PPaperPicks

Yifan Liu

24 papers at tracked venues · 14 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Can LLMs Hear the Dogwhistle?
    ACL 2026 · Yifan Liu
  2. Driving with Regulation: Trustworthy and Interpretable Decision-Making for Autonomous Driving with Retrieval-Augmented Reasoning
  3. Integrating Data Validation with Large Language Models for Regulation-Guided Tabular Anomaly Detection
  4. LLaVA-UHD v2: Exploiting Hierarchical Vision Granularity in MLLMs via Inverse Semantic Pyramid
  5. "Good" XAI Design: For What? In Which Ways?
  6. AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity
    EMNLP 2025 · Yifan Liu
  7. Balancing Fine-tuning and RAG: A Hybrid Strategy for Dynamic LLM Recommendation Updates
  8. DVIB: Towards Robust Multimodal Recommender Systems via Variational Information Bottleneck Distillation
  9. DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility
    NAACL 2025 · Yifan Liu
  10. Explainable AI for Daily Scenarios from End-Users' Perspective: Non-Use, Concerns, and Ideal Design
  11. Fast and Effective Early Termination for Simple Ranking Functions
  12. Learning Efficient and Generalizable Human Representation with Human Gaussian Model
    ICCV 2025 · Yifan Liu
  13. MA-DPR: Manifold-aware Distance Metrics for Dense Passage Retrieval
    EMNLP 2025 · Yifan Liu
  14. MCLPD: Multi-View Contrastive Learning for EEG-Based PD Detection Across Datasets
  15. Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions
  16. Socially-Aware Robot Navigation Enhanced by Bidirectional Natural Language Conversations Using Large Language Models
  17. User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems
  18. Visual-informed Silent Video Identity Conversion
    ACM MM 2025 · Yifan Liu
  19. HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects
  20. High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field
  21. Inter-X: Towards Versatile Human-Human Interaction Analysis
  22. LLMs for User Interest Exploration in Large-scale Recommendation Systems
  23. MirageRoom: 3D Scene Segmentation with 2D Pre-Trained Models by Mirage Projection
  24. UniMPC: Towards a Unified Framework for Multi-Party Conversations