Time-Continuous Modeling for Temporal Affective Pattern Recognition in LLMs
Not on the map. Why?
Abstract (arXiv)
This paper introduces a dataset and conceptual framework for LLMs to mimic real world emotional dynamics through time and in-context learning leveraging physics-informed neural network, opening a possibility for interpretable dialogue modeling.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 24 references that are in the map. First posted on arXiv 18 Jan 2026.
Builds on
11 of 24 references.
References · 11
- 2024Qwen2.5 Technical Reportcited by 4,942
- 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
- 2017Mixed Precision Trainingcited by 1,156
- 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 554
- 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
- 2023In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steeringcited by 245
- 2020Liquid Time-constant Networkscited by 161
- 2023Fairness-guided Few-shot Prompting for Large Language Modelscited by 53
- 2023A Practical Survey on Zero-shot Prompt Design for In-context Learningcited by 49
- 2024Modeling Emotional Trajectories in Written Stories Utilizing Transformers and Weakly-Supervised Learningcited by 4
- 2024The Computational Mechanisms of Detached Mindfulnesscited by 1
Built on by
Not cited yet.