Writing AI Conference Papers: A Handbook for Beginners

ReFT: Representation Finetuning for Language Models

A resource repository for representation engineering in large language models

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

⚡ InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

A simple unified framework for evaluating LLMs

TrustMark - Universal Watermarking for Arbitrary Resolution Images

Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models

Official inference repo for FLUX.1 models

nanoGPT style version of Llama 3.1

A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.

[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)

EB1A Full Application - I-140 and I-485

Officail Implementation for "ReNoise: Real Image Inversion Through Iterative Noising"

Official repo of On Exact Inversion of DPM-Solvers by Hong et al, in CVPR 2024.

A curated list of watermarking schemes for generative AI models

A collection of benchmarks and datasets for evaluating LLM.

[TPAMI 2022] GAN Inversion: A Survey

[ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

Code for our paper "Fixed-point Inversion for Text-to-image diffusion models"

ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment

The official implementation of Self-Play Preference Optimization (SPPO)

This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses

A SOTA lightweight multilingual LLM

Code for Zero-Shot Tokenizer Transfer

Source code for paper "Sampling-based Pseudo-Likelihood for Membership Inference Attacks".