May 2024
- New Method Keeps LLM Outputs Grammatical While Preserving Natural Probability Distributions· AI
- Large Language Models Fail at Generating True Random Sequences, Amplifying Human Cognitive Biases· AI
- New Framework Tackles Anomaly Detection When Training Data Contains Hidden Defects· Machine Learning
- New AI model detects hazard information in social media posts to identify influence operations· Agentic AI
- New Method Uses GFlowNets to Generate Diverse Attacks for Safer AI Models· Agentic AI
- New framework balances adversarial robustness and generalization in vision-language models· AI
- AI System Generates Research Ideas from 58M Papers, but Expert Interest Remains Limited· AI
- Mamba-Based Model Challenges Transformers for Time-Series Forecasting· AI
- AI Model Generates Realistic Daily Mobility Patterns for Urban Planning· AI
- Comprehensive Review Maps the Landscape of Text Generation Research and Open Challenges· Natural Language Processing
- New control-theory method makes language models steer away from harmful outputs without slowing them down· AI
- New gradient framework enables safer AI through risk-aware reinforcement learning· Agentic AI
- New Unsupervised Method Discovers Meaning in Mixed Text and Video Conversations· AI
- Comprehensive survey maps efficiency improvements across transformer language models· AI
- New AI method improves learning from imbalanced data with unknown test distributions· Machine Learning
- New AI framework uses synthetic disease images to boost potato crop health detection· AI
- FlashBack Makes Retrieval-Augmented AI Models 4x Faster· AI
- Kotlin-Java cross-language interactions breed bugs and defects, study reveals· Software Engineering
- New model learns to optimize unseen problems without retraining· AI
- New Benchmark Reveals How AI Models Hallucinate Citations in Scientific Papers· AI
- New neural model handles massive variations in routing problems for real-time logistics· AI