Decoupling Perception from Description: Computation-Grounded Representation Alignment between Multivariate Time Series and Language
cs.LG
Submitted: 2026-08-05
Updated: 2026-09-19
Comments: 46 pages, 9 figures, including supplementary material. Submitted to AAAI 2027. Xinran Feng and Yi Xie contributed equally
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Chronos: Learning the Language of Time Series
- TimeSeriesExam: A time series understanding exam
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models
- Let's Verify Step by Step
- PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
- GPT-4o System Card
- gpt-oss-120b & gpt-oss-20b Model Card
- BEDTime: A Unified Benchmark for Automatically Describing Time Series
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Time Series Language Model for Descriptive Caption Generation
- Solving math word problems with process- and outcome-based feedback
- ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
- Qwen3 Technical Report
- Qwen2.5 Technical Report
- TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
- STaR: Bootstrapping Reasoning With Reasoning
- A Survey of Reinforcement Learning for Large Reasoning Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks