A collection of useful links on GenAI (and related) collected from the web.
For helping keep pace with advancements in GenAI and in general helping with the DSAN-6725 course contents.
Gen-AI • Others • Significant Papers • Contributing • License
While we live and breathe AI in this course, it is important to step back and reflect on something timeless, something that will not change with AI. Read this paper:
The Mundanity of Excellence: An Ethnographic Report on Stratification and Olympic Swimmers
This paper reminds us that excellence is not about talent or superhuman abilities. It is about doing small things consistently well. This applies to mastering AI just as much as it does to swimming.
- Required Reading: The Mundanity of Excellence
- Table of Contents
- Gen-AI
- Others
- Significant Papers
- Contributing
- License
| Category | Link | Description |
|---|---|---|
| GPU Optimization | https://x.com/Hesamation/status/2009012165123195342 | Robert Nishihara explains 5 GPU optimization methods while walking NYC streets in under 7 min |
| Category | Link | Description |
|---|---|---|
| LLM Basics | https://goyalpramod.github.io/blogs/Transformers_laid_out/ | Transformers explained (must read!) |
| LLM Basics | https://youtu.be/Axd50ew4pco | A short 4-minute video on CPU Vs GPU |
| LLM Basics | https://x.com/Hesamation/status/1875376552374104300 | Temperature and LLM sampling process visualized in Excel |
| LLM Basics | https://arxiv.org/pdf/2401.02038 | Paper: Understanding LLMs: A Comprehensive Overview from Training to Inference |
| LLM Basics | https://x.com/akshay_pachaar/status/1873345735250641173 | What are Mixture of Experts (MoE) |
| LLM Basics | https://newsletter.maartengrootendorst.com/p/a-visual-guide-to-mixture-of-experts | Visual introduction to Mixture-of-Experts |
| LLM Basics | https://x.com/Hesamation/status/1872050437312147499 | Calculating GPU memory for serving LLMs |
| LLM Basics | https://stackoverflow.blog/2023/11/09/an-intuitive-introduction-to-text-embeddings/ | Introduction to text embeddings |
| LLM Basics | https://arxiv.org/abs/2501.00663 | Paper on neural memory modules for improving long-term sequence retention |
| LLM Basics | https://x.com/Aurimas_Gr/status/1876635530302992875 | Discussion on practical applications of neural memory in LLMs |
| LLM Basics | https://poloclub.github.io/transformer-explainer/ | Interactive visualization tool explaining LLM Transformer architecture |
| LLM Basics | https://www.youtube.com/watch?v=h9Z4oGN89MU&t=663s | Exploring GPU Architecture |
| LLM Basics | https://arxiv.org/pdf/2501.09636 | Deployment of the mixture-of-experts mechanism in the stock investment domain |
| LLM Basics | https://github.com/vllm-project/aibrix/blob/main/docs/paper/AIBrix_White_Paper_0219_2025.pdf | Scalable, Cost Effective LLM Inference Infrastructure |
| LLM Basics | https://towardsdatascience.com/all-you-need-to-know-to-develop-using-large-language-models-5c45708156bc/ | Introduces key overviews of LLM development concepts |
| Category | Link | Description |
|---|---|---|
| RAG | https://piotr-jurowiec.medium.com/retrieval-augmented-generation-in-business-applications-enhancing-efficiency-and-innovation-3c3886c88705 | Article: Retrieval-Augmented Generation in Business Applications |
| RAG | https://arxiv.org/abs/2404.17723 | Paper: A Recent Study on RAG in NLP |
| RAG | https://arxiv.org/pdf/2005.11401 | Paper: Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks |
| RAG | https://arxiv.org/pdf/2401.15884 | Paper: Corrective Retrieval Augmented Generation |
| RAG | https://arxiv.org/html/2409.13731v3 | Paper: KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation |
| RAG | https://x.com/akshay_pachaar/status/1875520939536142656 | Traditional RAG Vs Graph RAG |
| RAG | https://www.dailydoseofds.com/p/traditional-rag-vs-hyde/ | Traditional RAG Vs HyDE |
| RAG | https://www.theunwindai.com/p/build-a-corrective-rag-agent | Build a corrective RAG application |
| RAG | https://x.com/Aurimas_Gr/status/1879148810158452777 | Challenges and components of production-grade RAG AI systems |
| RAG | https://x.com/akshay_pachaar/status/1879154648327811134 | Building a multi-tenant RAG app with easy integrations |
| RAG | https://x.com/akshay_pachaar/status/1878916141122462139 | MemoRAG enhances RAG with long-term memory capabilities |
| RAG | https://arxiv.org/pdf/2412.15605v1 | Cache-augmented generation (CAG) as an alternative to RAG |
| RAG | https://div.beehiiv.com/ | Great Blog Series on RAG, Agents, and Other Cutting-Edge Gen-AI Topics |
| RAG | https://www.anthropic.com/news/contextual-retrieval | Introducing Contextual Retrieval |
| RAG | [https://github.blog/ai-and-ml/generative-ai/what-is-retrieval-augmented-generation-and-what-does-it-do-for-generative-ai/] | Use of RAG in Gen AI |
| RAG | https://docs.llamaindex.ai/en/stable/ | LlamaIndex simplifies data integration for LLMs and enables efficient search for RAG applications. |
| RAG | https://aws.amazon.com/what-is/retrieval-augmented-generation/ | AWS Introduction to RAG |
| RAG | https://arxiv.org/pdf/2312.10997v3.pdf | Retrieval-Augmented Generation for Large Language Models: A Survey |
| RAG | https://medium.com/gitconnected/testing-18-rag-techniques-to-find-the-best-094d166af27f | Testing 18 RAG Techniques to Find the Best |
| Category | Link | Description |
|---|---|---|
| Agents | https://www.kaggle.com/whitepaper-agents | Google's whitepaper on Agents |
| Agents | https://medium.com/@goutham_nivass/agentic-workflow-amazon-bedrock-and-crewai-3a1a0597a2ce | Agentic Workflow: Amazon Bedrock and CrewAI |
| Agents | https://github.com/SamuelSchmidgall/AgentLaboratory | Autonomous LLM-driven research workflow for scientific projects |
| Agents | https://github.com/inferablehq | Open-source platform for building agentic automations |
| Agents | https://www.newsletter.swirlai.com/p/building-ai-agents-from-scratch-part | Guide to building AI agents from scratch |
| Agents | https://huyenchip.com//2025/01/07/agents.html | Overview of intelligent AI agents, tools, and planning |
| Agents | https://github.com/AgentOps-AI/agentops | Building, evaluating, monitoring, and benchmarking AI agents through dashboards |
| Agents | https://arxiv.org/pdf/2401.03568 | Agent AI: Surveying the Horizons of Multimodal Interaction |
| Agents | https://github.com/microsoft/AutoGen | Open-source library for building LLM agents. |
| Agents | https://github.com/huggingface/smolagents | Build agents with a simple framework with the logic for agents fitting in ~thousand lines of code |
| Agents | https://medium.com/@thomas.latterner/ai-agents-what-are-they-50ced8323b9a | Overview of AI Agents |
| Agents | https://www.letta.com/blog/ai-agents-stack | The Agents Stack |
| Agents | https://www.mongodb.com/pt-br/library/resources/ai-agents?x=inokiP | Demystifying AI Agents: A Guide for Beginners |
| Agents | https://arxiv.org/pdf/2308.08155 | AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation |
| Agents | [https://github.com/NVIDIA/GenerativeAIExamples/tree/main#end-to-end-rag-examples-and-notebooks] (https://github.com/NVIDIA/GenerativeAIExamples/tree/main#end-to-end-rag-examples-and-notebooks) | GenAI and Agents Examples with NVIDIA (TianluZhu) |
| Agents | https://developer.nvidia.com/blog/building-autonomous-vehicles-that-reason-with-nvidia-alpamayo/ | Generative VLA models for reasoning-based autonomous driving |
| Category | Link | Description |
|---|---|---|
| Guardrails | https://github.com/ShreyaR/guardrails | Python package for LLM filtering to prevent generating bad content |
| Guardrails | https://www.microsoft.com/en-us/ai/responsible-ai | Empowering responsible AI practices |
| Guardrails | https://www.mckinsey.com/featured-insights/mckinsey-explainers/what-are-ai-guardrails | Overview of guardrails: definition, utility, implementation ideas, deployment |
| Category | Link | Description |
|---|---|---|
| Benchmarking | https://magazine.sebastianraschka.com/p/ai-research-papers-2024-part-2 | Summary of influential AI research papers from 2024 |
| Category | Link | Description |
|---|---|---|
| Fine-tuning | https://docs.unsloth.ai/basics/tutorial-how-to-finetune-llama-3-and-use-in-ollama | Fine-tuning LLMs with Unsloth.ai |
| Fine-tuning | https://www.kaggle.com/code/iamleonie/fine-tuning-gemma-2-jpn-for-yomigana-with-lora | Fine-tuning Gemma 2 JPN for Yomigana using LoRA |
| Fine-tuning | https://www.youtube.com/watch?v=b80by3Xk_A8 | Stanford’s Hugging Face Transformers fine-tuning course |
| Fine-tuning | https://www.sciencedirect.com/science/article/pii/S0950584924001289 | Automating Fine-tuning of LLMs using Prompt Engineering Techniques |
| Fine-tuning | https://arxiv.org/abs/2310.00035 | Usage of LoRA for LLM fine-tuning |
| Fine-tuning | https://arxiv.org/abs/2502.06807 | Large reasoning models: Generalized vs Domain-specific |
| Fine-tuning | https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Llama3.1_(8B)-GRPO.ipynb | Using GRPO RL algorithm to train LLama-3.1 |
| Fine-tuning | https://huggingface.co/learn/cookbook/en/fine_tuning_code_llm_on_single_gpu | Fine-tuning a Code LLM on Custom Code on a single GPU |
| Category | Link | Description |
|---|---|---|
| Responsible AI | https://www.aisnakeoil.com/ | Debunking AI hype |
| Responsible AI | https://learn.microsoft.com/en-us/azure/machine-learning/concept-responsible-ai | Overview of Microsoft's Responsible AI framework |
| Responsible AI | https://oecd.ai/en/ai-principles | OECD AI Principles |
| Category | Link | Description |
|---|---|---|
| Apps | https://bi.new/ | Build live BI dashboards using Gen AI |
| Apps | https://github.com/patchy631/ai-engineering-hub | Code samples for RAG, Agents and everything LLM related |
| Apps | https://github.com/cyclotruc/gitingest | Turn any code based into a text ingest of its code |
| Apps | https://github.com/browser-use/browser-use | Make websites accessible to AI agents |
| Apps | https://www.linkedin.com/blog/engineering/ai/practical-text-to-sql-for-data-analytics | How LinkedIn built text-to-sql for data analytics |
| Apps | https://x.com/sharifshameem/status/1872880360922726667 | A vibe based book search engine app built with Claude |
| Apps | https://github.com/egoist/sitefetch | Tool for fetching and saving website content as text |
| Apps | https://data-people-group.github.io/blogs/2025/01/13/docwrangler/ | Interactive LLM-powered data processing with DocWrangler |
| Apps | https://github.com/CatchTheTornado/text-extract-api | IOCR API for document conversion to text/JSON |
| Apps | https://github.com/docsifyjs/docsify | Lightweight documentation site generator using Markdown |
| Apps | https://github.com/nanbingxyz/5ire | Cross-platform AI assistant with local knowledge base support |
| Apps | https://github.com/BuilderIO/gpt-crawler | Crawl a site to generate knowledge files |
| Apps | https://github.com/open-webui/open-webui | Open-source web UI for LLM, Ollama |
| Apps | https://github.com/comfyanonymous/ComfyUI | diffusion model GUI, api with a nodes interface |
| Apps | https://github.com/chatscope/chat-ui-kit-react | React-based chat UI kit for building LLM apps |
| Apps | https://link-springer-com.proxy.library.georgetown.edu/article/10.1007/s10639-024-12537-x | Using GPT to generate math word problems with difficulty levels |
| Category | Link | Description |
|---|---|---|
| Git | https://x.com/ChShersh/status/1875495972593131561 | A very short list of useful git commands |
| Python | https://www.dailydoseofds.com/p/pandas-vs-fireducks-performance-comparison/ | Pandas Vs Fireducks |
| Deepseek | https://github.com/deepseek-ai/DeepSeek-Coder | Open-source AI code generation model |
| Paper | Link | Description |
|---|---|---|
| Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation | Paper • GitHub | A training technique in Language Models to intensify their generalization ability |
| FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading | Paper | This paper mainly focuses on the financial domain, using LLMs as agents with gradient-driven RL policy optimization for autonomous decision-making. |
Fork this repo and submit a PR to contribute. Your PR should only contain your update to the relevant file in the community/ folder (e.g. community/spring-2026/README.md for the current semester). Do not include any other changes in the PR.
Follow these instructions while making contributions:
- Find the relevant semester folder in the
community/folder and add your contribution to theREADME.mdfile there. - Add your contribution as a line in the appropriate markdown table. Make sure to view the rendered file to confirm that the table formatting is not broken.
- Make sure that you put an appropriate value in the
Categoryfield and useful information in theDescriptionfield (the description should not exceed 10 words). - If you are using an existing
Categorythen add your line just after the last line in thatCategory's table. If you want to add a new category then create a new section for it similar to the other sections. - Prefer adding actionable content such as a code sample or a blog post with code. If you are adding a link to a paper then also include a link to its associated GitHub code repo.
This library is licensed under the MIT-0 License. See the LICENSE file.