[NeurIPS 2025 Spotlight] "Detecting Generated Images by Fitting Natural Image Distributions"

Docker App which chooses a random movie from your movie library.

TransNet V2: Shot Boundary Detection Neural Network

Official training code for MUG-V 10B video generation model. Built on Megatron-LM (v0.14.0) with production-ready distributed training for 10B DiT.

Awesome curated collection of images and prompts generated by gemini-2.5-flash-image (aka Nano Banana) state-of-the-art image generation and editing model. Explore AI generated visuals created with…

🔥Highlighting the top ML papers every week.

Entropy Based Sampling and Parallel CoT Decoding

code repo for ICLR 2024 paper "Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs"

[ICML'2024] Can AI Assistants Know What They Don't Know?

SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper

FuseAI Project

official code for "Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding"

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

AI Router

Official Repository of ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning

A PDF to Markdown converter

My develoopment fork of llama.cpp. For now working on RK3588 NPU and Tenstorrent backend

A high-throughput and memory-efficient inference and serving engine for LLMs

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Inference code for Mistral and Mixtral hacked up into original Llama implementation

Port of Facebook's LLaMA model in C/C++

Minimal keyword extraction with BERT

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Transformer related optimization, including BERT, GPT

The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Transformer related optimization, including BERT, GPT

Python bindings for llama.cpp

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

A high-throughput and memory-efficient inference and serving engine for LLMs