EML Munich

ReNO

[NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization

flair

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

Vision_by_Language

[ICLR 2024] Official repository for "Vision-by-Language for Training-Free Compositional Image Retrieval"

HyperNoise

fomo_in_flux

Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]

DataDream

[ECCV 2024] Official repository for "DataDream: Few-shot Guided Dataset Generation"

ProbVLM

ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models

sae-for-vlm

[NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

EgoCVR

[ECCV 2024] EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval

cosmos

[CVPR 2025] COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training

sketch-primitives

ECCV 2022: Abstracting Sketches through Simple Primitives

TCAF-GZSL

This repository contains the code for our ECCV 2022 paper "Temporal and cross-modal attention for audio-visual zero-shot learning"

in-context-impersonation

[NeurIPS 2023 Spotlight] In-Context Impersonation Reveals Large Language Models' Strengths and Biases

ZerAuCap

[NeurIPS 2023 - ML for Audio Workshop (Oral)] Zero-shot audio captioning with audio-language model guidance and audio context keywords

ImageFreeZSL

uot-fm

Official Repository for "Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation" [ICLR 2024]

DeLoRA

[ICLR25] Official Implementation of "Decoupling Angles and Strength in Low-rank Adaptation"

TiViT

Time Vision Transformer

WikiBigEdit

This is the official repository for the WikiBigEdit benchmark, introduced in the paper Understanding the Limits of Lifelong Knowledge Editing in LLMs.

AVDIFF-GFSL

This repository contains the code for our DAGM GCPR 2023 paper "Text-to-feature diffusion for audio-visual few-shot learning"

concept_realignment

Official PyTorch implementation of "Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models" (ECCV 2024)

General-Knowledge-Transfer

Official repository for "Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model" [ICLR 2024 spotlight]

sub

vla-gender-bias

[ICLR 2025] Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)

LoFT

Synthetic Dataset Generation with Few-shot Guidance: LoFT [Arxiv] & DataDream [ECCV24]

align-then-unlearn

[ICML 2025 Workshop MUGen] Align-then-Unlearn: Embedding Alignment for LLM Unlearning

Deep-Graph-Persistence

Code for the paper "Addressing caveats of neural persistence with deep graph persistence".

eml_website

FantasticGains

[ICLR 2024] Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model

flair-website

Project Page for FLAIR [CVPR 2025]