Evolutionary Algorithms, Multimodal Representations, and Reinforcement Learning Advancements

Latest research summaries in ML, Robotics, CV, NLP and AI

Welcome to today's edition of State of AI 👋 And a warm welcome to our 221 new subscribers since last edition!

Let's get into it 👇

Contents

1. Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications

2. OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety

3. CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations

4. MedGemma Technical Report

5. CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions

6. Enhancing Scientific Visual Question Answering through Multimodal Reasoning and Ensemble Modeling

7. Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics

8. DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting

9. Beating the Best Constant Rebalancing Portfolio in Long-Term Investment: A Generalization of the Kelly Criterion and Universal Learning Algorithm for Markets with Serial Dependence

10. Instruction Following by Boosting Attention of Large Language Models

11. UQLM: A Python Package for Uncertainty Quantification in Large Language Models

12. Efficiency-Effectiveness Reranking FLOPs for LLM-based Rerankers

13. Embedding Atlas: Low-Friction, Interactive Embedding Visualization

14. Bias, Accuracy, and Trust: Gender-Diverse Perspectives on Large Language Models

15. Hidden Prompts in Manuscripts Exploit AI-Assisted Peer Review

Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications

Authors: Xinye Tang, Haijun Zhai, Chaitanya Belwal, Vineeth Thayanithi, Philip Baumann, Yogesh K Roy

Source and references: https://arxiv.org/abs/2506.20815v2

---

Introduction

This paper presents a novel dynamic context-aware prompt recommendation system for domain-specific AI applications. The system aims to address the challenges faced by users in crafting high-quality prompts, particularly in complex and specialized domains.

Key Points