PPaperPicks

Qifeng Liu

17 papers at tracked venues · 12 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. VividListener: Expressive and Controllable Listener Dynamics Modeling for Multi-Modal Responsive Interaction
  2. Co3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion
  3. Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model
  4. Empowering World Models with Reflection for Embodied Video Prediction
  5. Importance Weighting Can Help Large Language Models Self-Improve
  6. VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling
  7. AttnZero: Efficient Attention Discovery for Vision Transformers
  8. Auto-GAS: Automated Proxy Discovery for Training-Free Generative Architecture Search
  9. ChatMusician: Understanding and Generating Music Intrinsically with LLM
  10. DetKDS: Knowledge Distillation Search for Object Detectors
  11. Dirichlet Continual Learning: Tackling Catastrophic Forgetting in NLP
  12. Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
  13. Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
  14. FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation
  15. FlashSpeech: Efficient Zero-Shot Speech Synthesis
  16. PyramidCodec: Hierarchical Codec for Long-form Music Generation in Audio Domain
  17. Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-Speech Gesture Generation