Machine Heart
May 18, 2026 · Artificial Intelligence
Can Large Models Reason Deeply with Only a Few Thinking Tokens?
The paper introduces Heima, a framework that compresses chain‑of‑thought reasoning into a small set of abstract “thinking tokens” for multimodal large models, dramatically reducing generated tokens while preserving inference capability, and provides an adaptive interpreter to reconstruct human‑readable reasoning for analysis.
Chain-of-ThoughtEfficient Inferencelatent reasoning
0 likes · 12 min read