Junnan Liu

jnanliu's activity

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

authored 2 papers about 1 month ago

How Brittle is Agent Safety? Rethinking Agent Risk under Intent Concealment and Task Complexity

Paper • 2511.08487 • Published Nov 11, 2025 • 2

Rectifying LLM Thought from Lens of Optimization

Paper • 2512.01925 • Published Dec 1, 2025 • 24

authored a paper about 2 months ago

ATLAS: A High-Difficulty, Multidisciplinary Benchmark for Frontier Scientific Reasoning

Paper • 2511.14366 • Published Nov 18, 2025 • 16

authored 3 papers 5 months ago

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis

Paper • 2508.15754 • Published Aug 21, 2025 • 4

Intern-S1: A Scientific Multimodal Foundation Model

Paper • 2508.15763 • Published Aug 21, 2025 • 259

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

Paper • 2508.03686 • Published Aug 5, 2025 • 37

authored a paper 6 months ago

Coding Triangle: How Does Large Language Model Understand Code?

Paper • 2507.06138 • Published Jul 8, 2025 • 21

authored 2 papers 8 months ago

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Paper • 2502.06781 • Published Feb 10, 2025 • 58

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective

Paper • 2505.19815 • Published May 26, 2025 • 36

authored a paper about 1 year ago

Are Your LLMs Capable of Stable Reasoning?

Paper • 2412.13147 • Published Dec 17, 2024 • 93