Dongrui Liu

Venues

Frequent coauthors

Papers

1. AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
   ACL 2026 ·

   Zhiheng Xi

   DBLP profile ↗ORCID search ↗
2. AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems
   ACL 2026 ·

   Yulang Chen

   DBLP profile ↗ORCID search ↗
3. Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models
   AAAI 2026 ·

   Yifan Jia

   DBLP profile ↗ORCID search ↗
4. IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks
   AAAI 2026 ·

   Xiaoya Lu

   DBLP profile ↗ORCID search ↗
5. LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions
   ACL 2026 ·

   Xuhao Hu

   DBLP profile ↗ORCID search ↗
6. ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
   ACL 2026 ·

   Junyao Yang

   DBLP profile ↗ORCID search ↗
7. Cooperative or Competitive? Understanding the Interaction between Attention Heads From A Game Theory Perspective
   ACL 2025 ·

   Xiaoye Qu

   DBLP profile ↗ORCID search ↗
8. Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning
   CVPR 2025 ·

   Qianli Ma

   DBLP profile ↗ORCID search ↗
9. Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
   NeurIPS 2025 ·

   Chen Qian

   DBLP profile ↗ORCID search ↗
10. EvoBench: Towards Real-world LLM-Generated Text Detection Benchmarking for Evolving Large Language Models
    ACL 2025 ·

    Xiao Yu

    DBLP profile ↗ORCID search ↗
11. LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
    ACL 2025 ·

    Qianli Ma

    DBLP profile ↗ORCID search ↗
12. LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
    ACL 2025 ·

    Qibing Ren

    DBLP profile ↗ORCID search ↗
13. REEF: Representation Encoding Fingerprints for Large Language Models
    ICLR 2025 ·

    Jie Zhang

    DBLP profile ↗ORCID search ↗
14. RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
    NeurIPS 2025 ·

    Jingyi Yang

    DBLP profile ↗ORCID search ↗
15. The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations
    EMNLP 2025 ·

    Yubo Zhu

    DBLP profile ↗ORCID search ↗
16. The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models
    ACL 2025 ·

    Chen Qian

    DBLP profile ↗ORCID search ↗
17. VLSBench: Unveiling Visual Leakage in Multimodal Safety
    ACL 2025 ·

    Xuhao Hu

    DBLP profile ↗ORCID search ↗
18. X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Jailbreak Attacks without Compromising Usability
    EMNLP 2025 ·

    Xiaoya Lu

    DBLP profile ↗ORCID search ↗
19. Explaining Generalization Power of a DNN Using Interactive Concepts
    AAAI 2024 ·

    Huilin Zhou

    DBLP profile ↗ORCID search ↗
20. Identifying Semantic Induction Heads to Understand In-Context Learning
    ACL 2024 ·

    Jie Ren

    DBLP profile ↗ORCID search ↗
21. MLP Can Be a Good Transformer Learner
    CVPR 2024 ·

    Sihao Lin

    DBLP profile ↗ORCID search ↗
22. Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
    ACL 2024 ·

    Chen Qian

    DBLP profile ↗ORCID search ↗
23. Towards the Dynamics of a DNN Learning Symbolic Interactions
    NeurIPS 2024 ·

    Qihan Ren

    DBLP profile ↗ORCID search ↗