LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics

About this episode

This episode discusses the development of LLaTiSA, a model for time series reasoning that integrates visual and numerical data to improve understanding in large language models.

🤗 Upvotes: 77 | cs.AI Authors: Yueyang Ding, HaoPeng Zhang, Rui Dai, Yi Wang, Tianyu Zong, Kaikui Liu, Xiangxiang Chu Title: LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics Arxiv: http://arxiv.org/abs/2604.17295v1 Abstract: Comprehensive understanding of time series remains a significant challenge for Large Language Models (LLMs). Current research is hindered by fragmented task definitions and benchmarks with inherent ambiguities, precluding rigorous evaluation and the development of unified Time Series Reasoning Models(TSRMs). To bridge this gap, we formalize Time Series Reasoning (TSR) via a four-level taxonomy of increasing cognitive complexity. We introduce HiTSR, a hierarchical time series reasoning dataset comprising 83k samples with diverse task combinations and verified Chain-of-Thought (CoT) trajectories. Leveraging HiTSR, we propose LLaTiSA, a strong TSRM that integrates visualized patterns with precision-calibrated numerical tables to enhance the temporal perception of Vision-Language Models (VLMs). Through a multi-stage curriculum fine-tuning strategy, LLaTiSA achieves superior performance and exhibits robust…

People in this episode

Hosts: Jingwen Liang, Gengyu Wang

Topics covered

• time series reasoning
• visual perception
• cognitive complexity
• large language models
• data sets
• machine learning

Keywords

• LLaTiSA
• time series reasoning
• HiTSR
• cognitive complexity
• machine learning
• data sets
• visual perception

Mentioned in this episode

Organizations: Large Language Models, HiTSR, Vision-Language Models, LLaTiSA, GitHub

More episodes of Daily Paper Cast

• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments · June 13, 2026 · 24 min
• MiniMax Sparse Attention · June 13, 2026 · 26 min
• SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning · June 13, 2026 · 23 min
• InterleaveThinker: Reinforcing Agentic Interleaved Generation · June 13, 2026 · 21 min
• FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents · June 13, 2026 · 23 min
• Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? · June 13, 2026 · 20 min