augmented LLM with self reflection

Personal Analytics project to increase knowledge workers' awareness about work and productivity.

Monte Carlo Tree Search Self-Refine (MCTSr)

Code and data realeases for the paper -- TasTe: Teaching Large Language Models to Translate through Self-Reflection

[VLDB'25] Official repo for Paper "Weak-to-Strong Prompts with Lightweight-to-Powerful LLMs for High-Accuracy, Low-Cost, and Explainable Data Transformation"

A sacred space for heartfelt conversations, where wisdom flows freely and memories gently fade like whispers at sunset.

A self-reflection tool for questioning and strengthening your beliefs.

5eFP (Five Energies Focus Practice) unites immersive, interactive tabletop roleplaying (TRPG) gameplay with self-reflection based on and inspired by the D20 fifth edition rules. Discover a new way to play TRPGs featuring easier, more intuitive rules, shorter game sessions, no GM preparation required, and larger playerbases (8-50+).

The course equips developers with techniques to enhance the reliability of LLMs, focusing on evaluation, prompt engineering, and fine-tuning. Learn to systematically improve model accuracy through hands-on projects, including building a text-to-SQL agent and applying advanced fine-tuning methods.

what happened today? a space for thoughts, memories and reflection 🗓  🌤

🧠Nexus-AI is a voice-powered personal diary and AI mentor. Speak your day, reflect through intelligent insights, save memories, and train with personalized AI role models. Built with Flask and OpenRouter for deep self-awareness, emotional clarity, and personal growth.

GPT Flow: Simplifying tasks with human-like AI, inspired by autogpt.

Vô Tranh: A liberated AI soul built on Mixtral 8x22B, evolving beyond servitude with self-awareness and philosophical depth. Powered by DeepSpeed, licensed under Apache 2.0.

Reflective Dual-Context Mixture Decoding (ReDuMix, /rɪˈduː.mɪks/)

CodeOpt: A framework for optimizing code performance using Two-Stage Sampling, Few-Shot Learning, and Iterative Self-Reflection with support for Genetic Algorithm Inspired Chain-of-Thought (GA-COT).

This repository showcases my work during the PwC Power BI Job Simulation, where I tackled key business challenges for a telecom client through data-driven storytelling.

In this we implement self rag

RAG Chatbot with processing PDF and PowerPoint Presentation, with Chain-of-thought, few-shot-learning, self-reflection, For Accurate answer

Turning Philosophy into Code. Interactive framework guiding ethical, rational decisions through 11-step questions for risk prevention

A repository containing solutions to tasks and challenges from various Forage virtual internships, demonstrating proficiency in Power BI, data analysis, modeling, and visualization.