每天自动聚合 AI 领域最新动态
The capability of a modern AI agent depends not only on its foundation model but also on its harness, which construct...
OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platfo...
Reinforcement learning with verifiable rewards without human-annotated data, often referred to as zero RL, has emerge...
Structured pruning is a hardware-friendly way to compress LLMs, but it is mostly validated on multiple-choice recogni...
Image guardrails are typically trained and evaluated under a fixed safety policy, implicitly treating safety as an in...
World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future visual observations, ...
Current visual generation models are capable of producing high-quality content, yet they lack a coherent perception o...
Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the t...
The optimization of long-horizon agents increasingly relies on reflection-based mechanisms, where a large language mo...
When should an intelligent assistant speak up without being asked? Continuous egocentric video offers rich, evolving ...
While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely on 2D di...
We introduce Boogu-Image-0.1, an open-source unified multimodal understanding and generation model family, comprising...