Skip to content

@ExplainableML EML Munich

Change the repository type filter

All

    Repositories list

    56 repositories

    • LAION-400M-Person-Centric-Annotations

      Public
      [ICLR 2026] Official codebase of "Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models"
      social-biasautomatic-annotationdataset-biaslaion400mdemographic-bias
      Jupyter Notebook
      •0•0•0•0•Updated Feb 13, 2026Feb 13, 2026

    • eml_website

      Public
      JavaScript
      •0•2•0•0•Updated Feb 9, 2026Feb 9, 2026

    • RLLM-CoT-Robustness

      Public
      [ICLR 2026] Are Reasoning LLMs Robust to Interventions on their Chain-of-Thought?
      0•3•0•0•Updated Feb 7, 2026Feb 7, 2026

    • DeLoRA

      Public
      [ICLR25] Official Implementation of "Decoupling Angles and Strength in Low-rank Adaptation"
      Python
      •
      MIT License
      •0•15•0•0•Updated Dec 12, 2025Dec 12, 2025

    • HyperNoise

      Public
      Python
      •
      MIT License
      •2•70•1•0•Updated Dec 5, 2025Dec 5, 2025

    • sae-for-vlm

      Public
      [NeurIPS 2025] Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
      Python
      •8•62•1•0•Updated Nov 27, 2025Nov 27, 2025

    • sub

      Public
      [ICCV '25] SUB: Benchmarking CBM Generalization via Synthetic Attribute Substitutions
      Jupyter Notebook
      •0•8•0•0•Updated Nov 4, 2025Nov 4, 2025

    • czsl

      Public
      PyTorch CZSL framework containing GQA, the open-world setting, and the CGE and CompCos methods.
      Python
      •
      GNU General Public License v3.0
      •27•125•7•0•Updated Oct 29, 2025Oct 29, 2025

    • Stitch

      Public
      Stitch: Training-Free Position Control in Multimodal Diffusion Transformers
      Python
      •1•7•2•0•Updated Oct 8, 2025Oct 8, 2025

    • ReflectingOnRFCL

      Public
      Code repo to the 2024 CoLLAs Paper "Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models"
      Python
      •
      MIT License
      •0•0•0•0•Updated Sep 21, 2025Sep 21, 2025

    • ReNO

      Public
      [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
      text-to-imagetext-to-image-generationstable-diffusionreward-models
      Python
      •
      MIT License
      •15•164•5•0•Updated Sep 15, 2025Sep 15, 2025

    • TCAF-GZSL

      Public
      This repository contains the code for our ECCV 2022 paper "Temporal and cross-modal attention for audio-visual zero-shot learning"
      Python
      •
      MIT License
      •0•25•4•0•Updated Sep 12, 2025Sep 12, 2025

    • flair

      Public
      [CVPR 2025] FLAIR: VLM with Fine-grained Language-informed Image Representations
      clipmulti-modal-learningcontrastive-learningvision-language-model
      Python
      •6•132•0•0•Updated Sep 1, 2025Sep 1, 2025

    • TiViT

      Public
      Time Vision Transformer
      Python
      •
      MIT License
      •2•18•0•0•Updated Jul 20, 2025Jul 20, 2025

    • align-then-unlearn

      Public
      [ICML 2025 Workshop MUGen] Align-then-Unlearn: Embedding Alignment for LLM Unlearning
      unlearningllm
      Python
      •0•4•0•0•Updated Jun 17, 2025Jun 17, 2025

    • vla-gender-bias

      Public
      [ICLR 2025] Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)
      vlmsocial-biasmllm
      Python
      •0•6•5•0•Updated Jun 5, 2025Jun 5, 2025

    • flair-website

      Public
      Project Page for FLAIR [CVPR 2025]
      JavaScript
      •0•1•0•0•Updated Apr 11, 2025Apr 11, 2025

    • EgoCVR

      Public
      [ECCV 2024] EgoCVR: An Egocentric Benchmark for Fine-Grained Composed Video Retrieval
      Python
      •
      MIT License
      •0•41•4•0•Updated Apr 11, 2025Apr 11, 2025

    • LoFT

      Public
      Synthetic Dataset Generation with Few-shot Guidance: LoFT [Arxiv] & DataDream [ECCV24]
      Python
      •0•5•1•0•Updated Mar 31, 2025Mar 31, 2025

    • cosmos

      Public
      [CVPR 2025] COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
      Python
      •3•38•2•0•Updated Mar 27, 2025Mar 27, 2025

    • WikiBigEdit

      Public
      This is the official repository for the WikiBigEdit benchmark, introduced in the paper Understanding the Limits of Lifelong Knowledge Editing in LLMs.
      Python
      •
      Other
      •0•10•0•0•Updated Mar 13, 2025Mar 13, 2025

    • fomo_in_flux

      Public
      Code and benchmark for the paper: "A Practitioner's Guide to Continual Multimodal Pretraining" [NeurIPS'24]
      Python
      •
      MIT License
      •4•61•0•0•Updated Dec 10, 2024Dec 10, 2024

    • in-context-impersonation

      Public
      [NeurIPS 2023 Spotlight] In-Context Impersonation Reveals Large Language Models' Strengths and Biases
      chatbottext-generationartificial-intelligencellamaclipreasoningbanditneurips-2023mmlullama2
      Python
      •
      MIT License
      •1•22•2•0•Updated Nov 30, 2024Nov 30, 2024

    • ZerAuCap

      Public
      [NeurIPS 2023 - ML for Audio Workshop (Oral)] Zero-shot audio captioning with audio-language model guidance and audio context keywords
      audiozero-shotoptaudio-captioningclotho-datasetlarge-language-modelsneurips-2023audiocaps
      Python
      •1•18•0•0•Updated Nov 30, 2024Nov 30, 2024

    • FantasticGains

      Public
      [ICLR 2024] Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model
      Python
      •
      MIT License
      •0•2•0•0•Updated Oct 31, 2024Oct 31, 2024

    • ImageFreeZSL

      Public
      Python
      •0•18•0•0•Updated Oct 5, 2024Oct 5, 2024

    • concept_realignment

      Public
      Official PyTorch implementation of "Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Models" (ECCV 2024)
      Python
      •
      MIT License
      •4•9•0•0•Updated Aug 12, 2024Aug 12, 2024

    • DataDream

      Public
      [ECCV 2024] Official repository for "DataDream: Few-shot Guided Dataset Generation"
      Python
      •8•50•5•0•Updated Jul 24, 2024Jul 24, 2024

    • AVDIFF-GFSL

      Public
      This repository contains the code for our DAGM GCPR 2023 paper "Text-to-feature diffusion for audio-visual few-shot learning"
      Python
      •
      MIT License
      •1•8•0•0•Updated Jul 23, 2024Jul 23, 2024

    • Vision_by_Language

      Public
      [ICLR 2024] Official repository for "Vision-by-Language for Training-Free Compositional Image Retrieval"
      image-retrievalmultimodalllm
      Python
      •
      MIT License
      •7•83•1•0•Updated Jul 4, 2024Jul 4, 2024