large-language-models

[ICML 2026] Decoding Tree Sketching (DTS): a training-free & model agonistic & plug-in framework for LLM parallel reasoning.

🪢 Auto-generated Java Client for Langfuse API

An AI-powered Discord bot blending playful conversation with smart moderation tools, adding charm and order to your server.

NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference

Official code for the Manning book on structural LLM optimization: depth/width pruning, knowledge distillation, and attention optimization, runnable on free Colab GPUs.

Evaluation framework for paper "VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?"

TOON — Laravel AI package for compact, human-readable, token-efficient data format with JSON ⇄ TOON conversion for ChatGPT, OpenAI, and other LLM prompts.

[ICLR 2025] Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

[NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient

A RAG based Generative AI Attorney fed with Indian Penal Code data. Developed using Streamlit, LangChain and TogetherAI API.

Generating and validating natural-language explanations for the brain.

Reproducible Structured Memory for LLMs

A living map of the AI agent security ecosystem.

Ask the Doc app built using Langchain and Streamlit.

[ICLR 2025] The offical implementation of "PSEC: Skill Expansion and Composition in Parameter Space", a new framework designed to facilitate efficient and flexible skill expansion and composition, iteratively evolve the agents' capabilities and efficiently address new challenges

Prompt Engineering Workshop @ AI Convention 2025 (IHK Schwaben)

An AI-powered tool for transcribing, summarizing, and creating smart clips from video and audio content.

Research papers about Chain of Thought (CoT)

Automated Course Content Generator (ACCG) is an AI-powered Streamlit app for SMEs, Content Creators, and Educators. Input Course Name, Audience Level, Difficulty, and Credits to get a dynamic course outline, full course content, and quizzes. Download everything as a PDF, PPT and customize as needed!

Prompts and source code for applying LLMs to UAV-based navigation tasks with various model integrations