AIM Intelligence

company

https://aim-intelligence.com

AIM-Intelligence

AI & ML interests

AI Safety & AI Security

Recent Activity

Dasool authored a paper about 1 month ago

What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models

Dasool submitted a paper about 1 month ago

What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models

oneonlee authored a paper about 2 months ago

Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmark

View all activity

Papers

COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs

X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates

View all Papers

authored a paper about 1 month ago

What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models

Paper • 2601.06165 • Published Jan 7 • 16

submitted a paper to Daily Papers about 1 month ago

What Users Leave Unsaid: Under-Specified Queries Limit Vision-Language Models

Paper • 2601.06165 • Published Jan 7 • 16

authored 2 papers about 2 months ago

Everyday Physics in Korean Contexts: A Culturally Grounded Physical Reasoning Benchmark

Paper • 2509.17807 • Published Sep 22, 2025 • 1

Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures

Paper • 2510.24081 • Published Oct 28, 2025 • 19

authored 2 papers about 2 months ago

Global PIQA: Evaluating Physical Commonsense Reasoning Across 100+ Languages and Cultures

Paper • 2510.24081 • Published Oct 28, 2025 • 19

Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting

Paper • 2409.14747 • Published Sep 23, 2024

authored a paper about 2 months ago

COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs

Paper • 2601.01836 • Published Jan 5 • 10

authored a paper about 2 months ago

COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs

Paper • 2601.01836 • Published Jan 5 • 10

updated a collection about 2 months ago

COMPASS

A Framework for Evaluating Organization-Specific Policy Alignment in LLMs • 5 items • Updated Jan 6 • 5

submitted a paper to Daily Papers about 2 months ago

COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs

Paper • 2601.01836 • Published Jan 5 • 10

updated 2 models about 2 months ago

AIM-Intelligence/COMPASS_gemma-3-4b-it_LoRA

Image-Text-to-Text • 4B • Updated Jan 6 • 1 • 2

AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA

Text Generation • 8B • Updated Jan 6 • 4 • 2

updated 2 datasets about 2 months ago

AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset

Viewer • Updated Jan 6 • 4.12k • 19 • 2

AIM-Intelligence/COMPASS-Policy-Alignment-Testbed-Dataset

Viewer • Updated Jan 6 • 5.92k • 115 • 11

published 2 models about 2 months ago

AIM-Intelligence/COMPASS_gemma-3-4b-it_LoRA

Image-Text-to-Text • 4B • Updated Jan 6 • 1 • 2

AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA

Text Generation • 8B • Updated Jan 6 • 4 • 2

published 2 datasets about 2 months ago

AIM-Intelligence/COMPASS-Policy-aware-SFT-Dataset

Viewer • Updated Jan 6 • 4.12k • 19 • 2

AIM-Intelligence/COMPASS-Policy-Alignment-Testbed-Dataset

Viewer • Updated Jan 6 • 5.92k • 115 • 11

updated a dataset about 2 months ago

AIM-Intelligence/COMPASS-Policy-Alignment-Testbed-Dataset

Viewer • Updated Jan 6 • 5.92k • 115 • 11

updated a collection about 2 months ago

COMPASS

A Framework for Evaluating Organization-Specific Policy Alignment in LLMs • 5 items • Updated Jan 6 • 5