Specify Privacy Yourself: Assessing Inference-Time Personalized Privacy Preservation Ability of Large Vision-Language Models
cs.CV, cs.AI, cs.CL, cs.CY, cs.LG
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/achernarwang/specifyprivacy-yourself
Terminology
Sources
- GPT-4 Technical Report
- A General Language Assistant as a Laboratory for Alignment
- Qwen Technical Report
- Qwen2.5-VL Technical Report
- Constitutional AI: Harmlessness from AI Feedback
- Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models
- The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models
- Noise Contrastive Alignment of Language Models with Explicit Rewards
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
- Can Language Models be Instructed to Protect Personal Information?
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
- Large (Vision) Language Models are Unsupervised In-Context Learners
- ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools
- A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications
- Measuring Massive Multitask Language Understanding
- Liger Kernel: Efficient Triton Kernels for LLM Training
- Membership Inference Attacks Against Vision-Language Models
- GPT-4o System Card
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs