Yaorui SHI

yrshi's activity

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

upvoted a paper 3 days ago

SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation

Paper • 2608.02287 • Published 10 days ago • 31

upvoted a paper 6 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 7 days ago • 92

upvoted 5 papers 13 days ago

CAST: Game Solvers as Turn-Level Teachers for LLM Agents

Paper • 2607.25308 • Published 16 days ago • 41

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Paper • 2607.26784 • Published 15 days ago • 28

MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing

Paper • 2607.27616 • Published 14 days ago • 39

Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation

Paper • 2607.27816 • Published 14 days ago • 34

BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms

Paper • 2607.26497 • Published 14 days ago • 50

upvoted a paper 23 days ago

HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement

Paper • 2607.18217 • Published 24 days ago • 61

upvoted 3 papers 28 days ago

Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation

Paper • 2607.05382 • Published Jul 9 • 88

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published Jul 13 • 85

SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding

Paper • 2607.10400 • Published Jul 11 • 71

upvoted 2 papers 30 days ago

EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis

Paper • 2601.05808 • Published Jan 9 • 38

Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading

Paper • 2607.08964 • Published Jul 9 • 77

upvoted a paper about 1 month ago

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Paper • 2607.02255 • Published Jul 2 • 68

upvoted a collection about 2 months ago

OpenThinker-Agent2

Collection

OpenThinker-Agent2: agentic SFT/RL datasets and 8B/32B models (cold-start SFT, RL, and the OpenThinkerAgent-32B release). • 11 items • Updated Jun 11 • 10

upvoted 2 papers about 2 months ago

DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation

Paper • 2606.26058 • Published Jun 24 • 67

FastContext: Training Efficient Repository Explorer for Coding Agents

Paper • 2606.14066 • Published Jun 12 • 95

upvoted 3 papers 2 months ago

On the Geometry of On-Policy Distillation

Paper • 2606.07082 • Published Jun 5 • 75

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 388

Rethinking Continual Experience Internalization for Self-Evolving LLM Agents

Paper • 2606.04703 • Published Jun 3 • 26