ZAYA1-8B AI Model: Breakthrough in Reasoning Performance
Discover ZAYA1-8B, an advanced AI model excelling in complex reasoning, math, and coding with innovative training and efficient architecture.
Improving AI Safety with Annotator Policy Models
Discover how Annotator Policy Models enhance AI safety by resolving annotation disagreements and clarifying policy ambiguities effectively.
Poly-EPO: Optimizing Language Models with Exploratory Training
Discover Poly-EPO, a novel framework enhancing language models through optimistic exploration and set reinforcement learning for better reasoning.
HWE-Bench: Real-World Benchmark for Hardware Bug Repair
Discover HWE-Bench, the first large-scale benchmark evaluating LLM agents on real-world hardware bug repair tasks across major open-source projects.
HiMAC: Hierarchical Learning for Long-Horizon LLM Agents
Discover HiMAC, a hierarchical learning framework boosting long-horizon planning and execution in LLM agents with improved efficiency and performance.