An Open-Source Engineering Guide for Prompt-in-context-learning from EgoAlpha Lab.
π Papers | β‘οΈ Playground | π Prompt Engineering | π ChatGPT Prompt ο½ β³ LLMs Usage Guide
βοΈ Shining βοΈ: This is fresh, daily-updated resources for in-context learning and prompt engineering. As Artificial General Intelligence (AGI) is approaching, let's take action and become a super learner so as to position ourselves at the forefront of this exciting era and strive for personal and professional greatness.
The resources include:
πPapersπ: The latest papers about In-Context Learning, Prompt Engineering, Agent, and Foundation Models.
πPlaygroundπ: Large language modelsοΌLLMsοΌthat enable prompt experimentation.
πPrompt Engineeringπ: Prompt techniques for leveraging large language models.
πChatGPT Promptπ: Prompt examples that can be applied in our work and daily lives.
πLLMs Usage Guideπ: The method for quickly getting started with large language models by using LangChain.
In the future, there will likely be two types of people on Earth (perhaps even on Mars, but that's a question for Musk):
- Those who enhance their abilities through the use of AIGC;
- Those whose jobs are replaced by AI automation.
πEgoAlpha: Hello! humanπ€, are you ready?
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration οΌNewοΌ
Published: 2026-05-19
Jiaqi Liu, Shi Qiu, Mairui Li, Bingzhou Li, Haonian Ji, Siwei Han, Xinyu Ye, Peng Xia, Zihan Dong, Congyu Zhang, Letian Zhang, Guiming Chen, Haoqin Tu, Xinyu Yang, Lu Feng, Xujiang Zhao, Haifeng Chen, - [arXiv]
Relit-LiVE: Relight Video by Jointly Learning Environment Video οΌNewοΌ
Published: 2026-05-07
Weiqing Xiao, Hong Li, Xiuyu Yang, Houyuan Chen, Wenyi Li, Tianqi Liu, Shaocong Xu, Chongjie Ye, Hao Zhao, Beibei Wang - [arXiv]
Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models οΌNewοΌ
Published: 2026-05-10
Yicheng Ji, Zhizhou Zhong, Jun Zhang, Qin Yang, XiTai Jin, Ying Qin, Wenhan Luo, Shuiyang Mao, Wei Liu, Huan Li - [arXiv]
Self-Distilled Agentic Reinforcement Learning οΌNewοΌ
Published: 2026-05-14
Zhengxi Lu, Zhiyuan Yao, Zhuowen Han, Zi-Han Wang, Jinyang Wu, Qi Gu, Xunliang Cai, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen - [arXiv]
MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents οΌNewοΌ
Published: 2026-05-12
Yining Chen, Jihao Zhao, Bo Tang, Haofen Wang, Yue Zhang, Fei Huang, Feiyu Xiong, Zhiyu Li - [arXiv]
π Complete history news π
You can directly click on the title to jump to the corresponding PDF link location
Motion meets Attention: Video Motion Prompts οΌ2024.07.03οΌ
Towards a Personal Health Large Language Model οΌ2024.06.10οΌ
Husky: A Unified, Open-Source Language Agent for Multi-Step Reasoning οΌ2024.06.10οΌ
Towards Lifelong Learning of Large Language Models: A Survey οΌ2024.06.10οΌ
Towards Semantic Equivalence of Tokenization in Multimodal LLM οΌ2024.06.07οΌ
LLMs Meet Multimodal Generation and Editing: A Survey οΌ2024.05.29οΌ
Tool Learning with Large Language Models: A Survey οΌ2024.05.28οΌ
When LLMs step into the 3D World: A Meta-Analysis of 3D Tasks via Multi-modal Large Language Models οΌ2024.05.16οΌ
Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach οΌ2024.04.24οΌ
A Survey on the Memory Mechanism of Large Language Model based Agents οΌ2024.04.21οΌ
πComplete paper list π for "Survey"π
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy οΌ2024.06.28οΌ
Dataset Size Recovery from LoRA Weights οΌ2024.06.27οΌ
Dual-Phase Accelerated Prompt Optimization οΌ2024.06.19οΌ
From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries οΌ2024.06.18οΌ
VoCo-LLaMA: Towards Vision Compression with Large Language Models οΌ2024.06.18οΌ
LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation οΌ2024.06.18οΌ
The Impact of Initialization on LoRA Finetuning Dynamics οΌ2024.06.12οΌ
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models οΌ2024.06.07οΌ
Cross-Context Backdoor Attacks against Graph Prompt Learning οΌ2024.05.28οΌ
Yuan 2.0-M32: Mixture of Experts with Attention Router οΌ2024.05.28οΌ
πComplete paper list π for "Prompt Design"π
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models οΌ2024.06.07οΌ
Cantor: Inspiring Multimodal Chain-of-Thought of MLLM οΌ2024.04.24οΌ
nicolay-r at SemEval-2024 Task 3: Using Flan-T5 for Reasoning Emotion Cause in Conversations with Chain-of-Thought on Emotion States οΌ2024.04.04οΌ
Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models οΌ2024.04.04οΌ
Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought οΌ2024.04.04οΌ
Visual CoT: Unleashing Chain-of-Thought Reasoning in Multi-Modal Language Models οΌ2024.03.25οΌ
A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science οΌ2024.03.21οΌ
NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning οΌ2024.03.12οΌ
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis οΌ2024.03.11οΌ
Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought οΌ2024.03.08οΌ
πComplete paper list π for "Chain of Thought"π
LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation οΌ2024.06.18οΌ
The Impact of Initialization on LoRA Finetuning Dynamics οΌ2024.06.12οΌ
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models οΌ2024.06.07οΌ
Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning οΌ2024.06.04οΌ
Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks οΌ2024.06.04οΌ
Long Context is Not Long at All: A Prospector of Long-Dependency Data for Large Language Models οΌ2024.05.28οΌ
Efficient Prompt Tuning by Multi-Space Projection and Prompt Fusion οΌ2024.05.19οΌ
MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning οΌ2024.05.19οΌ
Improving Diversity of Commonsense Generation by Large Language Models via In-Context Learning οΌ2024.04.25οΌ
Stronger Random Baselines for In-Context Learning οΌ2024.04.19οΌ
πComplete paper list π for "In-context Learning"π
Retrieval-Augmented Mixture of LoRA Experts for Uploadable Machine Learning οΌ2024.06.24οΌ
Enhancing RAG Systems: A Survey of Optimization Strategies for Performance and Scalability οΌ2024.06.04οΌ
Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training οΌ2024.05.31οΌ
Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection οΌ2024.05.25οΌ
DocReLM: Mastering Document Retrieval with Language Model οΌ2024.05.19οΌ
UniRAG: Universal Retrieval Augmentation for Multi-Modal Large Language Models οΌ2024.05.16οΌ
ChatHuman: Language-driven 3D Human Understanding with Retrieval-Augmented Tool Reasoning οΌ2024.05.07οΌ
REASONS: A benchmark for REtrieval and Automated citationS Of scieNtific Sentences using Public and Proprietary LLMs οΌ2024.05.03οΌ
Superposition Prompting: Improving and Accelerating Retrieval-Augmented Generation οΌ2024.04.10οΌ
Untangle the KNOT: Interweaving Conflicting Knowledge and Reasoning Skills in Large Language Models οΌ2024.04.04οΌ
πComplete paper list π for "Retrieval Augmented Generation"π
CELLO: Causal Evaluation of Large Vision-Language Models οΌ2024.06.27οΌ
PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation οΌ2024.06.26οΌ
Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models οΌ2024.06.24οΌ
OR-Bench: An Over-Refusal Benchmark for Large Language Models οΌ2024.05.31οΌ
TimeChara: Evaluating Point-in-Time Character Hallucination of Role-Playing Large Language Models οΌ2024.05.28οΌ
Subtle Biases Need Subtler Measures: Dual Metrics for Evaluating Representative and Affinity Bias in Large Language Models οΌ2024.05.23οΌ
HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models οΌ2024.05.16οΌ
Multimodal LLMs Struggle with Basic Visual Network Analysis: a VNA Benchmark οΌ2024.05.10οΌ
Vibe-Eval: A hard evaluation suite for measuring progress of multimodal language models οΌ2024.05.03οΌ
Causal Evaluation of Language Models οΌ2024.05.01οΌ
πComplete paper list π for "Evaluation & Reliability"π
Cooperative Multi-Agent Deep Reinforcement Learning Methods for UAV-aided Mobile Edge Computing Networks οΌ2024.07.03οΌ
Symbolic Learning Enables Self-Evolving Agents οΌ2024.06.26οΌ
Adversarial Attacks on Multimodal Agents οΌ2024.06.18οΌ
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning οΌ2024.06.14οΌ
Transforming Wearable Data into Health Insights using Large Language Model Agents οΌ2024.06.10οΌ
Neuromorphic dreaming: A pathway to efficient learning in artificial agents οΌ2024.05.24οΌ
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning οΌ2024.05.16οΌ
Learning Multi-Agent Communication from Graph Modeling Perspective οΌ2024.05.14οΌ
Smurfs: Leveraging Multiple Proficiency Agents with Context-Efficiency for Tool Planning οΌ2024.05.09οΌ
Unveiling Disparities in Web Task Handling Between Human and Web Agent οΌ2024.05.07οΌ
πComplete paper list π for "Agent"π
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output οΌ2024.07.03οΌ
LLaRA: Supercharging Robot Learning Data for Vision-Language Policy οΌ2024.06.28οΌ
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs οΌ2024.06.28οΌ
LLaVolta: Efficient Multi-modal Models via Stage-wise Visual Context Compression οΌ2024.06.28οΌ
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs οΌ2024.06.24οΌ
VoCo-LLaMA: Towards Vision Compression with Large Language Models οΌ2024.06.18οΌ
Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models οΌ2024.06.12οΌ
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models οΌ2024.06.07οΌ
Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning οΌ2024.06.04οΌ
DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models οΌ2024.05.31οΌ
πComplete paper list π for "Multimodal Prompt"π
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization οΌ2024.07.03οΌ
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs οΌ2024.06.28οΌ
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding οΌ2024.06.27οΌ
Adversarial Search Engine Optimization for Large Language Models οΌ2024.06.26οΌ
VideoLLM-online: Online Video Large Language Model for Streaming Video οΌ2024.06.17οΌ
Regularizing Hidden States Enables Learning Generalized Reward Model for LLMs οΌ2024.06.14οΌ
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation οΌ2024.06.10οΌ
Language models emulate certain cognitive profiles: An investigation of how predictability measures interact with individual differences οΌ2024.06.07οΌ
PaCE: Parsimonious Concept Engineering for Large Language Models οΌ2024.06.06οΌ
Yuan 2.0-M32: Mixture of Experts with Attention Router οΌ2024.05.28οΌ
πComplete paper list π for "Prompt Application"π
TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts οΌ2024.07.03οΌ
Pedestrian 3D Shape Understanding for Person Re-Identification via Multi-View Learning οΌ2024.07.01οΌ
Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs οΌ2024.06.28οΌ
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding οΌ2024.06.27οΌ
Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs? οΌ2024.06.27οΌ
Efficient World Models with Context-Aware Tokenization οΌ2024.06.27οΌ
The Remarkable Robustness of LLMs: Stages of Inference? οΌ2024.06.27οΌ
ResumeAtlas: Revisiting Resume Classification with Large-Scale Datasets and Large Language Models οΌ2024.06.26οΌ
AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation οΌ2024.06.18οΌ
Unveiling Encoder-Free Vision-Language Models οΌ2024.06.17οΌ
πComplete paper list π for "Foundation Models"π
Large language models (LLMs) are becoming a revolutionary technology that is shaping the development of our era. Developers can create applications that were previously only possible in our imaginations by building LLMs. However, using these LLMs often comes with certain technical barriers, and even at the introductory stage, people may be intimidated by cutting-edge technology: Do you have any questions like the following?
- β How can LLM be built using programming?
- β How can it be used and deployed in your own programs?
π‘ If there was a tutorial that could be accessible to all audiences, not just computer science professionals, it would provide detailed and comprehensive guidance to quickly get started and operate in a short amount of time, ultimately achieving the goal of being able to use LLMs flexibly and creatively to build the programs they envision. And now, just for you: the most detailed and comprehensive Langchain beginner's guide, sourced from the official langchain website but with further adjustments to the content, accompanied by the most detailed and annotated code examples, teaching code lines by line and sentence by sentence to all audiences.
Click πhereπ to take a quick tour of getting started with LLM.
This repo is maintained by EgoAlpha Lab. Questions and discussions are welcome via helloegoalpha@gmail.com.
We are willing to engage in discussions with friends from the academic and industrial communities, and explore the latest developments in prompt engineering and in-context learning together.
Thanks to the PhD students from EgoAlpha Lab and other workers who participated in this repo. We will improve the project in the follow-up period and maintain this community well. We also would like to express our sincere gratitude to the authors of the relevant resources. Your efforts have broadened our horizons and enabled us to perceive a more wonderful world.