# Lapras: Latent Reasoning for Time Series Language Models

arXiv: https://arxiv.org/abs/2610.11111 · HTML: https://mlsanity.com/paper/2610.11111/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Time series reasoning, one of 17 directions in LLM reasoning.
- Builds on 32 of its 34 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM reasoning / [Time series reasoning](https://mlsanity.com/lr/time-series-reasoning/)
- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 30 of 32)

- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models](https://mlsanity.com/paper/2403.06764/) (2024)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [How Language Model Hallucinations Can Snowball](https://mlsanity.com/paper/2305.13534/) (2023)
- [CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation](https://mlsanity.com/paper/2502.21074/) (2025)
- [Large Language Models are Few-Shot Health Learners](https://mlsanity.com/paper/2305.15525/) (2023)
- [Small Models Struggle to Learn from Strong Reasoners](https://mlsanity.com/paper/2502.12143/) (2025)
- [Latent Visual Reasoning](https://mlsanity.com/paper/2509.24251/) (2025)
- [Monet: Reasoning in Latent Visual Space Beyond Images and Language](https://mlsanity.com/paper/2511.21395/) (2025)
- [Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data](https://mlsanity.com/paper/2401.06866/) (2024)
- [MIRAGE: The Illusion of Visual Understanding](https://mlsanity.com/paper/2603.21687/) (2026)
- [Grounded Chain-of-Thought for Multimodal Large Language Models](https://mlsanity.com/paper/2503.12799/) (2025)
- [Interleaved-Modal Chain-of-Thought](https://mlsanity.com/paper/2411.19488/) (2024)
- [LLM Latent Reasoning as Chain of Superposition](https://mlsanity.com/paper/2510.15522/) (2025)
- [ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset](https://mlsanity.com/paper/2506.20093/) (2025)
- [OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data](https://mlsanity.com/paper/2510.02410/) (2025)
- [Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals](https://mlsanity.com/paper/2412.09758/) (2024)
- [TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models](https://mlsanity.com/paper/2509.24803/) (2025)
- [Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step](https://mlsanity.com/paper/2406.16144/) (2024)
- [Adaptive Time Series Reasoning via Segment Selection](https://mlsanity.com/paper/2602.18645/) (2026)
- [Learning Transferable Sensor Models via Language-Informed Pretraining](https://mlsanity.com/paper/2603.11950/) (2026)
- [ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation](https://mlsanity.com/paper/2603.14326/) (2026)

## Abstract (arXiv)

Time Series Language Models (TSLMs) offer a promising path toward time series understanding by reasoning over temporal signals and producing natural language answers and explanations. A common approach is Chain-of-Thought (CoT), which generates step-by-step rationales linking relevant signal patterns to final answers. Although these models learn from reference CoT traces during post-training, generating faithful descriptions of input time series at inference remains challenging. Expressing high-dimensional, continuous temporal representations in discrete language tokens may cause the model to neglect task-relevant patterns or describe them inaccurately. Because later reasoning steps build on these descriptions, early errors propagate, leading to incorrect answers with plausible explanations that are inconsistent with the input signal. We propose Lapras (Latent Post-trained Reasoning Across Series), a post-training framework that equips TSLMs with latent reasoning. A model trained with Lapras reasons through a sequence of continuous thoughts in the joint time series-language space, producing text only for the final answer. It learns this through teacher-student self-distillation, where a teacher trained on CoT reference traces reasons explicitly through text. The student aligns its hidden states with the teacher's at the answer stage, transferring the teacher's reasoning ability into its latent computation. We evaluate Lapras across four TSLM backbones on five time series question answering benchmarks. Lapras improves average F1 by up to 10.79% over explicit CoT while generating 23.9x fewer tokens. Lapras's continuous thoughts can also be decoded into readable reasoning traces via standard language decoding, preserving textual explanations. Together, these results highlight Lapras as a promising post-training paradigm for efficient, effective, and interpretable TSLM reasoning.