💬 Prompt Engineering - hello · Scour

From Pixels to Prompts: Vision-Language Models 📱Edge AI

Hierarchical Prompting with Dual LLM Modules for Robotic Task and Motion Planning 🤖Robotics

Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs 🛡️AI Security

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs 📊Profile-Guided Optimization

From History to State: Constant-Context Skill Learning for LLM Agents 🛡️AI Security

Novelty-based Tree-of-Thought Search for LLM Reasoning and Planning 🔀Procedural Generation

Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs 🏗️MLIR

MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems ⚓Anchors

Plug-and-play Class-aware Knowledge Injection for Prompt Learning with Visual-Language Model 🎨Chroma

Steer Like the LLM: Activation Steering that Mimics Prompting 🌀Naiad

Relation Reasoning with LLMs in Expensive Optimization 🐻‍❄️Polars Lazy

When Prompts Interact: Assessing Prompt Arithmetic for Deconfounding under Distribution Shift ✏️Count-Min Sketch

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection 🛡️AI Security

How Many Iterations to Jailbreak? Dynamic Budget Allocation for Multi-Turn LLM Evaluation 🦙Ollama

MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents 🗺️Memory-Mapped Queues

Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning 🎲Deterministic Simulation

Elicitation Matters: How Prompts and Query Protocols Shape LLM Surrogates under Sparse Observations 🐻‍❄️Polars Lazy

Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning 📱Edge AI

Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMs 🌲CedarDB

Governed Metaprogramming for Intelligent Systems: Reclassifying Eval as a Governed Effec 🎭Program Synthesis

Log in to enable infinite scrolling