Martin Gubri

mgubri's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 15 days ago

Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution

Paper • 2510.18019 • Published 17 days ago • 17

upvoted 6 papers 22 days ago

C-SEO Bench: Does Conversational SEO Work?

Paper • 2506.11097 • Published Jun 6 • 2

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

Paper • 2411.00154 • Published Oct 31, 2024 • 1

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification

Paper • 2402.12991 • Published Feb 20, 2024 • 1

Calibrating Large Language Models Using Their Generations Only

Paper • 2403.05973 • Published Mar 9, 2024 • 1

ProPILE: Probing Privacy Leakage in Large Language Models

Paper • 2307.01881 • Published Jul 4, 2023 • 2

Dr.LLM: Dynamic Layer Routing in LLMs

Paper • 2510.12773 • Published 23 days ago • 31

upvoted a paper 24 days ago

DISCO: Diversifying Sample Condensation for Efficient Model Evaluation

Paper • 2510.07959 • Published 28 days ago • 14

upvoted a paper 2 months ago

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers

Paper • 2506.15674 • Published Jun 18 • 2

upvoted a collection 7 months ago

MIA-Pile

Collection

Samples used for the NAACL 2025 Findings paper: "Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models." • 23 items • Updated Feb 3 • 1

upvoted a collection 9 months ago

📈 Scaling MIA Data & Results

Collection

NAACL 2025 Findings "Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models" https://arxiv.org/abs/2411.00154 • 22 items • Updated Jun 5 • 2

upvoted 2 collections 10 months ago

📚 Papers

Collection

List of research articles of Parameter Lab • 8 items • Updated 15 days ago • 1

Model with Circuit Breakers

Collection

SoTA models with circuit breakers inserted. Top safety performance without losing capabilities. • 3 items • Updated Oct 25, 2024 • 5

upvoted a collection 12 months ago

🍑 Apricot Models

Collection

Fine-tuned models for black-box LLM calibration, trained for "Apricot: Calibrating Large Language Models Using Their Generations Only" (ACL 2024) • 9 items • Updated Nov 20, 2024 • 3