Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Wei Wu

Wei Wu

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

AI×3Distributed×2ML×1NLP×1Vision×1Software Eng.×1

Frequent co-authors

Daifeng Li1×
Huiqiang Jiang1×
Chengruidong Zhang1×
Xudong Guo1×
Jianhong Tu1×
Jianwei Zhang1×

Research Timeline

2026
When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime

A longitudinal study of silent failures in a personal-assistant agent runtime, identifying a new type of failure called 'fail-plausible' and proposing a defense framework.

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

This paper introduces LingBot-Video, a video pretraining paradigm for embodied intelligence using a DiT-based approach, Mixture-of-Experts framework, and extensive robot-oriented data.

Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks

This paper introduces an open-source framework for evaluating the efficacy of AI agents powered by open-weight large language models on data preparation tasks in research using locally deployable models.

D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?

The paper introduces D2K-Bench, a diagnostic benchmark to measure how effectively large language model agents translate expert design guidance into efficient GPU kernels.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.DCEmpiricalRecentOct 2, 2026

D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?

Daifeng Li, Huiqiang Jiang, Chengruidong Zhang, Wei Wu +5 more

The paper introduces D2K-Bench, a diagnostic benchmark to measure how effectively large language model agents translate expert design guidance into efficient GPU kernels.

View →
cs.AIcs.CLEmpirical
Recent
Jul 23, 2026

Agentic coding without the cloud: evaluating open-weight large language models on longitudinal data preparation tasks

Mack Nixon, Liam Wright, Yevgeniya Kovalchuk, Alison Fang-Wei Wu +3 more

This paper introduces an open-source framework for evaluating the efficacy of AI agents powered by open-weight large language models on data preparation tasks in research using locally deployable mode…

View →
cs.CVEmpiricalRecentJul 8, 2026

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Shuailei Ma, Jiaqi Liao, Xinyang Wang, Jingjing Wang +23 more

This paper introduces LingBot-Video, a video pretraining paradigm for embodied intelligence using a DiT-based approach, Mixture-of-Experts framework, and extensive robot-oriented data.

View →
cs.SEcs.AIcs.DCEmpiricalRecentJun 12, 2026

When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime

Wei Wu

A longitudinal study of silent failures in a personal-assistant agent runtime, identifying a new type of failure called 'fail-plausible' and proposing a defense framework.

View →