Jude Tran

judetran's activity

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

upvoted a paper about 1 hour ago

ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training

Paper • 2609.00188 • Published 5 days ago • 46

upvoted a paper 2 days ago

StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing

Paper • 2608.24777 • Published 11 days ago • 16

upvoted 2 papers 3 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 4 days ago • 480

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published 10 days ago • 196

upvoted a paper 4 days ago

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

Paper • 2608.27456 • Published 9 days ago • 111

upvoted a paper 6 days ago

Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs

Paper • 2608.20492 • Published 16 days ago • 111

upvoted a paper 7 days ago

AutoSaddler: Automatic Harness Optimization with Durable Updates from Agent Execution Traces

Paper • 2608.23041 • Published 12 days ago • 64

upvoted a paper 8 days ago

CAFE: Self-Improving Search Agents Need Co-Evolving Feedback

Paper • 2608.24794 • Published 11 days ago • 6