PPaperPicks

Zhengqi Wen

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

Venues

Frequent coauthors

Papers

  1. AStar: Boosting Multimodal Reasoning with Automated Structured Thinking
  2. ATLAS: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning
  3. Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models
  4. CAIR: Causal Adaptive Information-based Reinforcement Learning for Multimodal Emotion Reasoning
  5. Calibration-Aware Policy Optimization for Reasoning LLMs
  6. PSA-MF: Personality-Sentiment Aligned Multi-Level Fusion for Multimodal Sentiment Analysis
  7. ReFL: Reflective Feedback Learning for Hallucination Detection of Large Language Models
  8. SPARK: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
  9. TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning
  10. Two-Stage Regularization-Based Structured Pruning for LLMs
  11. ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection
  12. Code-switching Mediated Sentence-level Semantic Learning
  13. ImViD: Immersive Volumetric Videos for Enhanced VR Engagement
  14. Less is More? Textual-Only Language Model for AVI challenge 2025
  15. M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction
  16. MDPE: A Multimodal Deception Dataset with Personality and Emotional Characteristics
  17. RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routing
  18. Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio
  19. Generalized Fake Audio Detection via Deep Stable Learning
  20. Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategy
  21. Genuine-Focused Learning using Mask AutoEncoder for Generalized Fake Audio Detection
  22. PPPR: Portable Plug-in Prompt Refiner for Text to Audio Generation
  23. Residual Speaker Representation for One-Shot Voice Conversion
  24. TraceableSpeech: Towards Proactively Traceable Text-to-Speech with Watermarking