Pai 的 AI 雷达
今天：Improving GPT‑5.6 Sol，Working with the。并行还有 Baseten on Hugging、DeepSeek-V4 Flash 0731、WeatherNext。
GUI agents must remember both useful experience from earlier tasks and unfinished progress in the current interaction. Latent memory offers a compact solution by compressing multimodal trajectories into a few continuous
Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often treat skills as experience summaries, memory entries, or direct summari
Interactive video world models are essential for long-horizon planning and exploration, yet they suffer from compounding errors. Post-training methods such as reinforcement learning (RL) can improve these models, but the
Leading open text-to-image models often carry complementary strengths: one may lead on preference-aligned aesthetics while another follows compositional instructions more faithfully. However, differences in their autoenc
https://www.xiaoyuzhoufm.com/episode/6a69b07eb581962ce2bd4d97 2024 年 4 月，一篇挂在 arXiv 上的论文在技术社群里炸开了锅。 有人说，统治深度学习几十年的 MLP（多层感知机）可能要被改写了。 也有人说，这不过是又一个"看起来很美"的架构。 这篇
Vision offers a critical axis for advancing foundation models, driving a shift towards natively unified multimodal pretraining. Despite this momentum, the design space and the fundamental mechanisms of how modalities int