PPaperPicks

Mengze Li

Zhejiang University, Hangzhou, China

19 papers at tracked venues · 16 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Active Multi-source Domain Adaptation for Multimodal Fake News Detection
  2. Tailoring Diagnostic Modeling to Individual Learners: Personalized Distractor Generation via MCTS-Guided Reasoning Reconstruction
  3. Consistent and Invariant Generalization Learning for Short-video Misinformation Detection
  4. Contrastive Cross-Course Knowledge Tracing via Concept Graph Guided Knowledge Transfer
  5. EcoFace: Audio-Visual Emotional Co-Disentanglement Speech-Driven 3D Talking Face Generation
  6. Embracing Imperfection: Simulating Students with Diverse Cognitive Levels Using LLM-based Agents
  7. ExpTalk: Diverse Emotional Expression via Adaptive Disentanglement and Refined Alignment for Speech-Driven 3D Facial Animation
  8. Few-Shot Incremental Learning via Foreground Aggregation and Knowledge Transfer for Audio-Visual Semantic Segmentation
  9. Grasp the Key Takeaways from Source Domain for Few Shot Graph Domain Adaptation
  10. HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
  11. LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning
  12. Out-of-Distribution Detection via LLM-Guided Outlier Generation for Text-attributed Graph
  13. Semantic-guided Diverse Decoding for Large Language Model
  14. Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving
  15. What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
  16. Cross-modal Observation Hypothesis Inference
    ACM MM 2024 · Mengze Li
  17. Hierarchical Debiasing and Noisy Correction for Cross-domain Video Tube Retrieval
  18. Panoptic Scene Graph Generation with Semantics-Prototype Learning
  19. Semantic Alignment for Multimodal Large Language Models