按时间倒序排列。用上方导航或分类/标签可以按主题浏览。
When the Application Layer Is Disposable: Putting Integrity Constraints Back in the Database
Integrity constraints have been central to the relational model since its inception. However, beyond keys, single-row CH
//
全部文章
677 篇Multi-Objective Reinforcement Learning Using Routed Ensembles and Trajectory Attribution
Multi-objective reinforcement learning is a fundamental problem for modern AI, with applications spanning post-training,
FISRF: Flexible Instructional Scaffolding Reflection Framework for Robotics Task Planning with Large Language Model
Large Language Models (LLMs) are widely adopted for reflective error correction in task planning; however, existing appr
模型好选，搜索难做：一个投研Agent的两年开发历程
点击查看原文>
Context Is Not Free: Carbon-Aware LLM Routing for Multi-Turn LLM Web Services across Geo-Distributed Data Centers
The sustainability of the Web has drawn growing attention, as large language model (LLM)-based web services leave a subs
SmartCall v1.0.9 发布：智能体知识库上线，让 AI 客服先查资料再回答
📖 项目简介 SmartCall 是一套基于 AI 大模型 + Asterisk 通信引擎构建的新一代智能客服呼叫中心系统。系统深度融合了 AI 语音机器人、智能 IVR 流程编排、端到端双工对话模型、实时语音识别（ASR）、语音合成（TT
Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control
Assistive agents in shared-control settings face a dual challenge: acting proactively to align with the human's intentio