Qiushi

QiushiSun's activity

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

upvoted a paper 16 days ago

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

Paper • 2610.20538 • Published 25 days ago • 56

upvoted a paper 18 days ago

MOSS-Image Technical Report

Paper • 2610.23374 • Published 23 days ago • 93

upvoted a paper 20 days ago

OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools

Paper • 2610.14157 • Published 30 days ago • 48

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

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

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published Sep 14 • 56

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 • 66

upvoted a paper 2 months ago

FrontierChallenge: Evaluating Scientific Workflow Completion

Paper • 2608.24979 • Published Aug 25 • 154

upvoted a collection 3 months ago

OSReward & OS-Shepherd

Collection

5 items • Updated Aug 19 • 3

upvoted 2 papers 3 months ago

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

Paper • 2607.28609 • Published Jul 30 • 69

Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking

Paper • 2607.23514 • Published Jul 26 • 13

upvoted a collection 4 months ago

ScienceBoard

Collection

3 items • Updated Aug 5 • 2

upvoted a paper 5 months ago

Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence

Paper • 2606.15932 • Published Jun 16 • 37

upvoted 3 papers 6 months ago

WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

Paper • 2605.25874 • Published May 25 • 76

EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

Paper • 2605.18703 • Published May 18 • 51

OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis

Paper • 2604.15093 • Published Apr 16 • 30

upvoted 2 papers 7 months ago

How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

Paper • 2604.14164 • Published Mar 23 • 35

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping

Paper • 2604.11297 • Published Apr 13 • 144