机器翻译论文趋势 2023–2026

主要结论

• 机器翻译论文从 2023 年的 54 篇降到 2026 年的 34 篇，热度在回落。
• NeurIPS 是发机器翻译论文最多的会议，2023–2026 年共 53 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 9 篇。
• 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的检索增强生成是 5.4 倍，机器翻译是 0.6 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation
• ICML 2026Any2Any: Unified Arbitrary Modality Translation for Remote Sensing
• ICLR 2026Translation Heads: Unveiling Attention's Role in LLM Multilingual Translation
• CVPR 2026BoostSLT Boosting Sign Language Translation via a Plug-and-Play Diffusion-Based Semantic
• NeurIPS 2025Equi-mRNA: Protein Translation Equivariant Encoding for mRNA Language Models
• ICML 2025Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
• ICLR 2025Improving Neural Optimal Transport via Displacement Interpolation
• CVPR 2025Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues
• NeurIPS 2024Towards Explainable Evaluation Metrics for Machine Translation
• ICML 2024Translation Equivariant Transformer Neural Processes
• ICLR 2024Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation
• CVPR 2024StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation
• NeurIPS 2023Accessing Higher Dimensions for Unsupervised Word Translation
• ICML 2023Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization
• ICLR 2023Efficient Federated Domain Translation
• CVPR 2023Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
• NeurIPS 2026ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation
• ICML 2026Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation
• ICLR 2026DiscoX: Benchmarking Discourse-Level Translation in Expert Domains
• CVPR 2026MERIT Multi-domain Efficient RAW Image Translation

全部机器翻译论文

共 15 篇，第 1 / 1 页

1. ICLR 2024A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
2. ICLR 2024An interpretable error correction method for enhancing code-to-code translation
3. ICLR 2024Guess & Sketch: Language Model Guided Transpilation
4. ICLR 2024Multilingual Jailbreak Challenges in Large Language Models
5. ICLR 2024On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection
6. ICLR 2024PolyVoice: Language Models for Speech to Speech Translation
7. ICLR 2024Quantifying the Plausibility of Context Reliance in Neural Machine Translation
8. ICLR 2024Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation
9. ICLR 2024Sparse MoE with Language Guided Routing for Multilingual Machine Translation
10. ICLR 2024Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns
11. ICLR 2024The Reasonableness Behind Unreasonable Translation Capability of Large Language Model
12. ICLR 2024Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
13. ICLR 2024Transferring Labels to Solve Annotation Mismatches Across Object Detection Datasets
14. ICLR 2024Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation
15. ICLR 2024Unpaired Image-to-Image Translation via Neural Schrödinger Bridge

常见问题

2023–2026 年四大会议一共有多少篇机器翻译论文？

共 153 篇，按年份分别是 2023 年 54 篇、2024 年 33 篇、2025 年 32 篇、2026 年 34 篇。

NeurIPS 2026 有多少篇机器翻译论文？

NeurIPS 2026 有 13 篇机器翻译论文，上一届是 14 篇。

ICLR 2026 有多少篇机器翻译论文？

ICLR 2026 有 6 篇机器翻译论文，上一届是 7 篇。

ICML 2026 有多少篇机器翻译论文？

ICML 2026 有 10 篇机器翻译论文，上一届是 6 篇。

CVPR 2026 有多少篇机器翻译论文？

CVPR 2026 有 5 篇机器翻译论文，上一届是 5 篇。

哪个会议的机器翻译论文最多？

NeurIPS，2023–2026 年共 53 篇。