Ruiyan Liu

ruiyanliu's activity

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

upvoted a paper about 3 hours ago

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

Paper • 2610.15782 • Published 5 days ago • 29

upvoted a paper 1 day ago

Narrow Multimodal Fine-Tuning Can Induce Emergent Misalignment

Paper • 2609.35291 • Published 18 days ago • 26

upvoted a paper 2 days ago

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

Paper • 2610.02967 • Published 14 days ago • 41

upvoted a paper 3 days ago

AgentGarten: Code Worlds for Evolving Agents

Paper • 2610.12374 • Published 8 days ago • 133

upvoted 2 papers 4 days ago

CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use

Paper • 2610.09127 • Published 10 days ago • 22

Inverting Multi-Vector Visual Document Indices

Paper • 2610.09920 • Published 9 days ago • 28

upvoted 2 papers 5 days ago

AutoDataBench: A Data-centric Testbed for Accelerating Auto Research

Paper • 2609.40097 • Published 16 days ago • 50

Towards In-Parameter Memory Augmentation for Large Language Models

Paper • 2610.08630 • Published 10 days ago • 14

upvoted 3 papers 6 days ago

EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric Videos

Paper • 2609.39378 • Published 16 days ago • 74

CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?

Paper • 2610.07557 • Published 10 days ago • 76

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 15 days ago • 111

upvoted a paper 7 days ago

AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation

Paper • 2610.01218 • Published 15 days ago • 30

upvoted 2 papers 8 days ago

UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents

Paper • 2610.05622 • Published 12 days ago • 22

Video2Skill: From Streaming Experience to Reusable Embodied Skills

Paper • 2609.36691 • Published 17 days ago • 17

upvoted a paper 9 days ago

LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models

Paper • 2609.39071 • Published 16 days ago • 67

upvoted a paper 10 days ago

PixelUMM: Encoder-Free Unified Image and Video Understanding and Generation

Paper • 2609.38597 • Published 17 days ago • 34

upvoted a paper 11 days ago

CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding

Paper • 2609.40048 • Published 16 days ago • 16

upvoted a paper 12 days ago

Raven: The Harness of Harnesses for Composable Agentic Intelligence

Paper • 2609.33439 • Published 19 days ago • 595

upvoted 2 papers 13 days ago

IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking

Paper • 2609.29167 • Published 22 days ago • 22

TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces

Paper • 2609.33295 • Published 19 days ago • 72