Results 301 to 310 of about 5,332,049 (311)

Erasing Concepts from Diffusion Models

IEEE International Conference on Computer Vision, 2023
Motivated by concerns that large-scale diffusion models can produce undesirable output such as sexually explicit content or copyrighted artistic styles, we study erasure of specific concepts from diffusion model weights.
Rohit Gandikota, Joanna Materzynska, Jaden Fiotto-Kaufman, David Bau   +3 more
semanticscholar   +1 more source

CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer

International Conference on Learning Representations
We present CogVideoX, a large-scale text-to-video generation model based on diffusion transformer, which can generate 10-second continuous videos aligned with text prompt, with a frame rate of 16 fps and resolution of 768 * 1360 pixels.
Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Xiaotao Gu, Yuxuan Zhang, Weihan Wang, Yean Cheng, Ting Liu, Bin Xu, Yuxiao Dong, Jie Tang   +18 more
semanticscholar   +1 more source

Large Language Diffusion Models

arXiv.org
The capabilities of large language models (LLMs) are widely regarded as relying on autoregressive models (ARMs). We challenge this notion by introducing LLaDA, a diffusion model trained from scratch under the pre-training and supervised fine-tuning (SFT)
Shen Nie, Fengqi Zhu, Zebin You, Xiaolu Zhang, Jingyang Ou, Jun Hu, Jun Zhou, Yankai Lin, Jirong Wen, Chongxuan Li   +9 more
semanticscholar   +1 more source

Simple and Effective Masked Diffusion Language Models

Neural Information Processing Systems
While diffusion models excel at generating high-quality images, prior work reports a significant performance gap between diffusion and autoregressive (AR) methods in language modeling.
S. Sahoo, Marianne Arriola, Yair Schiff, Aaron Gokaslan, Edgar Marroquin, Justin T Chiu, Alexander Rush, Volodymyr Kuleshov   +7 more
semanticscholar   +1 more source

Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion

Neural Information Processing Systems
This paper presents Diffusion Forcing, a new training paradigm where a diffusion model is trained to denoise a set of tokens with independent per-token noise levels.
Boyuan Chen, Diego Marti Monso, Yilun Du, Max Simchowitz, Russ Tedrake, Vincent Sitzmann   +5 more
semanticscholar   +1 more source

Diffusion of Innovations

, 1964
E. Rogers
semanticscholar   +1 more source

Diffusion of Innovations

, 2011
Ronald E. Rice
semanticscholar   +1 more source

Directed diffusion: a scalable and robust communication paradigm for sensor networks

ACM/IEEE International Conference on Mobile Computing and Networking, 2000
C. Intanagonwiwat, R. Govindan, D. Estrin   +2 more
semanticscholar   +1 more source

Absence of Diffusion in Certain Random Lattices

, 1958
P. Anderson
semanticscholar   +1 more source

Spin diffusion measurements : spin echoes in the presence of a time-dependent field gradient

, 1965
E. Stejskal, J. E. Tanner
semanticscholar   +1 more source