Results for “in-context-learning”

Emu2: Generative Multimodal Models are In-Context Learners

Place trusted contextual information into prompts or agent state using explicit boundaries, provenance, and templates. Use when relevant context has already been selected and must be inserted safely; use context-retrieval to find it or context-optimization to choose and order it.

Build students' capacity to place historical documents in their temporal and social context. Use when students read sources without considering what was happening at the time, or know the context but don't deploy it.

Diagnose and mitigate context degradation patterns including lost-in-middle failures, context poisoning, distraction, confusion, and clash in AI agent systems.

当需要深化对某个主题的理解、检验知识掌握程度或克服“冒名顶替综合征”时

Provides guidance for training Mixture-of-Experts models with long context windows, covering context parallelism sizing, selective recomputation, dispatcher choices, and practical patterns from recent experiments.

LongVA: Long Context Transfer from Language to Vision

COCO: Microsoft COCO: Common Objects in Context

Extends effective context capacity through strategic compression, masking, caching, and partitioning techniques.

Retrieve relevant information from a knowledge base using semantic, keyword, or hybrid search to ground a query. Use when the task starts with a corpus or index that must be searched; use context-ranking when candidate chunks already exist and only need ordering.

Use when context window is filling up, sessions are getting slow, or you need to preserve state across sessions. For context compression, state snapshots, search-first discipline, and cross-session memory management.

Build the smallest, highest-signal context package for an AI coding task — goal, constraints, repo facts, boundaries, and a verification plan. Load when prompts are underspecified, the agent is missing key files or decisions, the user says "use the right context", "here's the repo", or when work is drifting due to missing constraints. Also triggers on "context engineering", "gather context", "what do you need from me", "before you start". Not for cross-session continuity (use memory-startup/memory-recall).

Capture and maintain a foundational marketing context document covering positioning, messaging, brand voice, target audience, and competitive landscape for consistent use across marketing skills.

Breaks down current state, context, user input, and data into a structured assessment before taking action.

Install and configure Acontext, a memory layer for AI agents that provides persistent sessions, file storage, and skill management.

Rank an existing set of context chunks by relevance, diversity, freshness, and utility. Use when retrieval has already produced candidates that must be scored or reranked; use context-retrieval when the source corpus still needs to be searched.

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.

One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Diagnose whether an AI workflow suffers from context stuffing or benefits from context engineering, and apply structured techniques to improve reliability.

Use this skill for context gathering, file triage, source maps, assumptions, task framing, prompt hygiene. Trigger when the task involves programming work related to Context Engineering, production implementation, audits, debugging, strategy, or validation.

Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.md. Use when discussing learnings, corrections, or when the user mentions remembering something. Trigger with phrases like "remember this", "don't forget", "use X not Y", or "actually...".

Design a learning sequence teaching prompt quality — comparing vague vs. refined prompts to show why specificity and context transform AI output. Use when students use AI without understanding why output quality varies.

Provides structured guidance for building production-grade AI agent systems through context engineering, covering fundamentals, architectural patterns, operational excellence, and evaluation.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Diverga Memory System v7.0 - Context-persistent research support with checkpoint auto-trigger and cross-session continuity. Triggers: memory, remember, context, recall, checkpoint, decision, persist, 기억, 맥락, 세션, 체크포인트

Design metacognitive checkpoints that prevent AI-assisted learning from bypassing genuine understanding. Use when students use AI tools and may overestimate their own comprehension.

Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task. Use when developing students' thinking-about-thinking during independent work.

LLaVA-NeXT: Improved Reasoning, OCR, and World Knowledge

Mantis: Interleaved Multi-Image Instruction Tuning

Manage and compress conversation context in long sessions. Detect when context is growing large, summarize completed work phases, archive old findings while preserving key decisions. Prevents context degradation.

Optimize a complete candidate context package by deduplicating, filtering, ordering, and allocating its token budget. Use when retrieved or assembled material is noisy or exceeds the useful context budget; use context-ranking for scoring chunks and context-compression for shrinking selected content.

Map a current event below the surface into patterns, structures, and mental models. Use when a class or team needs systemic understanding before action.