2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
Paper
β’
2501.00958
β’
Published
β’
109
VLM ποΈποΈ
-
-
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
Paper β’ 2412.19723 β’ Published β’ 87 -
VisionZip: Longer is Better but Not Necessary in Vision Language Models
Paper β’ 2412.04467 β’ Published β’ 117 -
PaliGemma 2: A Family of Versatile VLMs for Transfer
Paper β’ 2412.03555 β’ Published β’ 133 -
ShowUI: One Vision-Language-Action Model for GUI Visual Agent
Paper β’ 2411.17465 β’ Published β’ 89 -
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
Paper β’ 2501.04003 β’ Published β’ 27 -
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
Paper β’ 2501.00599 β’ Published β’ 46 -
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs
Paper β’ 2501.06186 β’ Published β’ 65 -
DRIVINGVQA: Analyzing Visual Chain-of-Thought Reasoning of Vision Language Models in Real-World Scenarios with Driving Theory Tests
Paper β’ 2501.04671 β’ Published -
The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
Paper β’ 2502.03628 β’ Published β’ 12 -
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper β’ 2502.14786 β’ Published β’ 157 -
Qwen2.5-VL Technical Report
Paper β’ 2502.13923 β’ Published β’ 212