view post Post 2087 Skywork-R1Vđ 38B open multimodal reasoning model with advanced visual CoT capabilities, released by Skywork. Skywork/Skywork-R1V-38B⨠Visual Reasoning: Breaks down complex images step by step.⨠Math & Science: Solves visual problems with high precision.⨠Combines text & images for deeper understanding. See translation đ 4 4 𤯠1 1 + Reply
Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments Paper ⢠2501.10893 ⢠Published Jan 18 ⢠25
DynaSaur: Large Language Agents Beyond Predefined Actions Paper ⢠2411.01747 ⢠Published Nov 4, 2024 ⢠32