Zheng Wu

wuuuuuz's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 8 papers about 5 hours ago

LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition

Paper • 2605.24005 • Published May 30

Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents

Paper • 2505.14418 • Published Jun 15

ColorEcosystem: Powering Personalized, Standardized, and Trustworthy Agentic Service in massive-agent Ecosystem

Paper • 2510.21566 • Published Oct 27, 2025

Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation

Paper • 2511.22235 • Published Mar 4

OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents

Paper • 2604.24348 • Published Apr 27

Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents

Paper • 2605.28629 • Published May 27

Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning

Paper • 2601.03641 • Published Apr 11

GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents

Paper • 2505.12842 • Published Nov 22, 2025

authored 5 papers about 12 hours ago

MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft

Paper • 2605.30931 • Published May 29 • 10

Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning

Paper • 2607.28478 • Published Jul 30 • 6

Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation

Paper • 2607.28439 • Published Jul 30

UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

Paper • 2608.27456 • Published Aug 27 • 55

Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents

Paper • 2611.03092 • Published 2 days ago • 15

upvoted a paper about 16 hours ago

Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents

Paper • 2611.03092 • Published 2 days ago • 15

submitted a paper to Daily Papers about 16 hours ago

Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents

Paper • 2611.03092 • Published 2 days ago • 15

published a dataset 6 days ago

wuuuuuz/Jev-Agent-Workflows

Updated 6 days ago • 31

upvoted 2 papers 12 days ago

Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds

Paper • 2610.28698 • Published 15 days ago • 73

SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

Paper • 2610.26659 • Published 16 days ago • 102

upvoted a paper 15 days ago

More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning

Paper • 2610.19789 • Published 21 days ago • 43

upvoted a paper 2 months ago

What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents

Paper • 2608.27260 • Published Aug 27 • 74