AI 雷达 / 周报
按原始发布周整理来源摘录与阅读线索，不自动生成个人观点或趋势结论。
重点信号
本周动态 / 来源信号
AI 雷达 / 信号 · 智能体 · 论文 ·
来源摘录
Large language models (LLMs) increasingly generate Markdown that is consumed by renderers, agents, code extractors, and structured downstream pipelines. Yet existing evaluations…
AI 雷达 / 信号 · 智能体 · 论文 ·
来源摘录
Social-deduction games such as Werewolf are increasingly used to evaluate LLM agents, but existing evaluations often rely on final game outcomes. We propose a belief-shift evalu…
本周动态 / 来源信号
AI 雷达 / 信号 · 具身智能 · 论文 ·
来源摘录
Human video datasets have emerged as a compelling alternative to expensive real-robot data, offering rich diversity at scale. To bridge the human-to-robot embodiment gap, existi…
AI 雷达 / 信号 · 具身智能 · 论文 ·
来源摘录
Diffusion-based robot policies have become widely used in robotic manipulation, where they are typically trained with behavior cloning. However, policies trained purely from dem…
值得跟进