Muti-human Interactive Talking Dataset

Foundation Models and Data for Human-Human and Human-AI interactions.

The official SpeakerVid-5M data curation code.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

Built by a PhD whose memory was failing, whose diet was a mess, and whose anxiety had its own agenda. Most second brain tools ignore the fact that your brain doesn't work in isolation: your body an…

This repository contains code for the paper "Why Diffusion Models Don't Memorize: The Role of Implicit Dynamical Regularization in Training" by T. Bonnaire, R. Urfin, G. Biroli and M. Mézard.

Official PyTorch Implementation of "Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions". Accepted at EMNLP 2025

[VISAPP2024] Towards the Detection of Diffusion Model Deepfakes

[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

Investigating patches for fake image classification

IFAKE is an application for detecting image and video forgery, designed to help users verify the authenticity of digital media. This repository also contains the AI model and dataset that we develo…

This repository is the official implementation of our paper "Preserving Fairness Generalization in Deepfake Detection", which has been accepted by CVPR 2024.

Official implementation of the paper ``On the Exploitation of DCT-Traces in Generative-AI Domain', accepted for publication at the ICIP 2024 conference.

Official implementation of CVPR'24 paper 'Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts'.

Official repository of "A Hitchhiker's Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning" published in NeurIPS'2024 (D&B track)

Refine high-quality datasets and visual AI models

deepfake dataset collected on the web for deepfake detection

The official repo of the Comics Survey: "A missing piece in Vision and Language: A Survey on Comics Understanding"

The official code of "DRCT: Diffusion Reconstruction Contrastive Training towards Universe Detection of Diffusion Generated Images"

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

[ECCV 2024] MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance

Pen and paper exercises in machine learning

[ICPR 2024] Exemplar-free continual deepfake detector that leverages CLIP and domain-specific multi-modal prompts

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

Official Repository for VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning