Lapras: Latent Reasoning for Time Series Language Models
cs.CL, cs.LG
Submitted: 2026-10-08
Updated: 2026-10-08
Code: https://github.com/yuc0805/Lapras
Terminology
Sources
- Flamingo: a Visual Language Model for Few-Shot Learning
- Chronos: Learning the Language of Time Series
- MIRAGE: The Illusion of Visual Understanding
- Emerging Properties in Self-Supervised Vision Transformers
- An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
- Learning Transferable Sensor Models via Language-Informed Pretraining
- A decoder-only foundation model for time-series forecasting
- LLM Latent Reasoning as Chain of Superposition
- Interleaved-Modal Chain-of-Thought
- MOMENT: A Family of Open Time-series Foundation Models
- Large Language Models Are Zero-Shot Time Series Forecasters
- TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
- Training Large Language Models to Reason in a Continuous Latent Space
- Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data
- OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Latent Visual Reasoning
- Small Models Struggle to Learn from Strong Reasoners
- Large Language Models are Few-Shot Health Learners
- Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering