Lapras (Latent Post-trained Reasoning Across Series) is a post-training framework that equips time series language models (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 from reference chain-of-thought (CoT) traces. This repository holds the 15 Lapras checkpoints reported in the paper: three TSLM backbones, each finetuned separately on five time series question answering tasks. Each backbone folder has one checkpoint per task: laprasecg, laprassleep, laprashar, laprastsr, laprasengine. A…
Independent publisher
Leo Chen
leochen085
Models in Library1
Datasets in Library0
Models on Hugging Face3
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.