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 53 篇，第 1 / 2 页

1. NeurIPS 2026CRESiST: Self-Enhancing Exploritive Policy Learning for Simultaneous Speech Translation
2. NeurIPS 2026DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation
3. NeurIPS 2026Efficient One-to-many Domain Translation via Diffusive Entropic Optimal Transport
4. NeurIPS 2026Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment
5. NeurIPS 2026Magnetic Resonance Unpaired Image Translation with Pseudometric Schrödinger Bridges
6. NeurIPS 2026On Making $SE(2)$-Invariant Networks Optimal
7. NeurIPS 2026ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation
8. NeurIPS 2026Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
9. NeurIPS 2026ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
10. NeurIPS 2026ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation
11. NeurIPS 2026RIVET: Regex-to-Indexable Keys via Neural Translation for Interactive LIMIT-k Retrieval
12. NeurIPS 2026Verifiers in the Loop: Decoding Time Verification for Code Translation
13. NeurIPS 2026Winning the Symmetry Lottery: Learning Invariance from Data Augmentations with Transformers
14. NeurIPS 2025Alias-Free ViT: Fractional Shift Invariance via Linear Attention
15. NeurIPS 2025Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
16. NeurIPS 2025Calibrating Translation Decoding with Quality Estimation on LLMs
17. NeurIPS 2025Equi-mRNA: Protein Translation Equivariant Encoding for mRNA Language Models
18. NeurIPS 2025Exploring the Translation Mechanism of Large Language Models
19. NeurIPS 2025Fractional Diffusion Bridge Models
20. NeurIPS 2025GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow
21. NeurIPS 2025Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation
22. NeurIPS 2025MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
23. NeurIPS 2025PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation
24. NeurIPS 2025QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
25. NeurIPS 2025QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
26. NeurIPS 2025ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge
27. NeurIPS 2025SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation
28. NeurIPS 2024Consistency Diffusion Bridge Models
29. NeurIPS 2024Expert-level protocol translation for self-driving labs
30. NeurIPS 2024How do Large Language Models Handle Multilingualism?
31. NeurIPS 2024Improving Gloss-free Sign Language Translation by Reducing Representation Density
32. NeurIPS 2024Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
33. NeurIPS 2024QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation
34. NeurIPS 2024Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards
35. NeurIPS 2024Schrodinger Bridge Flow for Unpaired Data Translation
36. NeurIPS 2024Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
37. NeurIPS 2024The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
38. NeurIPS 2024Towards Explainable Evaluation Metrics for Machine Translation
39. NeurIPS 2024TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation
40. NeurIPS 2023A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
41. NeurIPS 2023Accessing Higher Dimensions for Unsupervised Word Translation
42. NeurIPS 2023Binarized Neural Machine Translation
43. NeurIPS 2023Extremal Domain Translation with Neural Optimal Transport
44. NeurIPS 2023Fast Model DeBias with Machine Unlearning
45. NeurIPS 2023Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
46. NeurIPS 2023Implicit Regularization in Over-Parameterized Support Vector Machine
47. NeurIPS 2023MADLAD-400: A Multilingual And Document-Level Large Audited Dataset
48. NeurIPS 2023Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions
49. NeurIPS 2023Non-autoregressive Machine Translation with Probabilistic Context-free Grammar
50. NeurIPS 2023On the Pareto Front of Multilingual Neural Machine Translation

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。