GitHub

FAR: Frame Autoregressive Model for Both Short- and Long-Context Video Modeling

🔥 FAR leverages clean visual context without additional image-to-video fine-tuning: Unconditional pretraining on UCF-101 achieves state-of-the-art results in both video generation (context frame = 0) ...
GitHub

Getting started with Ollama for Python

So far, running LLMs has required a large amount of computing resources, mainly GPUs. Running locally, a simple prompt with a typical LLM takes on an average Mac ...
IEEE

Autoregressive Action Sequence Learning for Robotic Manipulation

Abstract: Designing a universal policy architecture that performs well across diverse robots and task configurations remains a key challenge. In this work, we address this by representing robot ...
Microsoft

Autoregressive Speech Synthesis without Vector Quantization

We present MELLE, a novel continuous-valued tokens based language modeling approach for text to speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from ...
IEEE

Dynamic Autoregressive Tensor Factorization for Pattern Discovery of Spatiotemporal Systems

Abstract: Spatiotemporal systems are ubiquitous in a large number of scientific areas, representing underlying knowledge and patterns in the data. Here, a fundamental question usually arises as how to ...