[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] Sotopia-RL: Reward Design for Social Intelligence
Keyang Xuan์ด [arXiv]์ ๊ฒ์ํ โSotopia-RL: Reward Design for Social Intelligenceโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
Recent Posts
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering
Ambuj Mehrish์ด [arXiv]์ ๊ฒ์ํ โSonicMaster: Towards Controllable All-in-One Music Restoration and Masteringโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] Sel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generation
Hao Huang์ด [arXiv]์ ๊ฒ์ํ โSel3DCraft: Interactive Visual Prompts for User-Friendly Text-to-3D Generationโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
Yunxin Liu์ด [arXiv]์ ๊ฒ์ํ โSculptor: Empowering LLMs with Cognitive Agency via Active Context Managementโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.
[๋ ผ๋ฌธ๋ฆฌ๋ทฐ] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
Xiaoyi Dong์ด [arXiv]์ ๊ฒ์ํ โSEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experienceโ ๋ ผ๋ฌธ์ ๋ํ ์์ธํ ๋ฆฌ๋ทฐ์ ๋๋ค.