technique

autoregressive transformer

techniqueactiveautoregressive-transformer-ed2d7bb8·1 events·first seen 1mo ago

Aliases: autoregressive transformer

Co-occurring entities

UC Berkeley information-driven imaging framework mutual information NeurIPS 2025 PixelCNN

More like this (12)

Graph Transformer transformer-based neural renderer feed-forward transformer Channel-wise Autoregressive (CAR)TRL (Transformer Reinforcement Learning)Sparse Transformer Autoformer causal transformer Differential Transformer Decision Transformer Variable-Width Transformers Linear Diffusion Transformer

Recent events (1)

5Berkeley Ai Research (Bair) Blog·1mo ago·source ↗

Information-Driven Design of Imaging Systems

Researchers from Berkeley present a framework for evaluating and optimizing imaging systems based on mutual information content rather than traditional metrics like resolution or SNR, published at NeurIPS 2025. The method estimates mutual information directly from noisy measurements using known noise physics and learned probabilistic models (including transformers and PixelCNN), avoiding the need for task-specific decoders. Validated across four domains—color photography, radio astronomy, lensless imaging, and microscopy—the information metric predicts downstream decoder performance and enables hardware optimization with less compute and memory than end-to-end neural approaches.

Evaluation and Benchmarking Inference Economics UC Berkeley information-driven imaging framework mutual information +3 more