Re-implementing LangChain in 100 lines of code (2023)
blog.scottlogic.com·19h·
Discuss: Lobsters
🪄Prompt Engineering
Checklists Are The Thief Of Joy
soatok.blog·22h·
Discuss: Hacker News
🕳LLM Vulnerabilities
So, I decided to write a BUFR decoder
stormscale.io·14h·
Discuss: Hacker News
💾Binary Formats
Instruction Aware Embeddings – Why Your Retriever Is Failing
dipkumar.dev·2h·
Discuss: Hacker News
📌Embedding Retrieval
From Street Form to Spatial Justice: Explaining Urban Exercise Inequality via a Triadic SHAP-Informed Framework
arxiv.org·10h
🏗️Infrastructure Economics
Multicollinearity Resolution Based on Machine Learning: A Case Study of Carbon Emissions
arxiv.org·10h
📊Vector Databases
Iterative Zoom-In: Temporal Interval Exploration for Long Video Understanding
arxiv.org·10h
🔍Information Retrieval
You Can't Objectively Compare Seven Bees to One Human
lesswrong.com·20h
🧩Types
Economics of Claude 3 Opus Inference
lesswrong.com·20h
📊Model Serving Economics
MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction
arxiv.org·10h
🏆LLM Benchmarking
AutoLayout: Closed-Loop Layout Synthesis via Slow-Fast Collaborative Reasoning
arxiv.org·10h
📊Vector Databases
PrivTuner with Homomorphic Encryption and LoRA: A P3EFT Scheme for Privacy-Preserving Parameter-Efficient Fine-Tuning of AI Foundation Models
arxiv.org·10h
📋MCP
Enhanced knowledge retention through MedScrab: an interactive mobile game
arxiv.org·10h
📋MCP
Leveraging Out-of-Distribution Unlabeled Images: Semi-Supervised Semantic Segmentation with an Open-Vocabulary Model
arxiv.org·10h
📄Semantic Chunking
Causal-SAM-LLM: Large Language Models as Causal Reasoners for Robust Medical Segmentation
arxiv.org·10h
🔍AI Interpretability
Deep Learning-Based Forecasting of Hotel KPIs: A Cross-City Analysis of Global Urban Markets
arxiv.org·10h
🏆LLM Benchmarking
From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought
arxiv.org·10h
🧠LLM Inference
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
arxiv.org·10h
🧠LLM Inference
A Data-Driven Novelty Score for Diverse In-Vehicle Data Recording
arxiv.org·10h
📊Vector Databases
Distilling High Diagnostic Value Patches for Whole Slide Image Classification Using Attention Mechanism
arxiv.org·10h
📊Embeddings