爱可可 AI 前沿推介(7.5)

文章预览

LG - 机器学习 CV - 计算机视觉 CL - 计算与语言 AS - 音频与语音 RO - 机器人 1、[LG] DisCo-Diff：Enhancing Continuous Diffusion Models with Discrete Latents 2、[RO] Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models 3、[LG] Meta Large Language Model Compiler： Foundation Models of Compiler Optimization 4、[CL] SOS! Soft Prompt Attack Against Open-Source Large Language Models 5、[LG] LLM-Select：Feature Selection with Large Language Models 摘要：用离散潜变量增强连续扩散模型、利用视觉语言模型为四足机器人自适应性提供常识推理、编译器优化的基础模型、针对开源大型语言模型的软提示攻击、用大型语言模型进行特征选择 1、[LG] DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents Y Xu, G Corso, T Jaakkola, A Vahdat, K Kreis [NVIDIA & MIT] DisCo-Diff：用离散潜变量增强连续扩散模型 要点: 传统的扩散模型会把复杂的、多 ………………………………