PPaperPicks

Kai Liu

22 papers at tracked venues · 15 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. A Principle-Driven Adaptive Policy for Group Cognitive Stimulation Dialogue for Elderly with Cognitive Impairment
  2. RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game
  3. Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
  4. Beyond Fixed Length: Bucket Pre-training is All You Need
  5. Exact Sparse Orthogonal Dictionary Learning
  6. GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-Based Transformer
  7. La RoSA: Enhancing LLM Efficiency via Layerwise Rotated Sparse Activation
    ICML 2025 · Kai Liu
  8. Mask Does Not Matter: A Unified Latent Diffusion-Enhanced Framework for Mask-Free Virtual Try-On
  9. ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdom
  10. RoFt-Mol: Benchmarking Robust Fine-tuning with Molecular Graph Foundation Models
  11. SEI3D: CPU-only 3D Object Tracking Fusing Sparse-flow-filtered Edge and Interior Alignment
  12. Scaling up the State Size of RNN LLMs for Long-Context Scenarios
    ACL 2025 · Kai Liu
  13. UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery
  14. UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection
  15. UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design
  16. CycleVTON: A Cycle Mapping Framework for Parser-Free Virtual Try-On
  17. Differentiable Model Scaling using Differentiable Topk
    ICML 2024 · Kai Liu
  18. HoloVic: Large-scale Dataset and Benchmark for Multi-Sensor Holographic Intersection and Vehicle-Infrastructure Cooperative
  19. Learning Identifiable Factorized Causal Representations of Cellular Responses
  20. LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack
  21. Pointsoup: High-Performance and Extremely Low-Decoding-Latency Learned Geometry Codec for Large-Scale Point Cloud Scenes
  22. SwiftPillars: High-Efficiency Pillar Encoder for Lidar-Based 3D Detection