Главная
Study mode:
on
You
History
Saved
In progress 0 courses
compleat 0 courses
#Art & Design #Adobe #ChatGPT #GitHub

#Vision-Language Models

Showing: 20 courses
OpenSource Connections

Vision Language Models and PDFs: What You See Is What You Search - Haystack EU 2024

0 rewiews
Explore ColPali, a novel retrieval model using Vision Language Models to embed entire PDF pages, improving retrieval quality and simplifying extraction processes for complex document formats.
Add to list
1 Lesons
45 minutes
On-Demand
Free-Video
Launchpad

LLaRA: Supercharging Robot Learning Data for Vision-Language Policy

0 rewiews
Enhance robotic decision-making using LLMs and VLMs. Learn to formulate actions as conversation pairs and incorporate auxiliary data for improved performance in simulated and real-world tasks.
Add to list
1 Lesons
16 minutes
On-Demand
Free-Video
Montreal Robotics

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

0 rewiews
Explore vision-language-action models for robotic control, enhancing generalization and semantic reasoning through Internet-scale data integration and end-to-end training.
Add to list
1 Lesons
1 hour 11 minutes
On-Demand
Free-Video
Discover AI

Robotics Transformer 2 (RT-2) - Vision-Language Models for Advanced Robotics

0 rewiews
Explore how RT-2 combines Vision-Language Models with robotics, enabling advanced control systems and improved generalization through web-scale pre-training and specialized datasets.
Add to list
1 Lesons
28 minutes
On-Demand
Free-Video
Discover AI

ColPALI: Efficient Document Retrieval Using Vision Language Models for RAG Systems

0 rewiews
Discover how ColPALI revolutionizes document retrieval by using Vision Language Models to efficiently process and retrieve visually rich documents without OCR, enhancing RAG systems performance.
Add to list
1 Lesons
28 minutes
On-Demand
Free-Video
Discover AI

BLIP-2: Connecting Vision-Language Models with Q-Former for Image Chat

0 rewiews
Explore BLIP-2's innovative approach to combining vision and language models through Q-Former, enabling advanced image-based conversations and multimodal AI interactions.
Add to list
1 Lesons
13 minutes
On-Demand
Free-Video
Discover AI

Fine-tuning Vision Language Models with PaLiGemma-3B - A Practical Guide

0 rewiews
Master fine-tuning techniques for Vision Language Models using PyTorch and JAX FLAX, with practical examples for PaliGemma-3B implementation on free compute platforms like Google Colab and Vertex AI.
Add to list
1 Lesons
14 minutes
On-Demand
Free-Video
USC Information Sciences Institute

Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks

0 rewiews
Explore a unified neural model for diverse AI tasks, including computer vision, image synthesis, and NLP. Learn about its innovative approach to homogenizing inputs and outputs across multiple domains.
Add to list
19 Lesons
49 minutes
On-Demand
Free-Video
Roboflow

Fine-tuning PaliGemma for Custom Object Detection

0 rewiews
Step-by-step guide to fine-tune PaliGemma for custom object detection, covering setup, dataset preparation, training, evaluation, and deployment. Includes practical tips and important considerations.
Add to list
10 Lesons
21 minutes
On-Demand
Free-Video
Sam Witteveen

Florence-2: The Best Small Vision Language Model - Capabilities and Demo

0 rewiews
Explore Florence-2, a powerful new Vision Language Model capable of detailed image captioning, visual grounding, and open vocabulary detection, with demonstrations and practical usage examples.
Add to list
9 Lesons
14 minutes
On-Demand
Free-Video
Nerdy Rodent

New Flux IMG2IMG Trick, Upscaling Options, and Prompt Ideas in ComfyUI

0 rewiews
Explore advanced ComfyUI techniques: Flux IMG2IMG trick, upscaling options, and creative prompt ideas. Enhance your AI image generation skills with practical demonstrations and workflows.
Add to list
4 Lesons
23 minutes
On-Demand
Free-Video
Discover AI

Understanding Task Vectors in Vision-Language Models - Cross-Modal Representations

0 rewiews
Explore how Vision-Language Models create task vectors - internal representations enabling cross-modal performance through text and images, revolutionizing AI's ability to understand and execute diverse tasks.
Add to list
1 Lesons
23 minutes
On-Demand
Free-Video
Discover AI

Layer Increasing Network Scaling (LiNeS) - Preventing Catastrophic Forgetting in Language Models

0 rewiews
Explore LiNeS, a novel post-training layer scaling technique that prevents catastrophic forgetting in large language models while enhancing multi-task performance and model merging capabilities.
Add to list
9 Lesons
21 minutes
On-Demand
Free-Video
SK AI SUMMIT 2024

Vision-Language Model을 활용한 Vision Data Asset 구축 - AI 이미지 이해와 데이터 관리

0 rewiews
Discover how SKT builds and manages 100TB of vision data assets using Vision-Language Models, standardizing fragmented data for enhanced AI services and efficient situation recognition in CCTV systems.
Add to list
1 Lesons
31 minutes
On-Demand
Free-Video
Paul G. Allen School

Beyond Rules and Rewards: From Pixels to Adaptive Policies Through Imitation, Reinforcement, and Multimodal Learning

0 rewiews
Explore advanced robotic learning methodologies, from imitation-based training to multimodal systems, focusing on adaptive policies and vision-language models for enhanced real-world robot interactions.
Add to list
1 Lesons
59 minutes
On-Demand
Free-Video
Simons Institute

Understanding and Steering Generative AI Systems

0 rewiews
Explore techniques for analyzing and directing AI systems' behavior, focusing on tools to identify patterns, improve accuracy, and enhance truthfulness in language and vision models.
Add to list
1 Lesons
1 hour 4 minutes
On-Demand
Free-Video
HuggingFace

OpenVLA: An Open-Source Vision-Language-Action Model - Research Presentation

0 rewiews
Explore OpenVLA, an open-source vision-language-action model, in this research presentation by Moo Jin Kim. Learn about cutting-edge developments in AI that integrate visual, linguistic, and action-based learning.
Add to list
1 Lesons
1 hour 19 minutes
On-Demand
Free-Video
Discover AI

Knowledge-Adapted Fine-Tuning for Medical Vision Language Models

0 rewiews
Explore how Knowledge-Adapted Fine-Tuning (KnowAda) improves vision-language models in medical AI, reducing hallucinations while maintaining accurate image descriptions and diagnostic capabilities.
Add to list
10 Lesons
26 minutes
On-Demand
Free-Video
Nvidia

Deploying Generative AI Applications - Building Code Assistants, Image Search, and Robotics Solutions

0 rewiews
Discover practical implementations of LLMs through hands-on demonstrations of image search applications, coding assistance tools, and vision-language action models for robotics integration.
Add to list
1 Lesons
11 minutes
On-Demand
Free-Video
Discover AI

Fourier-Enhanced Fine-Tuning Vision Language Models Using PEFT-VFPT

0 rewiews
Discover how Visual Fourier Prompt Tuning revolutionizes vision model fine-tuning by integrating Fast Fourier Transform, enhancing adaptability and accuracy while using minimal trainable parameters.
Add to list
1 Lesons
27 minutes
On-Demand
Free-Video