Lapras: Latent Reasoning for Time Series Language Models
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.
ProofPaper ↗
Key points
- Although these models learn from reference CoT traces during post-training, generating faithful descriptions of input time series at inference remains challenging.
- 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.
- We evaluate Lapras across four TSLM backbones on five time series question answering benchmarks.
Sources (1)
- [1]Lapras: Latent Reasoning for Time Series Language ModelsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 02:33 AM
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.
Although these models learn from reference CoT traces during post-training, generating faithful descriptions of input time series at inference remains challenging.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces
- Oct 8, 2026One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts
- Oct 8, 2026Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models
- Oct 7, 2026KDFP: A first-principles approach to knowledge distillation in large language models
- Oct 7, 2026MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
- Oct 7, 2026Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts