PPaperPicks

Zhengtao Yu

Kunming University of Science and Technology, China

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

Venues

Frequent coauthors

Papers

  1. Activation-Guided Local Editing for Jailbreaking Attacks
  2. Breaking Consensus Bias: Unsupervised Reinforcement Learning for Machine Translation
  3. Bypassing Neural Evaluations for Fast Audio Editing via Adaptive Trajectory Extrapolation
  4. Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation
  5. Layer-aware Dual-directional Modulation for Low-resource Machine Translation
  6. On the Emotion Understanding of Synthesized Speech
  7. Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
  8. RPGen: Robust and Differentially Private Synthetic Image Generation
  9. SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
  10. SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement
  11. 2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models
  12. 3R: Enhancing Sentence Representation Learning via Redundant Representation Reduction
  13. A Mixed-Language Multi-Document News Summarization Dataset and a Graphs-Based Extract-Generate Model
  14. Ambiguous Instance-Aware Contrastive Network with Multi-Level Matching for Multi-View Document Clustering
  15. BiDeV: Bilateral Defusing Verification for Complex Claim Fact-Checking
  16. Community Detection in Large-Scale Complex Networks via Structural Entropy Game
  17. Dynamic Syntactic Feature Filtering and Injecting Networks for Cross-lingual Dependency Parsing
  18. GRPO-Guided Modality Selection Enhanced LoRA-Tuned LLMs for Multimodal Emotion Recognition
  19. Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
  20. MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization
  21. Memory-enhanced Large Language Model for Cross-lingual Dependency Parsing via Deep Hierarchical Syntax Understanding
  22. Multilingual Generative Retrieval via Cross-lingual Semantic Compression
  23. Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharing
  24. SECodec: Structural Entropy-based Compressive Speech Representation Codec for Speech Language Models
  25. Unsupervised Graph Clustering with Deep Structural Entropy
  26. "In-Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning
  27. Can Large Language Models Mine Interpretable Financial Factors More Effectively? A Neural-Symbolic Factor Mining Agent Model
  28. DGSRN: Noise-Robust Speech Recognition Method with Dual-Path Gated Spectral Refinement Network
  29. Does Large Language Model Contain Task-Specific Neurons?
  30. Hierarchical and Incremental Structural Entropy Minimization for Unsupervised Social Event Detection
  31. Hypergraph Neural Architecture Search
  32. Integrating Speech Self-Supervised Learning Models and Large Language Models for ASR
  33. Prompt Based Tri-Channel Graph Convolution Neural Network for Aspect Sentiment Triplet Extraction
  34. Representation Alignment and Adversarial Networks for Cross-lingual Dependency Parsing
  35. RicciNet: Deep Clustering via A Riemannian Generative Model
  36. StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses