DrugPlayGround: Benchmarking LLMs for Drug Discovery
Discover how DrugPlayGround benchmarks large language models to enhance drug discovery with advanced AI-driven insights and performance evaluation.
UI-Oceanus: Scalable GUI Agents with Synthetic Dynamics
Discover how UI-Oceanus improves GUI agent scalability using synthetic environmental dynamics and forward predictive modeling for robust automation.
LLMs Achieve Massive Compression: Haiku to Opus in 10 Bits
Discover how LLMs unlock breakthrough compression gains with lossless and lossy methods, including innovative Question-Asking protocols for efficient data...
PROGRS: Enhancing LLM Reasoning with Process Rewards
Discover PROGRS, a framework improving LLM mathematical reasoning by combining process rewards and outcome correctness for accurate, efficient AI solutions...
Lower Bounds for Language Models Using Semantic Structures
Discover empirical lower bounds for language modeling with locally-bootstrapped semantic structures to improve NLP model efficiency and accuracy.