Author

Kai Chen

h-index 5 View on Semantic Scholar

We have 2 of 13 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Turn-level Multiscale Density Ratio Estimation for LLM Agents

Turn-level Multiscale Density Ratio Estimation (tlm-DRE), which assigns different weights on corresponding turns and proposes asymmetric token-level training based on the positive-negative space gaps across multiple turns of tasks, enables LLMs to perform robustly in multi-turn reasoning tasks with both in-domain and o...

Zi-Shuo Zhao, Kai Chen, Aoao Li et al. · 0 citations

#artificial intelligence May 2026

IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation

IntentVLA is introduced, a history-conditioned VLA framework that encodes recent visual observations into a compact short-horizon intent representation and uses it to condition chunk generation and improves rollout stability and outperforms strong VLA baselines.

Shijie Lian, Bin Yu, Xiaopeng Lin et al. · arXiv.org · 6 citations