Tag: AI language models
Browse our exclusive articles!
Causal Evidence Reveals Dual Mechanisms in Graph Learning
Discover how large language models use dual mechanisms for in-context graph learning, combining structure inference and local transitions.
CoCoDA: Efficient Tool-Augmented Agents with Compositional DAG
Discover CoCoDA, a novel compositional DAG framework that enhances tool-augmented AI agents with efficient retrieval and adaptive training.
MISA: Efficient Sparse Attention for Long-Context LLMs
Discover MISA, a novel sparse attention method that boosts long-context LLM inference efficiency while reducing computational costs and maintaining perform...
Detecting Backdoors in SAE Architectures: Diff-SAE vs Crosscoders
Explore how Diff-SAE outperforms Crosscoders in isolating backdoors in language models, enhancing AI safety through effective detection methods.
Mutual Reinforcement Learning for Diverse Language Models
Discover how Mutual Reinforcement Learning enables experience sharing among heterogeneous language models to boost AI learning efficiency.