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 54 篇，第 1 / 2 页

1. CVPR 20233D-Aware Multi-Class Image-to-Image Translation With NeRFs
2. CVPR 2023A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization
3. CVPR 2023BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models
4. CVPR 2023Fix the Noise: Disentangling Source Feature for Controllable Domain Translation
5. CVPR 2023Gloss Attention for Gloss-Free Sign Language Translation
6. CVPR 2023Interactive Cartoonization With Controllable Perceptual Factors
7. CVPR 2023LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data
8. CVPR 2023Masked and Adaptive Transformer for Exemplar Based Image Translation
9. CVPR 2023On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer
10. CVPR 2023Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
11. CVPR 2023ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection
12. CVPR 2023Unpaired Image-to-Image Translation With Shortest Path Regularization
13. CVPR 2023Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation
14. ICLR 2023Bidirectional Language Models Are Also Few-shot Learners
15. ICLR 2023Code Translation with Compiler Representations
16. ICLR 2023Conditional Antibody Design as 3D Equivariant Graph Translation
17. ICLR 2023Diffusion-based Image Translation using disentangled style and content representation
18. ICLR 2023Dual Diffusion Implicit Bridges for Image-to-Image Translation
19. ICLR 2023Efficient Federated Domain Translation
20. ICLR 2023Federated Nearest Neighbor Machine Translation
21. ICLR 2023Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation
22. ICLR 2023Hidden Markov Transformer for Simultaneous Machine Translation
23. ICLR 2023Language Modelling with Pixels
24. ICLR 2023Multi-domain image generation and translation with identifiability guarantees
25. ICLR 2023Protein Sequence and Structure Co-Design with Equivariant Translation
26. ICLR 2023Pseudo-label Training and Model Inertia in Neural Machine Translation
27. ICLR 2023Simple and Scalable Nearest Neighbor Machine Translation
28. ICLR 2023SLTUNET: A Simple Unified Model for Sign Language Translation
29. ICLR 2023TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation
30. ICML 2023Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization
31. ICML 2023GLOBE-CE: A Translation Based Approach for Global Counterfactual Explanations
32. ICML 2023Kernel QuantTree
33. ICML 2023Measuring the Impact of Programming Language Distribution
34. ICML 2023Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think
35. ICML 2023Pre-training for Speech Translation: CTC Meets Optimal Transport
36. ICML 2023Prompting Large Language Model for Machine Translation: A Case Study
37. ICML 2023Rotation and Translation Invariant Representation Learning with Implicit Neural Representations
38. ICML 2023Scaling Laws for Multilingual Neural Machine Translation
39. ICML 2023Shiftable Context: Addressing Training-Inference Context Mismatch in Simultaneous Speech Translation
40. ICML 2023The Unreasonable Effectiveness of Few-shot Learning for Machine Translation
41. NeurIPS 2023A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
42. NeurIPS 2023Accessing Higher Dimensions for Unsupervised Word Translation
43. NeurIPS 2023Binarized Neural Machine Translation
44. NeurIPS 2023Extremal Domain Translation with Neural Optimal Transport
45. NeurIPS 2023Fast Model DeBias with Machine Unlearning
46. NeurIPS 2023Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
47. NeurIPS 2023Implicit Regularization in Over-Parameterized Support Vector Machine
48. NeurIPS 2023MADLAD-400: A Multilingual And Document-Level Large Audited Dataset
49. NeurIPS 2023Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions
50. NeurIPS 2023Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

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。