discrete-representations

Proposes HybridCodec, a novel framework combining temporally compressed discrete tokens with continuous residuals to improve speaker characteristic retention in speech language models, reducing autoregressive steps while maintaining quality.

ViQ presents a visual quantization framework that balances semantic richness and detail preservation in discrete representations, enabling efficient multimodal training with native-resolution inputs by using text-aligned pre-training and proximal representation learning.

ARM presents a unified autoregressive framework for image understanding, generation, and editing using discrete semantic tokenization and reinforcement learning optimization, showing cross-task synergy.