zhiyuan zeng

zyzeng's activity

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

upvoted a paper 2 days ago

Reverse-Engineered Reasoning for Open-Ended Generation

Paper • 2509.06160 • Published 4 days ago • 129

upvoted a paper 3 days ago

WideSearch: Benchmarking Agentic Broad Info-Seeking

Paper • 2508.07999 • Published about 1 month ago • 106

upvoted a paper 6 days ago

Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?

Paper • 2509.04292 • Published 7 days ago • 53

upvoted a paper 7 days ago

UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

Paper • 2509.02544 • Published 9 days ago • 112

upvoted a paper 15 days ago

TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

Paper • 2508.17445 • Published 18 days ago • 78

upvoted a paper 21 days ago

FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

Paper • 2508.11987 • Published 26 days ago • 67

upvoted a collection 5 months ago

Llama Nemotron Feedback-Edit Inference-Time Scaling

Collection

Novel ITS approach for open-ended tasks - No. 1 on Arena Hard on 18 Mar 2025 • 5 items • Updated 9 days ago • 5

upvoted a paper 6 months ago

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning

Paper • 2503.10480 • Published Mar 13 • 54

upvoted a paper 7 months ago

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?

Paper • 2502.12215 • Published Feb 17 • 16