Instruction-Guided Autoregressive Neural Network Parameter Generation
This addresses the challenge of model adaptability and transfer learning for AI researchers, offering a tool for pretrained weight retrieval and fine-tuning, though it appears incremental as it builds on existing autoregressive and VQ-VAE techniques.
The authors tackled the problem of generating neural network parameters conditioned on task descriptions and architecture specifications, proposing IGPG, an autoregressive framework that achieves competitive or superior performance to state-of-the-art methods, with improvements in scalability and efficiency for large architectures.
Learning to generate neural network parameters conditioned on task descriptions and architecture specifications is pivotal for advancing model adaptability and transfer learning. Existing methods especially those based on diffusion models suffer from limited scalability to large architectures, rigidity in handling varying network depths, and disjointed parameter generation that undermines inter-layer coherence. In this work, we propose IGPG (Instruction Guided Parameter Generation), an autoregressive framework that unifies parameter synthesis across diverse tasks and architectures. IGPG leverages a VQ-VAE and an autoregressive model to generate neural network parameters, conditioned on task instructions, dataset, and architecture details. By autoregressively generating neural network weights' tokens, IGPG ensures inter-layer coherence and enables efficient adaptation across models and datasets. Operating at the token level, IGPG effectively captures complex parameter distributions aggregated from a broad spectrum of pretrained models. Extensive experiments on multiple vision datasets demonstrate that IGPG consolidates diverse pretrained models into a single, flexible generative framework. The synthesized parameters achieve competitive or superior performance relative to state-of-the-art methods, especially in terms of scalability and efficiency when applied to large architectures. These results underscore ICPG potential as a powerful tool for pretrained weight retrieval, model selection, and rapid task-specific fine-tuning.