ZhiWei LI

Aragonaa's activity

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

upvoted a paper 19 days ago

PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis

Paper • 2610.20538 • Published 27 days ago • 56

upvoted a paper 21 days ago

MOSS-Image Technical Report

Paper • 2610.23374 • Published 25 days ago • 93

upvoted 2 papers 25 days ago

Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents

Paper • 2610.21463 • Published 26 days ago • 24

Mosaic: Multi-Session Agentic Reinforcement Learning

Paper • 2610.22174 • Published 26 days ago • 60

upvoted a paper about 1 month ago

ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds

Paper • 2609.30199 • Published Sep 24 • 27

upvoted 5 papers about 2 months ago

RULER: Instance-aware Rubric Rewards for SVG Generation

Paper • 2609.25270 • Published Sep 21 • 74

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

Paper • 2609.22000 • Published Sep 18 • 73

CodeMidas: Scaling Agentic Coding RL Environments from Code Itself

Paper • 2609.22068 • Published Sep 18 • 116

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

Paper • 2609.17708 • Published Sep 15 • 47

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

Paper • 2609.13141 • Published Sep 11 • 67

upvoted 2 papers 2 months ago

T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks

Paper • 2609.11042 • Published Sep 10 • 65

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

Paper • 2609.06702 • Published Sep 6 • 22

upvoted a paper 3 months ago

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

Paper • 2607.28609 • Published Jul 30 • 69

upvoted 2 papers 4 months ago

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published Jul 3 • 82

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

Paper • 2601.01426 • Published Jan 4 • 25

upvoted 5 papers 5 months ago

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

Paper • 2606.17682 • Published Jun 16 • 26

Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning

Paper • 2606.13106 • Published Jun 11 • 23

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It

Paper • 2606.11052 • Published Jun 9 • 17

Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation

Paper • 2606.06428 • Published Jun 4 • 25

Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs

Paper • 2605.30501 • Published May 28 • 27