💼 Hiring
Zhi Zhou
WNJXYK
AI & ML interests
Test-Time Intelligence: Test-Time Adaptation, Test-Time Scaling, and Test-Time Learning
Recent Activity
upvoted a paper 18 days ago
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness upvoted a paper 18 days ago
TradingAgents: Multi-Agents LLM Financial Trading Framework upvoted a paper about 1 month ago
Scaling Large Reasoning Models beyond Human Supervision: A Path toward SuperintelligenceOrganizations
-
Training-Free Group Relative Policy Optimization
Paper • 2510.08191 • Published • 46 -
A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
Paper • 2510.15444 • Published • 151 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 49 -
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Paper • 2504.15785 • Published • 22
-
Training-Free Group Relative Policy Optimization
Paper • 2510.08191 • Published • 46 -
A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
Paper • 2510.15444 • Published • 151 -
Reasoning with Sampling: Your Base Model is Smarter Than You Think
Paper • 2510.14901 • Published • 49 -
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Paper • 2504.15785 • Published • 22
Sampled Reasoning Paths for NeurIPS 2025 Paper: A Theoretical Study on
Bridging Internal Probability and Self-Consistency for LLM Reasoning