Tag
HALO introduces a hybrid adaptive latent refinement method for frozen language models that selectively applies second-stage refinement to a subset of tokens, achieving better performance than fixed refinement steps while using less compute.
Proposes ReLAR, a reinforcement-guided latent refinement framework that iteratively updates hidden representations in LLMs before decoding, improving reasoning reliability and efficiency compared to chain-of-thought methods.
LoopUS is a post-training framework that converts pretrained LLMs into looped architectures for improved reasoning performance via latent-refinement and adaptive early exiting. It addresses computational costs and capability preservation issues found in existing looped computation methods.