Rui Sun

ThreeSR's activity

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

upvoted 9 papers 1 day ago

Information-Aware KV Cache Compression for Long Reasoning

Paper • 2606.26875 • Published 20 days ago • 12

Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity

Paper • 2607.00248 • Published 15 days ago • 31

TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents

Paper • 2606.28480 • Published 19 days ago • 48

Qwen-Image-2.0-RL Technical Report

Paper • 2606.27608 • Published 20 days ago • 50

Agentic Abstention: Do Agents Know When to Stop Instead of Act?

Paper • 2606.28733 • Published 18 days ago • 147

OpenCoF: Learning to Reason Through Video Generation

Paper • 2607.08763 • Published 6 days ago • 21

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks

Paper • 2607.08768 • Published 6 days ago • 32

Vision as Unified Multimodal Generation

Paper • 2607.06560 • Published 8 days ago • 45

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published 5 days ago • 52

upvoted a paper 18 days ago

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

Paper • 2606.26907 • Published 20 days ago • 49

upvoted a paper 20 days ago

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published 22 days ago • 148

upvoted 3 papers 23 days ago

DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch

Paper • 2606.10728 • Published Jun 9 • 34

Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions

Paper • 2606.09076 • Published Jun 8 • 65

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 378

upvoted 2 papers about 1 month ago

OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents

Paper • 2606.02031 • Published Jun 1 • 21

PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

Paper • 2606.03264 • Published Jun 2 • 25

upvoted 4 papers about 2 months ago

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Paper • 2605.12500 • Published May 12 • 194

HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents

Paper • 2605.07177 • Published May 8 • 63

Teaching Language Models to Think in Code

Paper • 2605.07237 • Published May 11 • 31

From Web to Pixels: Bringing Agentic Search into Visual Perception

Paper • 2605.12497 • Published May 12 • 14