ZhiWei LI

Aragonaa's activity

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

upvoted a paper 3 days ago

RULER: Instance-aware Rubric Rewards for SVG Generation

Paper • 2609.25270 • Published 6 days ago • 86

upvoted 2 papers 5 days ago

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

Paper • 2609.22000 • Published 9 days ago • 77

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published 9 days ago • 132

upvoted a paper 9 days ago

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Paper • 2609.17708 • Published 12 days ago • 73

authored a paper 12 days ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published 16 days ago • 65

liked a model 12 days ago

tencent/Simple-Attention-Sparsification

Text Generation • Updated 12 days ago • 8

published a model 12 days ago

tencent/Simple-Attention-Sparsification

Text Generation • Updated 12 days ago • 8

updated a model 12 days ago

tencent/Simple-Attention-Sparsification

Text Generation • Updated 12 days ago • 8

upvoted a paper 12 days ago

SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking

Paper • 2609.13141 • Published 16 days ago • 65

upvoted 2 papers 15 days ago

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

Paper • 2609.11042 • Published 17 days ago • 63

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

Paper • 2609.06702 • Published 21 days ago • 26

upvoted a paper about 2 months ago

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models

Paper • 2607.28609 • Published Jul 30 • 75

upvoted a paper 3 months ago

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published Jul 3 • 85

liked a model 3 months ago

tencent/Hy3

Text Generation • 299B • Updated Jul 20 • 102k • • 971

upvoted a paper 3 months ago

SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving

Paper • 2601.01426 • Published Jan 4 • 25

liked a model 3 months ago

Lego-X/SWE-Lego-Qwen3-8B

308k • Updated Jan 13 • 407 • 8

liked a dataset 3 months ago

SWE-bench/SWE-bench_Verified

Benchmark • Updated Aug 16 • 500 • 125k • 166

liked a model 3 months ago

LARK-Lab/EnvFactory-8B

Text Generation • 8B • Updated May 20 • 177 • 1

upvoted a paper 3 months ago

From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning

Paper • 2606.17682 • Published Jun 16 • 26

liked a dataset 3 months ago

zai-org/LongAlign-10k

Viewer • Updated Feb 22, 2024 • 9.89k • 5.73k • 100