Results for “convolutional-layers”

CogVLM: Visual Expert for Pretrained Language Models

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.

LoRA: Low-Rank Adaptation of Large Language Models

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

COCO: Microsoft COCO: Common Objects in Context

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

Towards Open-World Segmentation of Parts

Create production-quality landscape materials with the master-material + material-function + material-instance paradigm, RVT, and auto-layering. Use when the user asks for an auto/procedural landscape material, slope/altitude/distance-based layer blending, Runtime Virtual Textures, biome configuration via instances, or layer material functions. For basic layer-blend materials load landscape-materials.

Generate composited images from layers — solid colors, gradients, text, images, QR codes, barcodes, and layouts.

Create a layered CSS progressive blur (top or bottom) using multiple backdrop-filter masks for depth and softness. Use when asked for “progressive blur”, “gradient blur overlay”, or stepped blur masks that fade from an edge of the viewport.

PyTorch, TensorFlow, neural networks, CNNs, transformers, and deep learning for production

Create landscape materials with layer blending, texture setup, and layer info objects (LandscapeMaterialService). Use when the user asks to build a landscape/terrain material, set up paint layers (grass/rock/dirt), create layer info objects, add a grass output, or assign a material to a landscape. For production master-material+RVT systems, load landscape-auto-material.

GLaMM: Pixel Grounding Large Multimodal Model

Multimodal Learning with Transformers: A Survey

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.

Fine-tune Cosmos Reason video QA models using supervised fine-tuning with FSDP parallelism, including dataset preparation, spec construction, and AutoML support.

Guides feature extraction and preprocessing for time series data using aeon transformers, covering collection and series transformers with code examples.

A design system has three token layers, and conflating them is what makes systems

LongVA: Long Context Transfer from Language to Vision

Use when composing corner-anchored laser accents with thin beams, a bright emitter node, bloom, and atmospheric glow or fog. Prefer this over mengto-webgl-laser when lasers are layout corner ornaments, not a fixed full-screen WebGL beam.

Nocaps: Novel Object Captioning at Scale

Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Use for writing, reviewing, debugging, testing, or optimizing Python CVXPY optimization models. Trigger on Variable, Parameter, Expression, Constraint, Objective, Problem, DCP, DPP, DGP, DQCP, solver selection/status, dual values, mixed-integer, cone, or repeated parametric solves. Do not use for scipy.optimize-only, PyMC inference, symbolic algebra without optimization, or hand-written solver implementations.

Defines a vibrant claymation-meets-data design system for Clay.com, including color palette, typography, layout, and elevation tokens for GTM-data interfaces.

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

SNLI-VE: Visual Entailment Dataset

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

Use when building cursor-following spotlight reveals that expose a second aligned image through a soft radial mask—hover-to-color, before-and-after, x-ray, material, texture, product-detail, or illustrated heroes where a desaturated or embossed base stays visible while another treatment follows an eased pointer.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques for 1.5-3.6× speedup without quality loss.

SA-1B: Segment Anything 1 Billion Masks Dataset

Qdrant vector database — collections, upsert, search, filtering, payloads, sparse vectors, BM25

VS-Enhanced Qualitative Design Consultant with Ethnography & Action Research Enhanced VS 3-Phase process: Avoids overused phenomenology, proposes context-optimal qualitative strategies Absorbed H1 (Ethnographic Research Advisor) and H2 (Action Research Facilitator) capabilities Use when: selecting qualitative research design, planning phenomenology/grounded theory/case study/ethnography/action research Triggers: phenomenology, 현상학, grounded theory, 근거이론, case study, 사례연구, narrative inquiry, ethnography, 민족지, action research, 실행연구, qualitative design

Polishes existing motion against the transitions.dev motion-token scale by auditing duration, distance, scale, blur, and easing values and suggesting token-based corrections.