Awesome AI Agents
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Tian Liang — most-cited papers & profile · AI Agents
← authors
·
overview
Tian Liang
26
papers ·
94
citations ·
14
h-index
Hong Kong Baptist University · People's Government of Yunnan Province · China National Electric Apparatus Research Institute (China) · Hebei Normal University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Criticbench: Benchmarking Llms For Critique-correct Reasoning
2024 · 90 citations
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
2024 · 4 citations
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
2025
Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA
2026
Confidence Calibration for Multimodal LLMs: An Empirical Study through Medical VQA
2026
Free(): Learning to Forget in Malloc-Only Reasoning Models
2026
The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context
2026
From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space
2026
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
2026
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
2025
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
2025
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
2025
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
2025
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
2025
Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
2025
Topics
Training Techniques
Fine-Tuning
Evaluation
Efficiency
In-Context Learning
Reinforcement Learning
RAG
Safety & Alignment
Model Architecture
Agentic