PPaperPicks

Yang Xiang

Pengcheng Laboratory, Shenzhen, China

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

Venues

Frequent coauthors

Papers

  1. CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
  2. MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus
  3. The Visual Prism: Refracting Images into Parallel Multilingual Descriptions with Structured Visual Guidance
  4. When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning
    ACL 2026 · Yang Xiang
  5. A Survey on the Feedback Mechanism of LLM-based AI Agents
  6. Benchmarking LLMs for Translating Classical Chinese Poetry: Evaluating Adequacy, Fluency, and Elegance
  7. Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning
  8. Beware of Calibration Data for Pruning Large Language Models
  9. CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention
  10. Exploring the Translation Mechanism of Large Language Models
  11. From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement
  12. LLM-based Translation Inference with Iterative Bilingual Understanding
  13. Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning
  14. ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation
  15. Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales
  16. Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization
  17. DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
  18. Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration
  19. Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
  20. ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-Order Optimization