Author

Ke-Bin Peng

h-index 3 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 Oct 2026

Agent Skill Evolution: How Revisions Affect Coding Agents

Agent Skills, the SKILL.md files that tell an LLM coding agent how a project works, are revised like code, yet what a revision does to the agent is unknown. From 2,608 first/last revision pairs of 3,159 Skills, we characterize how Skills evolve and how they change together with the configuration of the agent's harness....

Jia-Jie Wang, Yu-Tong Zhao, Tian-Lin Li et al. · 0 citations

Preprint Aug 2026

GeoCache: Training-Free Acceleration of Multi-View Texture Diffusion via Geometric Delta Transport

Geometry-conditioned multi-view diffusion enables high-quality 3D texture generation, but its repeated per-view denoiser evaluations introduce substantial computational cost. Existing training-free accelerators primarily exploit temporal redundancy by reusing computation across denoising steps. In multi-view texturing,...

Haotang Li, Zhen-Yu Qi, Shaohan Wang et al. · 0 citations

#small language model Aug 2026

NavAI: an application-agnostic llm framework for navigation tasks in virtual reality environments

NavAI is an extensible navigation framework that leverages large language models (LLMs) to support both basic action commands and multi-step goal-oriented navigation through an application-agnostic screenshot-and-control interface and explores optimization strategies for virtual scene understanding and navigation goal...

Jiajie Wang, Sumesh Surendran Letha, M. DiGiovanni et al. · International Conference on... · 0 citations