Results for “vision-model”

Scaling Vision with Sparse Mixture of Experts

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

CogVLM: Visual Expert for Pretrained Language Models

ImageNet: A Large-Scale Hierarchical Image Database

Build .NET MVVM ViewModels with CommunityToolkit.Mvvm source generators, base classes, and commands for WPF, WinUI, MAUI, Uno, and Avalonia.

Enables decoupled pub/sub messaging between ViewModels using CommunityToolkit.Mvvm Messenger, covering weak/strong references, request/reply patterns, channel tokens, and lifecycle management.

COCO: Microsoft COCO: Common Objects in Context

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Advanced Optics Modeling Skill

Masked Autoencoders Are Scalable Vision Learners

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

Chameleon: Mixed-Modal Early-Fusion Foundation Models

当需要为某个生活领域或项目确立一个初步的、可迭代的积极方向时

Nocaps: Novel Object Captioning at Scale

Apply MVVM, Coordinators, and Clean Architecture (VIP/VIPER) in iOS apps. Use when applying MVVM, Coordinators, or VIP/VIPER architecture in iOS apps.

LongVA: Long Context Transfer from Language to Vision

NLVR2: A Visual Reasoning Benchmark for Natural Language

Scaling Vision Transformers to 22 Billion Parameters

Applied Optics Modeling Skill

Mental models and decision frameworks for building autonomous agents that continuously learn, explore, and accumulate skills in open-ended environments without human supervision

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when asked to "think bigger", "expand scope", "strategy review", "rethink this", or "is this ambitious enough". Proactively suggest when the user is questioning scope or ambition of a plan, or when the plan feels like it could be thinking bigger. (gstack)

Towards Open-World Segmentation of Parts

OpenCLIP: An Open Source Implementation of CLIP

VILA: On Pre-training for Visual Language Models

Vision-language chat: VQA, captioning, image dialogue.

Build a visual sequence that proves, explains, and supports decisions.

GLIP: Grounded Language-Image Pre-training

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Run state-of-the-art machine learning models directly in JavaScript/TypeScript across browsers and server-side runtimes using Transformers.js.