AISysRev: AI-Powered Tool for Fast Title-Abstract Screening
AISysRev uses advanced LLMs to speed up title-abstract screening, boosting systematic review efficiency with AI-driven accuracy and parallel processing.
RoleConflictBench: Evaluating LLMs’ Contextual Sensitivity
RoleConflictBench benchmarks large language models on role conflict scenarios to assess their ability to adapt to contextual social cues effectively.
Scaling Laws of LLMs in Reinforcement Learning Post-Training
Explore how model size, data, and compute impact LLM reinforcement learning post-training, with insights on mathematical reasoning efficiency.
WARBERT: Advanced BERT Model for Web API Recommendations
Discover WARBERT, a hierarchical BERT-based model improving accuracy and efficiency in Web API recommendations for developers and microservices.
OjaKV: Efficient Online KV Cache Compression for LLMs
Discover OjaKV, a context-aware online low-rank KV cache compression method that boosts large language model efficiency and memory usage.