# Think Sparse, Predict Dense: Continuous Thought Machines for Image Super-Resolution

arXiv: https://arxiv.org/abs/2607.18856 · HTML: https://mlsanity.com/paper/2607.18856/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 11 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network](https://mlsanity.com/paper/1803.08664/) (2018)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [MambaIRv2: Attentive State Space Restoration](https://mlsanity.com/paper/2411.15269/) (2024)
- [Continuous Thought Machines](https://mlsanity.com/paper/2505.05522/) (2025)
- [CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2503.06896/) (2025)

## Abstract (arXiv)

Continuous Thought Machines introduce an internal temporal dimension in which neuron-level histories and synchronization-derived representations evolve over a sequence of thought ticks. Extending this mechanism to dense visual prediction is non-trivial, because tasks such as image super-resolution require spatial evidence to remain available at every output location rather than being compressed into a single global representation. In the proposed window-level use of CTM, the thought dynamics produce a compact summary representation for each local window. DQ-CTM transforms this compact thought representation into window-aligned dense queries through a structured low-rank, parameter-efficient compact-to-dense query mechanism. Each position within a window receives its own query, while shared thought dynamics progressively refine the dense representation across ticks. In its super-resolution instantiation, termed ThinkSR, encoded feature maps are partitioned into local visual windows without token pooling, restored to the original feature field after shared refinement, and decoded into a high-resolution image. Preliminary experiments under a fixed four-tick training horizon reveal a progressive reconstruction trajectory. PSNR-Y increases from 28.1045 dB at T=0 to 30.2817 dB at T=4, while PSNR-RGB increases from 26.6271 dB to 28.7781 dB and the mean ℓ1 error decreases from 0.034602 to 0.023545. All 100 evaluated images improve from T=1 to T=4. These initial results establish the feasibility of sparse latent thought for dense spatial reconstruction and motivate broader continuous-thought architectures for dense vision.