WeClone
WeClone 使用微信聊天记录微调大语言模型，使用微信语音消息大模➕0.5B大模型实现高质量声音克隆，并绑定到微信机器人，实现自己的数字分身。 数字克隆/数字分身／声音克隆/LLM/大语言模型/微信...
排序
Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation
Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation 在数字动画领域，将创意草图转化为生动的三维动画一直是设计师...
RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation
RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation RAG-MCP: M...
ZeroSearch: Incentivize the Search Capability of LLMs without Searching
Hao Sun, Zile Qiao†, Jiayan Guo†, Xuanbo Fan, Yingyan Hou Yong Jiang, Pengjun Xie, Yan Zhang†, Fei H...
ORCA: An Open-Source, Reliable, Cost-Effective, Anthropomorphic Robotic Hand for Uninterrupted Dexterous Task Learning
ORCA：一款开源、可靠、成本高效、拟人化的机械手，可实现不间断灵巧任务学习 ORCA_An_Open-Source_Reliable_Cost-Effective_Anthropomorphic_R...
Advances and Challenges in Foundation Agents
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Coll...
Explaining Deep Neural Networks
Explaining Deep Neural Networks Oana-Maria Camburu Linacre College University of Oxford A thesis sub...
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
Preparing-for-the-Intelligence-Explosion
Preparing-for-the-Intelligence-Explosion 在过去的几年里，我们见证了人工智能的突飞猛进：从写诗答题到绘图编程，从对话聊天到法律分析，AI的成长速度简直令人目瞪口...
图解大模型RLHF系列之：人人都能看懂的PPO原理与源码解读
【by 知乎】 去年此时我写了这篇文章，当时的主要目的是，想让读者在没有RL知识的情况下，能从直觉上快速理解代码，以便上手训练和修改。由于一切从“直觉”出发，因此有很多表述不准确的地方，所以最近我写了...