Generative AI Survey: Top LLMs, Architectures & Uses 2026
Explore a comprehensive 2026 survey of generative AI covering leading large language models, architectures, protocols, and real-world applications across i...
ATBench: Realistic Agent Trajectory Benchmark for AI Safety
Discover ATBench, a diverse benchmark for evaluating AI agent safety through realistic multi-step trajectories and risk diagnosis.
Perception-Grounded Policy Optimization for Vision-Language Models
Improve Large Vision-Language Models with Perception-Grounded Policy Optimization that enhances token-level learning for better multimodal reasoning.
Efficient Amazons Chess AI Using LLMs and Graph Attention
Discover a resource-efficient Amazons chess AI framework combining large language models and graph attention for superior decision-making accuracy.
Omni Parsing Framework: Unified Multimodal Parsing Report
Explore the Omni Parsing framework for unified multimodal parsing, integrating perception and cognition to convert unstructured data into structured knowle...