[ACL 2026] Still Between Us? Evaluating and Improving Voice Assistant Robustness to Third-Party Interruptions

Scalable group inference for generating high quality and diverse images with diffusion models.

Collection of scripts and notebooks for OpenAI's latest GPT OSS models

Pytorch implementation for MeanFlow

Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

This repository is the official implementation of "Removing Undesirable Feature Contributions using Out-of-Distribution Data", published as a conference paper at ICLR 2021.

This repository is the official implementation of Dataset Condensation with Contrastive Signals (DCC), accepted at ICML 2022.

Official repository of "Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach" (ACL 2024 Oral)

[ACL 2025] Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis

PyTorch implementation of MeanFlow & iMF (one-step generative modeling).

[CVPR 2025] Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis

[NeurIPS 2025] Official code for Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing

[CVPR 2025] Science-T2I: Addressing Scientific Illusions in Image Synthesis

[ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens

Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models

Official Implementation for Diffusion Models Without Classifier-free Guidance

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Official PyTorch implementation of "Paralinguistics-Aware Speech-Empowered LLMs for Natural Conversation" (NeurIPS 2024)

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

[BMVC 2024] ControlDreamer enables high-quality 3D generation with creative geometry and styles via multi-view ControlNet.

Official implementation for "pOps: Photo-Inspired Diffusion Operators"

Implementation of "Disentangled Motion Modeling for Video Frame Interpolation", AAAI 2025

Official PyTorch Implementation for Readout Guidance, CVPR 2024

Consistency Models Made Easy

EDM2 and Autoguidance -- Official PyTorch implementation

Official Code for Stable Cascade