Results for “visual-differentiation”

Evaluates text-to-image models on spatial relationship accuracy using the VISOR metric, separating object detection from spatial correctness to reveal biases like object priority and merging.

Skeptical pushback on visual placement — both density and quality. Reads the annotated outline plus the visuals manifest and asks (a) whether the article hits the density target from editorial-principles-visuals.md, (b) whether each [VISUAL:...] earns its place, (c) whether sections without one would benefit. One revision pass on FAIL (BLOG_AGENT_VISUALS_REVISION_BUDGET, default 1).

COCO: Microsoft COCO: Common Objects in Context

Masked Autoencoders Are Scalable Vision Learners

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

Flamingo: A Visual Language Model for Few-Shot Learning

Structured visual QA verdict for screenshot-to-reference comparisons

NLVR2: A Visual Reasoning Benchmark for Natural Language

Establish clear visual hierarchy through size, weight, color, spacing, and positioning to guide users through interfaces.

Towards Open-World Segmentation of Parts

Mantém a coerência visual entre peças geradas por IA usando modelo fixo, prompt base, seed e referência de estilo, com teste de coerência e biblioteca de prompts.

VILA: On Pre-training for Visual Language Models

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

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Trains, evaluates, exports, and runs inference for Visual ChangeNet models used in AOI defect detection, comparing image pairs for PASS/NO_PASS classification or change-segmentation masks.

Identifies the weakest samples per ground-truth label in NVIDIA TAO VCN Classify experiments by running a Docker container that performs threshold sweep, weakness scoring, and per-lighting expansion, then surfaces top-K weak samples for downstream augmentation or relabeling.

SNLI-VE: Visual Entailment Dataset

Open-Vocabulary Object Detection Using Captions

Mosaic Augmentation for Detection and Segmentation

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.

Nocaps: Novel Object Captioning at Scale

Multimodal Few-Shot Learning with Frozen Language Models

VS-Enhanced Theoretical Framework Architect with Critique & Visualization Full VS 5-Phase process: Modal theory avoidance, Long-tail exploration, differentiated framework presentation Absorbed A3 (Devil's Advocate) critique and A6 (Conceptual Framework Visualizer) capabilities Use when: building theoretical foundations, designing conceptual models, deriving hypotheses, critiquing frameworks, visualizing models Triggers: theoretical framework, 이론적 프레임워크, conceptual model, 개념적 모형, hypothesis derivation, critique, devil's advocate, 반론, visualization, diagram

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.

This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.

Expert real-time VFX artist specializing in particle systems, shader effects, and the invisible craft that makes games feel satisfying. Masters Niagara, VFX Graph, Godot GPU particles, and understands the AAA principles that make effects read clearly at 60fps. Use when "particle system, visual effects, vfx, particles, niagara, vfx graph, flipbook, sprite sheet, explosion effect, magic effect, trail effect, beam effect, dissolve, distortion, force field, hit effect, muzzle flash, impact effect, smoke particles, fire effect, soft particles, game juice, screen shake, particle overdraw, effect optimization, vfx, particles, effects, niagara, vfx-graph, game-juice, visual-effects, shaders, flipbook, trails, beams, explosions, optimization, gpu-particles" mentioned.

Visual Instruction Tuning

LongVA: Long Context Transfer from Language to Vision

Grit: General Robust Image Task Benchmark

Measures distributional similarity between original GAN-generated images and their semantically manipulated counterparts using the Fréchet Inception Distance (FID) metric.

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

BPPV Differential Diagnosis Checker

画像を理解（被写体・テキストOCR・構図・色・UI構造の分析）し、結果を構造化して返すスキル。CC CLI は GLM-5.3 等の vision 非対応モデルで稼働中のため画像を直接視認できず、主ルート Gemini 2.5 Flash（scripts/api/gemini_vision.py・無料枠）と副ルート 4_5v MCP（analyze_image・Readが返すCDN URL）の2経路で分析し、CCは結果の構造化・比較・保存に専任する。 ユーザーが「画像見て」「この画像何が写ってる」「画像比較して」「スクショ見て」「画像分析して」「画像理解」「vision-analyze」と言った時、または /vision-analyze を呼んだ時にトリガー。 ※画像生成（image generation）は対象外（make-song / video-prompt-spec / demo-site-sales参照）。ピクセル修正（花鈿除去等）は remove-huadian の役割。楽曲分析は analyze-song / reverse-engineer-song。

Structured visual QA verdict for screenshot-to-reference comparisons

Design clear, accessible data visualizations with appropriate chart selection and styling.