Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling
It is proved that in-context learning extends further to data generation: frozen transformers can simulate iterative generative samplers from in-context samples, and it is proved that transformers can approximate an energy-based sampler.
Arman Adibi, Alireza Jafari, Mohammad Ghavamzadeh et al.
· 0 citations