joint-training

Tag

Cards List
#joint-training

Chronicle: A Multimodal Foundation Model for Joint Language and Time Series Understanding

arXiv cs.LG · 2026-05-21 Cached

Chronicle is a 324M-parameter decoder-only transformer pretrained from scratch on both natural language and time series, achieving competitive performance on NLU and time series classification tasks, and setting new state-of-the-art for frozen-embedding time series classification on UCR/UEA datasets.

0 favorites 0 likes
#joint-training

ICRL: Learning to Internalize Self-Critique with Reinforcement Learning

arXiv cs.AI · 2026-05-18 Cached

This paper introduces ICRL, a framework that jointly trains a solver and critic with reinforcement learning to internalize critique guidance, enabling the solver to improve without external critique. It uses distribution calibration and role-wise group advantage estimation, achieving 6-7 point gains over GRPO on agentic and mathematical reasoning tasks.

0 favorites 0 likes
← Back to home

Submit Feedback