Ruiyan Liu

ruiyanliu's activity

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

upvoted 4 papers 3 days ago

Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures

Paper • 2610.28887 • Published 7 days ago • 45

Memory-Centric Continual Learning for AI Agents

Paper • 2610.29357 • Published 6 days ago • 43

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Paper • 2610.26828 • Published 8 days ago • 102

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

Paper • 2610.28763 • Published 7 days ago • 29

upvoted 2 papers 4 days ago

BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References

Paper • 2610.23986 • Published 13 days ago • 40

Predicting Privileged Information Effectiveness for On-Policy Self-Distillation

Paper • 2610.22512 • Published 12 days ago • 10

upvoted 2 papers 5 days ago

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

Paper • 2610.14157 • Published 18 days ago • 62

LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets

Paper • 2610.09872 • Published 20 days ago • 62

upvoted 3 papers 7 days ago

HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution

Paper • 2610.02089 • Published 26 days ago • 36

τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions

Paper • 2610.19560 • Published 12 days ago • 28

Long-Horizon RL Needs Muon

Paper • 2610.20256 • Published 13 days ago • 30

upvoted a paper 8 days ago

Learning How to Remember: Memory Modality Selection for GUI Agents

Paper • 2610.17928 • Published 14 days ago • 42

upvoted 2 papers 9 days ago

The value of information and the emergence of communication in evolved e-puck robots

Paper • 2610.13118 • Published 18 days ago • 20

GreenWAM: A World Foundation Model for Robotics

Paper • 2610.18774 • Published 14 days ago • 103

upvoted a paper 10 days ago

Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping

Paper • 2610.15782 • Published 16 days ago • 31

upvoted a paper 11 days ago

Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment

Paper • 2609.35291 • Published 29 days ago • 30

upvoted a paper 12 days ago

Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards

Paper • 2610.02967 • Published 25 days ago • 44

upvoted a paper 13 days ago

AgentGarten: Code Worlds for Evolving Agents

Paper • 2610.12374 • Published 19 days ago • 296

upvoted 2 papers 14 days ago

CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use

Paper • 2610.09127 • Published 21 days ago • 24

Inverting Multi-Vector Visual Document Indices

Paper • 2610.09920 • Published 20 days ago • 29