Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

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 implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"

Official inference repo for FLUX.2 models

Mitigating Negative Flips via Margin Preserving Training

This repository contains the official implementation code of NeurIPS 2025 paper: "Instance-Level Composed Image Retrieval".

[ICCV 2025] What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models

[TMLR] Public code repo for paper "A Single Transformer for Scalable Vision-Language Modeling"

Fully Open Framework for Democratized Multimodal Training

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

Recurrence Meets Transformers for Universal Multimodal Retrieval

[IJCAI 2025] Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives

Official code for the paper "Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models" (ICLR 2025 Oral)

[ICCV 2025] - Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

[ICCV 2025] - Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

Official repository for "AM-RADIO: Reduce All Domains Into One"

Official code of Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning

Multi-scale Image Super Resolution with a Single Auto-Regressive Model

Single-pass Adaptive Image Tokenization for Minimum Program Search | What's the Kolmogorov Complexity of an Image?

Official implementation of the paper "Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals"

This is the official repository for the paper "Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction". ICCV 2025

[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

[CVPR 2025] FLAIR: VLM with Fine-grained Language-informed Image Representations

FRED: The Florence RGB-Event Drone Dataset

This repo contains the official implementation of the paper "Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency"

[NeurIPS 2025 Spotlight] ReSim: Reliable World Simulation for Autonomous Driving