Wangding Zeng
Artificial Intelligence · 2024–2026
A researcher in the Science corpus: 8 papers; trusts 1 researcher and is trusted by 0 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 119 citations into it
- Efficiency & Compression — 20 citations into it
Whom Wangding Zeng trusts
Their strongest outbound trust, strongest first, inferred from their citations.
- Noam Shazeer (in Artificial Intelligence)
Papers from Wangding Zeng's perspective
Ordered by how strongly the researchers Wangding Zeng trusts endorse each paper. Same corpus, a different order for every researcher.
- Neural Machine Translation of Rare Words with Subword Units
- Training language models to follow instructions with human feedback (Neural Information Processing Systems)
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity (Journal of machine learning research)
- Longformer: The Long-Document Transformer
- Measuring Mathematical Problem Solving With the MATH Dataset
- Program Synthesis with Large Language Models
- FastText.zip: Compressing text classification models
- DeepSeek-Coder: When the Large Language Model Meets Programming - The Rise of Code Intelligence
Their papers
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning (2025) — 5,477 citations
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence (2026) — 347 citations
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models (2025) — 637 citations
- Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025) — 426 citations
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models (2024) — 972 citations
- DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence (2024) — 469 citations
- DeepSeek-V3 Technical Report (2024) — 3,725 citations
- DeepSeek-V3 Technical Report (2024) — 0 citations