Shu Wu

Venues

Frequent coauthors

Papers

1. Audio-Thinker: Guiding Large Audio Language Model When and How to Think via Reinforcement Learning
   AAAI 2026 · Shu Wu
2. Enhancing Stability and Fidelity for Zero-Shot TTS with a Multi-Level Evaluator
   AAAI 2026 ·

   Hualei Wang

   DBLP profile ↗ORCID search ↗
3. OPS: An Order-Preserving Sorting Network for Information Retrieval
   SIGIR 2026 ·

   Chao Wang

   DBLP profile ↗ORCID search ↗
4. RLShield: Dynamic Jailbreak Detection for LLMs via Reinforced Adaptive Learning
   ACL 2026 ·

   Zhao Tong

   DBLP profile ↗ORCID search ↗
5. Reinforcement Learning-Guided Adaptive Tuning for Out-of-Distribution Harmful Text Detection
   ACL 2026 ·

   Mengyu Xiang

   DBLP profile ↗ORCID search ↗
6. Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing
   ACL 2026 ·

   Tingyu Song

   DBLP profile ↗ORCID search ↗
7. TRACE: Transformation-Aware Graph Refinement for Reaction Condition Prediction
   AAAI 2026 ·

   Yujie Chen

   DBLP profile ↗ORCID search ↗
8. When Safety Alignment Fails to Generalize: Probing with Language Game Jailbreaks
   ACL 2026 ·

   Zewen Long

   DBLP profile ↗ORCID search ↗
9. A Self-Supervised Adaptive Tuning Approach for Out-of-Distribution Social Media Bot Detection
   WWW 2025 ·

   Yuxuan Song

   DBLP profile ↗ORCID search ↗
10. Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models
    EMNLP 2025 ·

    Qiang Liu

    DBLP profile ↗ORCID search ↗
11. Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG
    ACL 2025 ·

    Xin Sun

    DBLP profile ↗ORCID search ↗
12. Dynamic Detection of Sarcasm Topic-Target Pairs via LLM-Based Knowledge Alignment
    WWW 2025 ·

    Mengyu Xiang

    DBLP profile ↗ORCID search ↗
13. Generate First, Then Sample: Enhancing Fake News Detection with LLM-Augmented Reinforced Sampling
    ACL 2025 ·

    Zhao Tong

    DBLP profile ↗ORCID search ↗
14. KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editing
    EMNLP 2025 ·

    Mengqi Zhang

    DBLP profile ↗ORCID search ↗
15. MolSpectra: Pre-training 3D Molecular Representation with Multi-modal Energy Spectra
    ICLR 2025 ·

    Liang Wang

    DBLP profile ↗ORCID search ↗
16. Personalized Text Generation with Contrastive Activation Steering
    ACL 2025 ·

    Jinghao Zhang

    DBLP profile ↗ORCID search ↗
17. REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing
    EMNLP 2025 ·

    Haitian Zhong

    DBLP profile ↗ORCID search ↗
18. Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing
    NeurIPS 2025 ·

    Junfei Wu

    DBLP profile ↗ORCID search ↗
19. SHARP: Steering Hallucination in LVLMs via Representation Engineering
    EMNLP 2025 ·

    Junfei Wu

    DBLP profile ↗ORCID search ↗
20. SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor Detection
    ACL 2025 ·

    Mingqing Zhang

    DBLP profile ↗ORCID search ↗
21. The Underappreciated Power of Vision Models for Graph Structural Understanding
    NeurIPS 2025 ·

    Xinjian Zhao

    DBLP profile ↗ORCID search ↗
22. Uncovering Overfitting in Large Language Model Editing
    ICLR 2025 ·

    Mengqi Zhang

    DBLP profile ↗ORCID search ↗
23. Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization
    NeurIPS 2024 ·

    Dingshuo Chen

    DBLP profile ↗ORCID search ↗
24. CAMLO: Cross-Attentive Multi-View Network for Long-Term Origin-Destination Flow Prediction
    SDM 2024 ·

    Liang Wang

    DBLP profile ↗ORCID search ↗
25. Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting
    ACL 2024 ·

    Yuwei Xia

    DBLP profile ↗ORCID search ↗
26. DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization
    SIGKDD 2024 ·

    Xin Sun

    DBLP profile ↗ORCID search ↗
27. EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification
    ACL 2024 ·

    Huanhuan Ma

    DBLP profile ↗ORCID search ↗
28. Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media
    CIKM 2024 ·

    Jiajun Zhang

    DBLP profile ↗ORCID search ↗
29. Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables
    AAAI 2024 ·

    Haisong Gong

    DBLP profile ↗ORCID search ↗
30. Knowledge Graph Enhanced Large Language Model Editing
    EMNLP 2024 ·

    Mengqi Zhang

    DBLP profile ↗ORCID search ↗
31. Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models
    ACL 2024 ·

    Junfei Wu

    DBLP profile ↗ORCID search ↗
32. Modality-Balanced Learning for Multimedia Recommendation
    ACM MM 2024 ·

    Jinghao Zhang

    DBLP profile ↗ORCID search ↗
33. Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-Shot Molecular Property Prediction
    NeurIPS 2024 ·

    Qiang Liu

    DBLP profile ↗ORCID search ↗
34. Rethinking Graph Masked Autoencoders through Alignment and Uniformity
    AAAI 2024 ·

    Liang Wang

    DBLP profile ↗ORCID search ↗
35. Semantic Evolvement Enhanced Graph Autoencoder for Rumor Detection
    WWW 2024 ·

    Xiang Tao

    DBLP profile ↗ORCID search ↗
36. Stealthy Attack on Large Language Model based Recommendation
    ACL 2024 ·

    Jinghao Zhang

    DBLP profile ↗ORCID search ↗
37. Text-Guided Molecule Generation with Diffusion Language Model
    AAAI 2024 ·

    Haisong Gong

    DBLP profile ↗ORCID search ↗
38. VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
    NeurIPS 2024 ·

    Han Huang

    DBLP profile ↗ORCID search ↗