Tian Liang

Venues

Frequent coauthors

Papers

1. CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs
   ACL 2026 ·

   Qiuyi Qi

   DBLP profile ↗ORCID search ↗
2. STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training
   ACL 2026 ·

   Qiuyi Qi

   DBLP profile ↗ORCID search ↗
3. UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning
   ACL 2026 ·

   Mutian Bao

   DBLP profile ↗ORCID search ↗
4. Competing Large Language Models in Multi-Agent Gaming Environments
   ICLR 2025 ·

   Jen-tse Huang

   DBLP profile ↗ORCID search ↗
5. Confidence Calibration for Multimodal LLMs: An Empirical Study Through Medical VQA
   MICCAI 2025 ·

   Yuetian Du

   DBLP profile ↗ORCID search ↗
6. Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
   ICML 2025 ·

   Zicheng Lin

   DBLP profile ↗ORCID search ↗
7. Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
   ICML 2025 ·

   Xingyu Chen

   DBLP profile ↗ORCID search ↗
8. Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation
   EMNLP 2025 ·

   Ziyin Zhang

   DBLP profile ↗ORCID search ↗
9. MoLE: Decoding by Mixture of Layer Experts Alleviates Hallucination in Large Vision-Language Models
   AAAI 2025 · Tian Liang
10. RaSA: Rank-Sharing Low-Rank Adaptation
    ICLR 2025 ·

    Zhiwei He

    DBLP profile ↗ORCID search ↗
11. Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
    ACL 2025 ·

    Youliang Yuan

    DBLP profile ↗ORCID search ↗
12. The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
    NeurIPS 2025 ·

    Ke Ji

    DBLP profile ↗ORCID search ↗
13. Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
    NeurIPS 2025 ·

    Yue Wang

    DBLP profile ↗ORCID search ↗
14. Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
    NeurIPS 2025 ·

    Xiaoyuan Liu

    DBLP profile ↗ORCID search ↗
15. Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
    NeurIPS 2025 ·

    Mengru Wang

    DBLP profile ↗ORCID search ↗
16. Addressing Entity Translation Problem via Translation Difficulty and Context Diversity
    ACL 2024 · Tian Liang
17. CriticBench: Benchmarking LLMs for Critique-Correct Reasoning
    ACL 2024 ·

    Zicheng Lin

    DBLP profile ↗ORCID search ↗
18. Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
    EMNLP 2024 · Tian Liang
19. Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model
    CVPR 2024 · Tian Liang