Pretrained LLMs adapted via convolutional projections and LoRA act as efficient frozen backbones for sensor-based human activity recognition, delivering strong data efficiency and cross-dataset transfer.
Title resolution pending
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
TS-Agent is an agentic framework that uses LLMs only for evidence-based reasoning while delegating extraction to raw time series tools, matching or exceeding baselines on four benchmarks with largest gains on reasoning tasks.
An RL agent learns domain re-weighting policies from evaluation feedback to improve balanced performance in continual pre-training of LLMs across source and target domains.
TSAG lets LLMs use external tools for financial time series analysis, with a new benchmark showing capable agents achieve near-perfect tool accuracy and minimal hallucination.
A literature survey that taxonomizes methods, datasets, and evaluation practices for natural language interfaces to geospatial and temporal databases while identifying recurring trends and future directions.
BEDTime benchmark tests 17 models on describing time series structure and finds vision-language models outperform dedicated time-series-language models and language-only approaches, with all models fragile to robustness tests.
Supervised fine-tuning of pretrained LLMs on offline trajectories yields better few-shot sequential decision-making than in-context-only baselines, with a theoretical suboptimality bound derived for linear MDPs by interpreting attention as Q-function estimation.
A physics-aware LLM framework generates high-fidelity probabilistic wind power scenarios under extreme icing by enforcing physical constraints like power limits and ramp rates on trajectories from real SCADA data.
citing papers explorer
-
BEDTime: A Unified Benchmark for Automatically Describing Time Series
BEDTime benchmark tests 17 models on describing time series structure and finds vision-language models outperform dedicated time-series-language models and language-only approaches, with all models fragile to robustness tests.