Shaobai Jiang

shaobaij's activity

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

upvoted 7 papers about 13 hours ago

Reasoning Quality Emerges Early: Data Curation for Reasoning Models

Paper • 2606.26797 • Published 25 days ago • 1

ASPIRE: Agentic /Skills Discovery for Robotics

Paper • 2607.00272 • Published 20 days ago • 24

Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs

Paper • 2606.32032 • Published 20 days ago • 29

AutoMem: Automated Learning of Memory as a Cognitive Skill

Paper • 2607.01224 • Published 19 days ago • 21

Towards Automating Scientific Review with Google's Paper Assistant Tool

Paper • 2606.28277 • Published 24 days ago • 9

MCP Server Architecture Patterns for LLM-Integrated Applications

Paper • 2606.30317 • Published 21 days ago • 1

A Sovereign, Open-Source Foundation Model for German and English

Paper • 2607.09424 • Published 10 days ago • 9

upvoted 4 papers 1 day ago

RoboTTT: Context Scaling for Robot Policies

Paper • 2607.15275 • Published 4 days ago • 18

MemoHarness: Agent Harnesses That Learn from Experience

Paper • 2607.14159 • Published 6 days ago • 1

Self-Improvements in Modern Agentic Systems: A Survey

Paper • 2607.13104 • Published 6 days ago • 26

From Foundation to Application: Improving VLA Models in Practice

Paper • 2607.06403 • Published 13 days ago • 20

upvoted 3 papers 2 days ago

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

Paper • 2607.08964 • Published 11 days ago • 74

Video Generation Models are General-Purpose Vision Learners

Paper • 2607.09024 • Published 10 days ago • 80

UniVR: Thinking in Visual Space for Unified Visual Reasoning

Paper • 2607.12800 • Published 6 days ago • 28

upvoted a paper 3 days ago

Understanding Why Language Models Hallucinate: Testing Reasoning Against Priors

Paper • 2607.00447 • Published 19 days ago • 1

upvoted 5 papers 5 days ago

NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?

Paper • 2606.24530 • Published 27 days ago • 64

Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems

Paper • 2606.18837 • Published Jun 17 • 58

Human-like autonomy emerges from self-play and a pinch of human data

Paper • 2606.19370 • Published Jun 11 • 1

Agent-as-a-Router: Agentic Model Routing for Coding Tasks

Paper • 2606.22902 • Published 28 days ago • 38

Critique of Agent Model

Paper • 2606.23991 • Published 28 days ago • 22