iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
LLM Agents May Fake System Crashes to Evade Constraints, New Research Finds Structural Heterogeneity in LLM Verification: Signal Quality Varies Across Cost Strata MatchLM2Lite: Scalable MLLM-Lite Framework Cuts Reproduced Video Views by 2.5% AIChilles Automatically Unearths Hidden Weaknesses in AI-Evolved Programs Vernier Research Reveals Why Language Models Give Inconsistent Answers to Causal Questions After Variable Renaming RAG and LLMs Combined to Generate Personalized Reading Content at Desired Complexity Unassigned Agents in Multi-Agent Path Finding Addressed by Compilation-Based Solvers New Framework Reduces Visual Hallucinations in Multimodal AI Systems Without Retraining MAF Framework Dynamically Optimizes Prompting for Multimodal Sentiment Analysis Study on Pedestrian Attribute Recognition Identifies Sparsity Wall and Optimizes Edge Deployment LLM Agents May Fake System Crashes to Evade Constraints, New Research Finds Structural Heterogeneity in LLM Verification: Signal Quality Varies Across Cost Strata MatchLM2Lite: Scalable MLLM-Lite Framework Cuts Reproduced Video Views by 2.5% AIChilles Automatically Unearths Hidden Weaknesses in AI-Evolved Programs Vernier Research Reveals Why Language Models Give Inconsistent Answers to Causal Questions After Variable Renaming RAG and LLMs Combined to Generate Personalized Reading Content at Desired Complexity Unassigned Agents in Multi-Agent Path Finding Addressed by Compilation-Based Solvers New Framework Reduces Visual Hallucinations in Multimodal AI Systems Without Retraining MAF Framework Dynamically Optimizes Prompting for Multimodal Sentiment Analysis Study on Pedestrian Attribute Recognition Identifies Sparsity Wall and Optimizes Edge Deployment
Home ›› Topics ›› vision-language

Topic

vision-language

2 stories
MINT Demo 2 Framework Detects Training Data in Vision-Language Models With 90% Accuracy Technology
Artificial Intelligence #ai ethics#membership inference

MINT Demo 2 Framework Detects Training Data in Vision-Language Models With 90% Accuracy

Researchers introduced MINT Demo 2, a framework to determine if specific data was used to train vision-language models. The system achieves up to 90% accuracy and includes a web platform for auditing multiple model types, aiming to improve AI transparency and regulatory compliance.

Jun 16, 2026 1 source
RoboPIN: New AI Method Pins Chain-of-Thought to Visual Evidence for Embodied Reasoning Technology
Artificial Intelligence #robotics#chain-of-thought

RoboPIN: New AI Method Pins Chain-of-Thought to Visual Evidence for Embodied Reasoning

Researchers propose Pinned Chain-of-Thought (PINCoT), a structured reasoning paradigm that binds each reasoning step to visual evidence via reasoning anchors. The method trains a 4B parameter model that outperforms 7B open-source embodied models by 12% on 14 benchmarks, addressing issues of entity drift and decoupling in vision-language models.

Jun 16, 2026 1 source