Megadose AI progress, ranked and analyzed.

Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling

· ArXiv · AI/CL/LG ·
The paper argues that frozen transformers can act as generative samplers using only examples in the prompt.

The authors prove constructions where attention computes responsibility weights and empirical averages, while feedforward layers carry out Euler-style sampler updates. They cover closed-form diffusion, smoothed diffusion, and an approximation to energy-based sampling. In experiments on semantic-topic prompts, hidden states show a two-stage pattern: toward a uniform spherical reference, then back to topic-specific structure near the output. ArXiv · AI/CL/LG's note

score 6

Categories: Research