3 papers
cs.CV2025
Autoregressive Video Generation beyond Next Frames Prediction
Sucheng Ren, Chen Chen, Zhenbang Wang +5
Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike wo…
cs.CV2025
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Yanghao Li, Rui Qian, Bowen Pan +24
Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold immense potential. However, existing open-source models often suffer from…
stat.ME2023
A General Framework for Regression with Mismatched Data Based on Mixture Modeling
Martin Slawski, Brady T. West, Priyanjali Bukke +3
Data sets obtained from linking multiple files are frequently affected by mismatch error, as a result of non-unique or noisy identifiers used during record linkage. Accounting for…