[ICLR26] Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
☆21Apr 16, 2026Updated 5 months ago
Alternatives and similar repositories for VLM-Safety-Unlearn
Users that are interested in VLM-Safety-Unlearn are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Face Generation Work (Preprint)☆19Dec 28, 2024Updated last year
- [CVPR 2026] MonoIA: Towards Intrinsic-Aware Monocular 3D Object Detection☆26Mar 31, 2026Updated 5 months ago
- [CVPR 2026 Highlight] MonoCoP: Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detection☆26Aug 3, 2026Updated last month
- Official code for the CVPR 2024 Paper "Can Biases in ImageNet Models Explain Generalization?".☆13Jun 24, 2024Updated 2 years ago
- [NeurIPS 2024] RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models☆31Nov 12, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Using LLMs and pre-trained caption models for super-human performance on image captioning.☆42Oct 13, 2023Updated 2 years ago
- [ACL 2025] An inference-time decoding strategy with adaptive foresight sampling☆107May 18, 2025Updated last year
- 🧠 Bio-Agent OS: 🇻🇳 Bio-Inspired Memory Framework for AI Agents (OpenClaw/ERP). Researched & Developed by Dev Tuan Anh Ha (Locaith Solu…☆20Aug 20, 2026Updated last month
- The second Homework of NLP☆13Jun 9, 2021Updated 5 years ago
- ☆11Mar 15, 2023Updated 3 years ago
- MD-FAS with SiW-Mv2 dataset (ECCV22 Oral)☆81Feb 27, 2025Updated last year
- ☆12Aug 14, 2019Updated 7 years ago
- attention으로 시계열 예측은 할 수 없을까☆10Apr 30, 2021Updated 5 years ago
- ☆13Sep 6, 2021Updated 5 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆11Nov 20, 2023Updated 2 years ago
- Mahalanobis Distance-based Multi-view Optimal Transport for Multi-view Crowd Localization, ECCV 2024☆15Nov 20, 2024Updated last year
- Official code release for the paper Trapped in texture bias? A large scale comparison of deep instance segmentation, accepted at ECCV 202…☆15Jan 16, 2024Updated 2 years ago
- Pytorch Sketch Classification☆11Apr 14, 2018Updated 8 years ago
- ☆13Feb 14, 2022Updated 4 years ago
- Code to enable layer-level steering in LLMs using sparse auto encoders☆35Sep 18, 2025Updated last year
- [NeurIPS25] Official repo for "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"☆47Oct 3, 2025Updated 11 months ago
- [CVPR 2022] "Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval”, IEEE Conf. on Computer Vision and Pattern Recognit…☆15May 30, 2022Updated 4 years ago
- List of PyTorch repositories for visual question answering☆15Jul 4, 2019Updated 7 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [CVPR 2026] Code for Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory☆17Jul 30, 2026Updated last month
- Code release for "Understanding Bias in Large-Scale Visual Datasets"☆25Dec 4, 2024Updated last year
- ☆19Nov 22, 2022Updated 3 years ago
- A repository for documenting the process of making the Clearpath Jackal UGV run on ROS 2 Humble☆16Oct 1, 2023Updated 2 years ago
- ☆16Jun 13, 2024Updated 2 years ago
- ☆18Oct 1, 2025Updated 11 months ago
- SB-Bench: Stereotype Bias Benchmark for Large Multimodal Models☆15Jun 26, 2026Updated 2 months ago
- Baseline Triplet Loss Based Model for Fine-Grained Sketch Based Image Retrieval.☆14Mar 11, 2023Updated 3 years ago
- ☆14Jun 22, 2020Updated 6 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICME 2023] FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation☆13May 13, 2023Updated 3 years ago
- This is an implementation of the paper "Are We Done with Object-Centric Learning?"☆14Jun 21, 2026Updated 2 months ago
- A curated list of academic papers and resources on Vision-Language-Action (VLA) and World Action Models (WAM)☆34Updated this week
- Master and PhD Thesis LaTeX Template of Xi'an Jiaotong University☆22Sep 29, 2021Updated 4 years ago
- Multimodal Safety Awareness Benchmark for Large Language Models☆15Jun 3, 2025Updated last year
- Image Action Recognition system that uses the Stanford40 dataset☆11Aug 15, 2023Updated 3 years ago
- [TMLR 25] An automated method for explaining complex neuron behaviors in deep vision models using large language models☆12Feb 20, 2025Updated last year