← Search

Shixiang Song

2 accepted papers

2026

PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space

ICML 2026spotlight

The remarkable success of Chain-of-Thought (CoT), which enhances performance by scaling generation steps at test-time, inspires us to ask: can we leverage a similar scaling of computational steps during pretraining to improve the generation of each individual token? To address this, we propose a nov…

Cited by 0SourceScholar
2026

PonderLM: Pretraining Language Models to Ponder in Continuous Space

ICLR 2026poster

Humans ponder before articulating complex sentence elements, enabling deeper cognitive processing through focused effort. In this work, we introduce this pondering process into language models by repeatedly invoking the forward process within a single token generation step. During pondering, instead…

Cited by 0SourcecodeScholar