PPaperPicks

JingBo Zhu

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

Venues

Frequent coauthors

Papers

  1. BIASEDTALES-ML: A Multilingual Dataset for Analyzing Narrative Attribute Distributions in LLM-Generated Stories
  2. Bypassing Neural Evaluations for Fast Audio Editing via Adaptive Trajectory Extrapolation
  3. CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
  4. GRAM-R²: Self-Training Generative Foundation Reward Models for Reward Reasoning
  5. LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
  6. MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
  7. NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
  8. On the Emotion Understanding of Synthesized Speech
  9. Probing Preference Representations: A Multi-Dimensional Evaluation and Analysis Method for Reward Models
  10. RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment
  11. SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams
  12. SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
  13. SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement
  14. WaveEx: Accelerating Flow Matching-based Speech Generation via Wavelet-guided Extrapolation
  15. Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation
  16. Enhancing Neural Machine Translation Through Target Language Data: A kNN-LM Approach for Domain Adaptation
  17. Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders
  18. GRAM: A Generative Foundation Reward Model for Reward Generalization
  19. HEAL: A Hypothesis-Based Preference-Aware Analysis Framework
  20. IIET: Efficient Numerical Transformer via Implicit Iterative Euler Method
  21. Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models
  22. Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
  23. MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization
  24. Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Models
  25. RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data
  26. Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models
  27. Clustering and Ranking: Diversity-preserved Instruction Selection through Expert-aligned Quality Estimation
  28. EIT: Enhanced Interactive Transformer
  29. ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation
  30. Exploiting Target Language Data for Neural Machine Translation Beyond Back Translation
  31. Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-Context Models
  32. Hybrid Alignment Training for Large Language Models
  33. PartialFormer: Modeling Part Instead of Whole for Machine Translation
  34. Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
  35. Recent Advances in End-to-End Simultaneous Speech Translation
  36. Revealing the Parallel Multilingual Learning within Large Language Models
  37. Revisiting Interpolation Augmentation for Speech-to-Text Generation
  38. Teaching Language Models to Self-Improve by Learning from Language Feedback