Paper Detail

A Model with No Head and Many Thoughts

Nikita Koriagin, Yaroslav Aksenov, George Bredis, Gleb Gerasimov, Nikita Balagansky, Daniil Gavrilov

arxiv Score 10.3

Published 2026-08-31 · First seen 2026-09-01

General AI

Abstract

Large language models decode by projecting hidden states through a large vocabulary head at every step. This operation is computationally costly and forces all reasoning to be expressed in discrete tokens. We introduce Soft Latent Thinking, a method that replaces the LM head during reasoning with a lightweight projector, enabling autoregressive rollout in embedding space where reasoning steps remain continuous rather than tokenized. Experiments on DeepSeek-Qwen-1.5B and LLaMA-3.2-3B show that Soft Latent Thinking consistently improves pass@k across all k while reducing per-step compute during chain-of-thought. Our method achieves the highest pass@32 among all soft-thinking approaches, demonstrating that effective reasoning can be carried out in continuous space without discrete token generation.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{koriagin2026model,
  title = {A Model with No Head and Many Thoughts},
  author = {Nikita Koriagin and Yaroslav Aksenov and George Bredis and Gleb Gerasimov and Nikita Balagansky and Daniil Gavrilov},
  year = {2026},
  abstract = {Large language models decode by projecting hidden states through a large vocabulary head at every step. This operation is computationally costly and forces all reasoning to be expressed in discrete tokens. We introduce Soft Latent Thinking, a method that replaces the LM head during reasoning with a lightweight projector, enabling autoregressive rollout in embedding space where reasoning steps remain continuous rather than tokenized. Experiments on DeepSeek-Qwen-1.5B and LLaMA-3.2-3B show that So},
  url = {https://arxiv.org/abs/2608.31069},
  keywords = {cs.LG, cs.CL},
  eprint = {2608.31069},
  archiveprefix = {arXiv},
}

Metadata

{}