Tag: VLM - Chen Yulin's Blog

BAGEL-Unified-Multimodal-Pretraining

Posted 2026-02-06Updated 2026-04-16Review10 minutes read (About 1443 words)

BAGEL-Unified-Multimodal-Pretraining

论文链接 | 项目主页

#Research-paper Multi-modal VLM Diffusion Transformer MoE Unified-Multimodal FoundationModel Image-generation Image2Text

GR00T N1 An Open Foundation Model for Generalist Humanoid Robots

Posted 2026-02-02Updated 2026-04-16Review28 minutes read (About 4167 words)

GR00T N1 An Open Foundation Model for Generalist Humanoid Robots

论文链接 | NVIDIA, 2025

#Research-paper Multi-modal VLM Transformer FoundationModel Robotics DiffusionModel ImitationLearning RobotLearning VLA HumanoidRobot

Vision-Language Interpreter for Robot Task Planning

Posted 2025-04-16Updated 2026-04-16Notea few seconds read (About 3 words)

Vision-Language Interpreter for Robot Task Planning

#Research-paper Multi-modal VLM Robotics Embodied-AI Task-Planning

Pixtral 12B

Posted 2025-04-15Updated 2026-04-16Reviewa few seconds read (About 30 words)

Web: https://mistral.ai/news/pixtral-12b
Demo: https://chat.mistral.ai/chat
Finetune: https://github.com/2U1/Pixtral-Finetune
Model: https://huggingface.co/mistralai/Pixtral-12B-2409

#Research-paper Multi-modal VLM Transformer FoundationModel

ConceptGraphs= Open-Vocabulary 3D Scene Graphs for Perception and Planning

Posted 2025-03-19Updated 2026-04-16Reviewa few seconds read (About 42 words)

ConceptGraphs= Open-Vocabulary 3D Scene Graphs for Perception and Planning

通过LLM来判断位置关系，以此构建scene graph

#Research-paper VLM LLM Robotics Scene-graph 3D-Scene Embodied-AI Open-Vocabulary Task-Planning

From Pixels to Graphs= Open-Vocabulary Scene Graph Generation with Vision-Language Models

Posted 2025-03-13Updated 2026-04-16Reviewa few seconds read (About 6 words)

From Pixels to Graphs= Open-Vocabulary Scene Graph Generation with Vision-Language Models

#CV Research-paper Multi-modal VLM Scene-graph Visual-Relation Open-Vocabulary

OMG-LLaVA

Posted 2025-03-11Updated 2026-04-16Reviewa few seconds read (About 0 words)

#Research-paper Multi-modal VLM LLM

Scene-LLM

Posted 2025-02-15Updated 2026-04-16Review6 minutes read (About 919 words)

本文提出的模型主要想解决3D密集标注和交互式规划。
结合

#Research-paper Multi-modal VLM LLM Robotics CLIP 3D-Scene Embodied-AI