LLM-reading-group

KO | EN

gitlite — search

#javascript #python #typescript #go #golang #android #rust #linux #java #nodejs #kubernetes #pytorch #security #ios

LLM-reading-group

(★ 42)

LLM reading group discussed at Houston Machine Learning Meetup

LLM-reading-group Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# LLM reading group
LLM reading group discussed at [Houston Machine Learning Meetup](https://www.meetup.com/houston-machine-learning/?eventOrigin=event_home_page)

## Agentic AI use cases
- Inside Claude Code: What Source Codes Revealed. [blog](https://medium.com/@YanAIx/inside-claude-code-design-principles-of-a-powerful-agent-d36a8bed5ada), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/6244bfe5110e87a85c2916442caed6855de0b936/presentation-slides/Inside_Claude_Code_Design_Principles_of_a_Powerful_Agent.pdf), [recording](https://youtu.be/vb0GY2VBC6E)
- AI Mode in Search: Proative Agent-driven Search. [Paper](https://dl.acm.org/doi/pdf/10.1145/3711896.3737249), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/8fe4102388631ba0933c599586ac4f23043c8292/presentation-slides/ProactiveAgentinSearch.pdf), [recording](https://youtu.be/aWBgDeCVcZI)
- How Claude Code is Built. [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/f1e004c077e44862a1a0a3859bc92620920b014f/presentation-slides/How_Claude_Code_is_Built.pdf), [recording](https://youtu.be/_KJPemq1M6o?si=sC63xNdcO6eo9JjD)
- How Manus is Built: Building Effective AI Agents for Millions of Users. [Web link](https://manus.im/blog/Context-Engineering-for-AI-Agents-Lessons-from-Building-Manus), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/00ac75da35e88b4516828fdc63eeddab31d2c61b/presentation-slides/Lessons_from_Building_Manus.pdf), [recording](https://youtu.be/u4Ox4SBSwLI?si=WmZpRGxYHkz8lX2_)
- Text-to-SQL for Enterprise Data Analytics. [Paper](https://drive.google.com/file/d/1VM-D4MWAUJ_Kovq9acN9GNLLp2LMN_YU/view), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/00ac75da35e88b4516828fdc63eeddab31d2c61b/presentation-slides/Text2SQL.pdf), [recording](https://youtu.be/LVkDuaqlhvs?si=UAHQoGVOFttbLQwK)
- LAW: Legal Agentic Workflows for Custody and Fund Services Contracts. [Paper](https://arxiv.org/pdf/2412.11063), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/007b85a438bc3d1a21b91dd0976dd3de6dba9a71/presentation-slides/LAW.pdf), [recording](https://youtu.be/RQsq_GqPKwc)
- AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environment. [Paper](https://arxiv.org/pdf/2405.07960), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/f19d9e79fb7f5285ada03ec142e6295e7732346f/presentation-slides/Agentic_AI_clinical_diagnosis.pdf), [recording](https://youtu.be/4KYuY-vNbDs?si=h4btqvqEiOPzBudX)
- Amazon 2024 KDD cup: Multi Task Online Shopping Challenge for LLMs. [paper](https://openreview.net/pdf?id=sv0E1mBhu8), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/NVIDIA-KDD2024-Slides.pdf), [recording](https://youtu.be/0rVId3DGEeY)
- MCP: Why, What and How. [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/007b85a438bc3d1a21b91dd0976dd3de6dba9a71/presentation-slides/MCP.pdf),[recording](https://youtu.be/BXeHMjAhrPk)
  
## Research papers
- LLM Inference Optimization: From token to scale. [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/c7e77e5c42342a8cd9dd5875a9077ae42c550db1/presentation-slides/LLM_Inference_Optimization_From_Token_to_Scale.pdf), [recording](https://youtu.be/pcUc5eIREU8)
- Effective context engineering for AI agents. [Web link](https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/00ac75da35e88b4516828fdc63eeddab31d2c61b/presentation-slides/Effective_Context_Engineering_for_AI_Agents.pdf), [recording](https://youtu.be/U4r2tsMfZ4Q?si=L5PB8IvQ5id-uw0Z)
- Small Language Models are the Future of Agentic AI. [Paper](https://arxiv.org/pdf/2506.02153), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/00ac75da35e88b4516828fdc63eeddab31d2c61b/presentation-slides/SLMs.pdf), [recording](https://youtu.be/K95EUedfDOI?si=t11cx-rykT8yOZVe)
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning. [Paper](https://arxiv.org/pdf/2506.09985), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/007b85a438bc3d1a21b91dd0976dd3de6dba9a71/presentation-slides/WorldModel.pdf), [recording](https://youtu.be/LY_J9-7BjOc)
- AFlow: Automating Agentic Workflow Generation. [Paper](https://arxiv.org/abs/2410.10762), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/a9caff8e065f1f015b2cdcfc2570d864f125c317/presentation-slides/AFlow.pdf), [recording](https://youtu.be/07FFbeD3qWM?si=prJNq6jQcxO7yAL6)
- Large Language Model based Multi-agent System: A Survey of Progress and Challenges. [Paper](https://arxiv.org/pdf/2402.01680), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/0c33c40b0afc6ff3ba972c959330b41ad5b29292/presentation-slides/Multi-agent%20system%20review.pdf), [recording](https://youtu.be/71-W_X2DQxk?si=5fwduJUVrhLbcXiy)
- DeepSeek R1: Incentivizing Reasoning Capability in LLMs. [paper](https://arxiv.org/abs/2501.12948), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/a91d35520f98d444cd3f52601585ecc5a6eb143b/presentation-slides/DeepSeek-R1.pdf), [recording](https://youtu.be/AEN_D3UIFvY?si=pQUQpzgYY6CiqmTx)
- DeepSeek V3: Architecture and Design. [paper](https://arxiv.org/pdf/2412.19437), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/c4970f07c99c031d0164a86054d2a120bd943a45/presentation-slides/DeepSeek-V3.pdf), [recording](https://youtu.be/pGn7h86V230?si=o-hL7nYOKtKXVFsH)
- Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning. [paper](https://arxiv.org/abs/2205.05638), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/Few-shot-fine-tuning.pdf), [recording](https://youtu.be/3NBp_us1Lww)
- LoRA: Low-Rank Adaptation of Large Language Models. [paper](https://arxiv.org/abs/2106.09685), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/LoRA_and_QLoRA.pdf), [recording](https://youtu.be/nFh0uRqlWjw)
- QLORA: Efficient Finetuning of Quantized LLMs. [paper](https://arxiv.org/abs/2305.14314), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/LoRA_and_QLoRA.pdf), [recording](https://youtu.be/nFh0uRqlWjw)
- Automatic multi-step reasoning and tool-use for large language models. [paper](https://arxiv.org/abs/2303.09014), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/Automatic%20Multi-step%20Reasoning%20and%20Tool-use.pdf), [recording](https://youtu.be/BFrrii1G9lQ)
- Inference Optimization for Foundation Models on AI Accelerators: Model Quantization and Distillation. [paper](https://drive.google.com/file/d/1uVhHtRBwXy7o8ejaS6Ab6pSybkzticE3/view), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/LLM_inference_optimization_model_compression.pdf), [recording](https://youtu.be/9nmmfjM-b8g)
- Inference Optimization for Foundation Models on AI Accelerators: Architecture, KV cache and Flash attention. [paper](https://drive.google.com/file/d/1uVhHtRBwXy7o8ejaS6Ab6pSybkzticE3/view), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/LLM_inference_optimization_architecture_KVcache_flash_attention.pdf), [recording](https://youtu.be/jk2FsJxZFo8)
- Mistral and Mixtral of Experts. [paper](https://arxiv.org/abs/2401.04088), [slides](), [recording](https://youtu.be/nw8ByURxaSQ)
- Textbooks are All You Need: Phi 1 & 2. [paper](https://arxiv.org/abs/2306.11644), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/Phi%20model%20series.pdf), [recording](https://youtu.be/VLoLFHg7aQM)
- Llama family: Alpaca Vicuna and LLaVA. [paper](https://arxiv.org/abs/2304.08485), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/LlamaFamliy.pdf), [recording](https://youtu.be/za4yminmZ-w)
- Llama 2: Open Foundation and Fine-Tuned Chat Models. [paper](https://arxiv.org/abs/2307.09288), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/llama2.pdf), [recording](https://youtu.be/cr42NH4cDEQ)
- LLaMA: Open and Efficient Foundation Language Models. [paper](https://arxiv.org/abs/2302.13971), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/llama1.pdf), [recording](https://youtu.be/A6h7shg8rEw)
- GPT-4. [paper](https://arxiv.org/abs/2303.08774), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/GPT4.pdf), [recording](https://youtu.be/gqP39VvAW-c)
- InstructGPT: Training language models to follow instructions with human feedback. [paper](https://arxiv.org/abs/2203.02155), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/InstructGPT.pdf), [recording](https://youtu.be/CnjCHNH0asw)
- GPT 3 - Language Models are Few-Shot Learners. [paper](https://arxiv.org/abs/2005.14165), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/GPT3.pdf), [recording](https://youtu.be/w53U1ypIFIc)
- Scaling Laws for Neural Language Models. [paper](https://arxiv.org/abs/2001.08361), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/scaling%20Laws.pdf), [recording](https://youtu.be/TZtk1B7K0Qk)
- T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. [paper](https://arxiv.org/abs/1910.10683), [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/T5.pdf), [recording](https://youtu.be/_uAMvBBYMu8)
- Secrets in Training a Large Language Model: Pretraining, Fine-tuning and RLHF. [slides](https://github.com/YanXuHappygela/LLM-reading-group/blob/e41c398a6dd38a1692271f12b2844bf4ea581d86/presentation-slides/secrets_in_training_LLM.pdf) [recording](https://youtu.be/cybEKSNBp-w)
- Introduction to Transformers. [paper](https://arxiv.org/abs/1706.03762), [recording](https://youtu.be/k6LrtDzrpWw)

## Hands-on Session
- Hands-on session with Fine-tuning a LLM. [notebook](https://colab.research.google.com/drive/1QNOyWzD8H7xA6_ulVeL-5NIXWqMMR7kp?usp=drive_link), [recording](https://youtu.be/ZRQBCSZR-5E)
- Hands-on session of RAG with Llama 3. [notebook](https://colab.research.google.com/drive/1CuohoBl31hcAKuRdTYwxGY374v0Mc7uV?usp=drive_link), [recording](https://youtu.be/ooz8juF2e3I)

## Backlog

LLM-reading-group

LLM-reading-group Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

LLM-reading-group

LLM-reading-group Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README