Author

Zhi-Peng Zhang

h-index 5 View on Semantic Scholar

We have 3 of 16 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.

Preprint Sep 2026

RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents

Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker than these numbers suggest. We trace this illusion to a structural property we term low scene entropy: when a visual scene admits only one valid task, language becomes redundant and a policy can score h...

Chang Guo, Yu-Kun Xie, Bo-Han Tan et al. · 0 citations

Jul 2026

Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool

Long-context LLM training suffers from a load-balancing problem that sequence packing does not solve. Packing samples into fixed-token sequences balances memory and linear-cost operators, but the dominant attention cost scales with the sum of squared sequence lengths. Thus, equally sized packed sequences drawn from a l...

Yan Wang, Xiu-Long Yuan, Kaiming Yang et al. · arXiv.org · 1 citation

Preprint Aug 2026

Grounded Semantic Re-Binding for Robust Instruction Generalization in Vision-Language-Action Models

This work demonstrates that robust semantic grounding can be achieved through elegant structural design, bypassing the inefficient brute-force data scaling paradigm and introduces ParaVLA, a natively decoupled 0.33B-parameter model exhibiting near-perfect robustness to instruction rewording.

Zhao-Kai Yin, Zhi-Peng Zhang · 0 citations