Profiles2021-2026
Jingang Wang
Meituan Inc
30Papers
3Last author
70Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers30
- OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and GenerationAuthor 7 of 10CVPR 2026 · 47 citations
- Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought PatternsAuthor 7 of 8ICLR 2026 · 5 citations
- LinkQA: Synthesizing Diverse QA from Multiple Seeds Strongly Linked by Knowledge PointsAuthor 5 of 6ACL 2026 · 3 citations
- From Mathematical Reasoning to Code: Generalization of Process Reward Models in Test-Time ScalingAuthor 8 of 8AAAI 2026 · 2 citations
- Large-Scale Diverse Synthesis for Mid-TrainingAuthor 5 of 6ACL Findings 2026
- Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred DataAuthor 7 of 8ACL Findings 2025 · 3 citations
- Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay PerspectiveAuthor 6 of 8ICLR 2025
- FIRE: Flexible Integration of Data Quality Ratings for Effective PretrainingAuthor 6 of 7EMNLP 2025
- FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining StrategyAuthor 7 of 8ACL Findings 2025
- Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training StrategiesAuthor 8 of 8ACL 2025
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive LearningAuthor 6 of 7AAAI 2024 · 42 citations
- C-ICL: Contrastive In-context Learning for Information ExtractionAuthor 6 of 7EMNLP Findings 2024 · 28 citations
- What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of PerturbationAuthor 3 of 6AAAI 2024 · 22 citations
- Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control MechanismAuthor 3 of 5ACL Findings 2024 · 6 citations
- Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient LearningAuthor 10 of 11NeurIPS 2024 · 5 citations
- Graph-Structured Speculative DecodingAuthor 5 of 8ACL Findings 2024 · 4 citations
- Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language ModelsAuthor 6 of 6EMNLP 2024 · 4 citations
- Forgetting Curve: A Reliable Method for Evaluating Memorization Capability for Long-Context ModelsAuthor 6 of 8EMNLP 2024 · 3 citations
- How Do Your Code LLMs perform? Empowering Code Instruction Tuning with Really Good DataAuthor 11 of 14EMNLP 2024 · 2 citations
- DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction TuningAuthor 9 of 11ACL 2024
- RankCSE: Unsupervised Sentence Representations Learning via Learning to RankAuthor 4 of 10ACL 2023 · 30 citations
- Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model CompressionAuthor 4 of 10EMNLP Findings 2023 · 4 citations
- Fusion or Defusion? Flexible Vision-and-Language Pre-TrainingAuthor 5 of 9ACL Findings 2023 · 2 citations
- Improving Input-label Mapping with Demonstration Replay for In-context LearningAuthor 4 of 7EMNLP Findings 2023
- XPrompt: Exploring the Extreme of Prompt TuningAuthor 4 of 8EMNLP 2022 · 23 citations
- VIRT: Improving Representation-based Text Matching via Virtual InteractionAuthor 6 of 9EMNLP 2022 · 8 citations
- GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage RetrievalAuthor 4 of 7EMNLP Findings 2022 · 5 citations
- Making Pretrained Language Models Good Long-tailed LearnersAuthor 3 of 5EMNLP 2022 · 5 citations
- Personalized Abstractive Opinion TaggingAuthor 4 of 9SIGIR 2022 · 2 citations
- Improving Document Representations by Generating Pseudo Query Embeddings for Dense RetrievalAuthor 4 of 6ACL 2021
