# Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space

arXiv: https://arxiv.org/abs/2512.24617 · HTML: https://mlsanity.com/paper/2512.24617/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 18 of its 21 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer](https://mlsanity.com/paper/2203.03466/) (2022)
- [Query-Key Normalization for Transformers](https://mlsanity.com/paper/2010.04245/) (2020)
- [Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset](https://mlsanity.com/paper/2412.02595/) (2024)
- [OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models](https://mlsanity.com/paper/2411.04905/) (2024)
- [Large Concept Models: Language Modeling in a Sentence Representation Space](https://mlsanity.com/paper/2412.08821/) (2024)
- [Dynamic Chunking for End-to-End Hierarchical Sequence Modeling](https://mlsanity.com/paper/2507.07955/) (2025)
- [MegaMath: Pushing the Limits of Open Math Corpora](https://mlsanity.com/paper/2504.02807/) (2025)
- [Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model](https://mlsanity.com/paper/2404.04167/) (2024)

## Built on by (most cited first, 17 of 17)

- [The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook](https://mlsanity.com/paper/2604.02029/) (2026)
- [SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion](https://mlsanity.com/paper/2602.11698/) (2026)
- [Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models](https://mlsanity.com/paper/2602.08984/) (2026)
- [ConceptMoE: Adaptive Token-to-Concept Compression for Implicit Compute Allocation](https://mlsanity.com/paper/2601.21420/) (2026)
- [Proxy Compression for Language Modeling](https://mlsanity.com/paper/2602.04289/) (2026)
- [DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking](https://mlsanity.com/paper/2603.06351/) (2026)
- [Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models](https://mlsanity.com/paper/2605.09630/) (2026)
- [From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models](https://mlsanity.com/paper/2607.26504/) (2026)
- [A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM](https://mlsanity.com/paper/2609.07821/) (2026)
- [Improving Test-Time Scaling with Adaptive Looped Transformers](https://mlsanity.com/paper/2609.35748/) (2026)
- [Density-aware Soft Context Compression with Semi-Dynamic Compression Ratio](https://mlsanity.com/paper/2603.25926/) (2026)
- [SuperThoughts: Reasoning Tokens in Superposition](https://mlsanity.com/paper/2606.13862/) (2026)
- [AdaMTP: An Adaptive Training Paradigm for Multi-Token Prediction](https://mlsanity.com/paper/2608.00434/) (2026)
- [NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction](https://mlsanity.com/paper/2609.10715/) (2026)
- [Information-Time Proximal Policy Optimization](https://mlsanity.com/paper/2609.24380/) (2026)
- [One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns](https://mlsanity.com/paper/2610.14074/) (2026)
- [Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation](https://mlsanity.com/paper/2610.14162/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating computation to semantically critical transitions. We propose Dynamic Large Concept Models (DLCM), a hierarchical language modeling framework that learns semantic boundaries from latent representations and shifts computation from tokens to a compressed concept space where reasoning is more efficient. DLCM discovers variable-length concepts end-to-end without relying on predefined linguistic units. Hierarchical compression fundamentally changes scaling behavior. We introduce the first compression-aware scaling law, which disentangles token-level capacity, concept-level reasoning capacity, and compression ratio, enabling principled compute allocation under fixed FLOPs. To stably train this heterogeneous architecture, we further develop a decoupled μP parametrization that supports zero-shot hyperparameter transfer across widths and compression regimes. At a practical setting (R=4, corresponding to an average of four tokens per concept), DLCM reallocates roughly one-third of inference compute into a higher-capacity reasoning backbone, achieving a +2.69% average improvement across 12 zero-shot benchmarks under matched inference FLOPs.