Official code for Dynamic Parametric RAG.
-
Updated
May 23, 2025 - Python
Official code for Dynamic Parametric RAG.
Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache
The data and implementation for the experiments in the paper "Flows: Building Blocks of Reasoning and Collaborating AI".
Belief-Bias evaluation of local LLMs
CoT Reasoning in Autoregressive Image Generation
Self-Improving LLMs Through Iterative Refinement
Latent-Explorer is the Python implementation of the framework proposed in the paper "Unveiling LLMs: The Evolution of Latent Representations in a Dynamic Knowledge Graph".
A set of auxiliary systems designed to provide a measure of estimated confidence for the outputs generated by Large Language Models.
Análise de Intervenção em Ansiedade com Descoberta Causal
Can LLMs really 'Think'? This repo contains implementation of different types of memory for LLMs.
A powerful Python library that combines the Google Books API with Cohere's LLM capabilities to create an intelligent book discovery and analysis system. This tool enables sophisticated book searches, AI-powered analysis, and smart recommendations.
A curated dataset of 31,822 annotated passages from Italian political speeches, featuring expert-validated explanations of implicatures and presuppositions. Derived from the IMPAQTS corpus, this resource supports research on implicit content, pragmatic inference, and political language understanding.
ReAct-powered autonomous agents for office task automation. They process various file formats, generate Excel spreadsheets, conduct deep research, and manage local emails and calendars. Utilizes Gemini 1.5 Flash, fine-tuned open-source models, and Deepseek R1 for efficient and economical execution.
Add a description, image, and links to the llms-reasoning topic page so that developers can more easily learn about it.
To associate your repository with the llms-reasoning topic, visit your repo's landing page and select "manage topics."