-ocr-200m 5 months ago

Extremely low quality of data

#1 opened 5 months ago by

dondosss

New activity in Salesforce/blip3-grounding-50m 5 months ago

Extremely low quality of data

#3 opened 5 months ago by

dondosss

upvoted 2 papers 5 months ago

Building and better understanding vision-language models: insights and future directions

Paper • 2408.12637 • Published Aug 22, 2024 • 125

Wavelets Are All You Need for Autoregressive Image Generation

Paper • 2406.19997 • Published Jun 28, 2024 • 30

upvoted 5 papers 6 months ago

Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents

Paper • 2408.07060 • Published Aug 13, 2024 • 42

Medical SAM 2: Segment medical images as video via Segment Anything Model 2

Paper • 2408.00874 • Published Aug 1, 2024 • 48

upvoted a paper 7 months ago

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

Paper • 2403.14520 • Published Mar 21, 2024 • 34