PPaperPicks

Chengqing Zong

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

Venues

Frequent coauthors

Papers

  1. DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation
  2. EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User's Internal World
  3. A Query-Response Framework for Whole-Page Complex-Layout Document Image Translation with Relevant Regional Concentration
  4. Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation
  5. Discovering Semantic Subdimensions through Disentangled Conceptual Representations
  6. From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment
  7. Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Model
  8. ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts
  9. Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment
  10. Improving MLLM's Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiency
  11. Investigating Hallucinations in Simultaneous Machine Translation: Knowledge Distillation Solution and Components Analysis
  12. Language Imbalance Driven Rewarding for Multilingual Self-improving
  13. OpenS2S: Advancing Fully Open-Source End-to-End Empathetic Large Speech Language Model
  14. Pay More Attention to Images: Numerous Images-Oriented Multimodal Summarization
  15. SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translation
  16. SimulPL: Aligning Human Preferences in Simultaneous Machine Translation
  17. Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine Translation
  18. TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship Classification
  19. TokAlign: Efficient Vocabulary Adaptation via Token Alignment
  20. A Hybrid Approach towards Chinese Spelling and Splitting Error Correction
  21. BLSP-Emo: Towards Empathetic Large Speech-Language Models
  22. DIUSum: Dynamic Image Utilization for Multimodal Summarization
  23. Document Image Machine Translation with Dynamic Multi-pre-trained Models Assembling
  24. F-MALLOC: Feed-forward Memory Allocation for Continual Learning in Neural Machine Translation
  25. Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment
  26. MapGuide: A Simple yet Effective Method to Reconstruct Continuous Language from Brain Activities
  27. Self-Modifying State Modeling for Simultaneous Machine Translation
  28. X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions