Reinforcement learning with a composite reward lifts Qwen2.5-VL-3B to 75.29% average accuracy on TIMERBED, above prompt-based GPT-4o and classical time-series baselines.
Tslanet: Rethinking transformers for time series representation learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TimeMaster: Training Time-Series Multimodal LLMs to Reason via Reinforcement Learning
Reinforcement learning with a composite reward lifts Qwen2.5-VL-3B to 75.29% average accuracy on TIMERBED, above prompt-based GPT-4o and classical time-series baselines.