Skip to content

Author

Wenqiang Zhang

We have 9 of 12 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 Oct 2026

VLA-$\Delta$: Learning Physical State Transition for Vision-Language-Action Models

This work constructs a large-scale pretraining dataset and derive physical state-transition annotations covering task-relevant semantics and visual motion changes, providing more direct supervision for continuous action generation.

Qian-Yu Lu, Jia-Run Li, Ce Zhang et al. · 0 citations
#artificial intelligence Preprint Oct 2026

VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse

VLA-Rolling is introduced, a lightweight inference framework that reuses action tails through three stages: action-tail inheritance, per-action confidence estimation, and confidence-guided refinement through renoising and denoising budget allocation, while the underlying VLA remains frozen.

Si-Cheng He, Ying-Ying Pan, Qiu-Ting Yu et al. · 0 citations
Preprint Sep 2026

EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks

Under matched backbones, EMem achieves the best overall performance among the evaluated memory systems and improves both open-source and proprietary models, while EMem-8B further improves over its backbone.

Li-Zhou Liang, Xin-Yue Zhong, Miao Pan et al. · 1 citation
#machine learning Preprint Sep 2026

Scaling Properties of Same-Family On-Policy Distillation

It is found that early OPD training dynamics uniformly exhibit a regular *useful-transfer* regime, in which held-out accuracy (the *gold score*, $G$) rises approximately linearly in $d=\sqrt{\mathrm{KL}(\pi_\theta \Vert \pi_{\mathrm{ref}})}$, the square root of token-level reverse KL divergence from the student initial...

Yun-Tai Bao, Qin-Feng Li, Guo-qing Jiang et al. · 0 citations
Jul 2026

AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction

AttriMem is proposed, an attribution-guided process-feedback framework for learning memory-construction policies with RL that outperforms retrieval-based, heuristic, and RL-based baselines, generalizes across benchmarks and answer models, and stabilizes RL optimization.

Qin-Feng Li, Yun-Tai Bao, Xinyang Yu et al. · 1 citation · ⚡1
#artificial intelligence Preprint Oct 2025

Compositional Machine Design as Program Synthesis with LLMs

Large language models (LLMs) have shown strong abilities in writing and revising programs, yet many program-synthesis benchmarks still evaluate programs in symbolic or digital environments. We introduce compositional machine design, a physically grounded form of program synthesis where machines are written as programs...

Wenqiang Zhang, Yang-Yi Huang, Wei-yu Liu et al. · 2 citations · ⚡1
Preprint Jul 2026

AttriMem: Attribution-Guided Process Feedback for Agent Memory Learning

Experiments show that AttriMem outperforms retrieval-based, heuristic, and RL-based baselines, generalizes across benchmarks and answer models, stabilizes RL optimization, and outperforms retrieval-based, heuristic, and RL-based baselines on long-horizon dialogue question answering.

Qin-Feng Li, Yun-Tai Bao, Xinyang Yu et al. · 0 citations
Preprint Aug 2026

SkillAligner: Treating Retrieved Skills as Adaptable Drafts at Execution Time

SkillAligner is proposed, a training-free execution-time skill adaptation framework that treats retrieved skills as adaptable drafts rather than fixed instructions that substantially improves task performance over existing skill-use baselines, reduces skill-induced regressions at the instance level, and lowers total in...

Qin-Feng Li, Dalin He, Yun-Tai Bao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.