GALA: Generation-Aware Cross-Modal Alignment for Text-to-Time-Series Synthesis
cs.CL, cs.LG
Submitted: 2026-08-13
Updated: 2026-10-13
Terminology
Sources
- Chronos-2: From Univariate to Universal Forecasting
- TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation
- Teaching Time Series to See and Speak: Forecasting with Aligned Visual and Textual Perspectives
- FlowTS: Time Series Generation via Rectified Flow
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- ConTSG-Bench: A Unified Benchmark for Conditional Time Series Generation
- Vector Quantized Time Series Generation with a Bidirectional Prior Model
- TTS-CGAN: A Transformer Time-Series Conditional GAN for Biosignal Data Augmentation
- Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era
- Representation Learning with Contrastive Predictive Coding
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- EmbeddingGemma: Powerful and Lightweight Text Representations
- CoCa: Contrastive Captioners are Image-Text Foundation Models
- CaTS-Bench: Can Language Models Describe Time Series?
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