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 153 篇，第 1 / 4 页

1. CVPR 2026BoostSLT Boosting Sign Language Translation via a Plug-and-Play Diffusion-Based Semantic
2. CVPR 2026LiDAR-to-4DRadar Diffusion Bridge via Cross-Modal Alignment and Translation in Latent
3. CVPR 2026MERIT Multi-domain Efficient RAW Image Translation
4. CVPR 2026Resolving Endpoint Underfitting in Diffusion Bridges via Noise Alignment
5. CVPR 2026TherA Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation
6. ICLR 2026DiscoX: Benchmarking Discourse-Level Translation in Expert Domains
7. ICLR 2026IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs
8. ICLR 2026Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method
9. ICLR 2026Tight Bounds for Schrodinger Potential Estimation in Unpaired Data Translation
10. ICLR 2026Translation Heads: Unveiling Attention's Role in LLM Multilingual Translation
11. ICLR 2026Universal Multi-Domain Translation via Diffusion Routers
12. ICML 2026Any2Any: Unified Arbitrary Modality Translation for Remote Sensing
13. ICML 2026Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC
14. ICML 2026Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code Translation
15. ICML 2026FullStack-Agent: Enhancing Agentic Full-Stack Web Coding via Development-Oriented Testing and Repository Back-Translation
16. ICML 2026Generalizable and Composable Multi-Model Embedding Translation
17. ICML 2026MatchFixAgent: Language-Agnostic Autonomous Repository-Level Code Translation Validation and Repair
18. ICML 2026Physiology as Language: Translating Respiration to EEG during Sleep
19. ICML 2026scChord: A Probabilistic Manifold Rectification Framework for RNA-to-Protein Translation
20. ICML 2026Structured Diffusion Bridges: Inductive Bias for Denoising Diffusion Bridges
21. ICML 2026Translation Heads: Disentangling meaning from language in LLM-based machine translation
22. NeurIPS 2026CRESiST: Self-Enhancing Exploritive Policy Learning for Simultaneous Speech Translation
23. NeurIPS 2026DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation
24. NeurIPS 2026Efficient One-to-many Domain Translation via Diffusive Entropic Optimal Transport
25. NeurIPS 2026Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment
26. NeurIPS 2026Magnetic Resonance Unpaired Image Translation with Pseudometric Schrödinger Bridges
27. NeurIPS 2026On Making $SE(2)$-Invariant Networks Optimal
28. NeurIPS 2026ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation
29. NeurIPS 2026Pygmalion Effect in Vision: Image-to-Clay Translation for Reflective Geometry Reconstruction
30. NeurIPS 2026ReflectMT: Internalizing Reflection for Efficient and High-Quality Machine Translation
31. NeurIPS 2026ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation
32. NeurIPS 2026RIVET: Regex-to-Indexable Keys via Neural Translation for Interactive LIMIT-k Retrieval
33. NeurIPS 2026Verifiers in the Loop: Decoding Time Verification for Code Translation
34. NeurIPS 2026Winning the Symmetry Lottery: Learning Invariance from Data Augmentations with Transformers
35. CVPR 2025Deterministic Image-to-Image Translation via Denoising Brownian Bridge Models with Dual Approximators
36. CVPR 2025FSboard: Over 3 Million Characters of ASL Fingerspelling Collected via Smartphones
37. CVPR 2025Learning to Filter Outlier Edges in Global SfM
38. CVPR 2025Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues
39. CVPR 2025StyleMaster: Stylize Your Video with Artistic Generation and Translation
40. ICLR 2025Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?
41. ICLR 2025Diffusion Bridge Implicit Models
42. ICLR 2025Improving Neural Optimal Transport via Displacement Interpolation
43. ICLR 2025Looking Backward: Streaming Video-to-Video Translation with Feature Banks
44. ICLR 2025Scaling Laws for Downstream Task Performance in Machine Translation
45. ICLR 2025X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
46. ICLR 2025YouTube-SL-25: A Large-Scale, Open-Domain Multilingual Sign Language Parallel Corpus
47. ICML 2025AEQA-NAT : Adaptive End-to-end Quantization Alignment Training Framework for Non-autoregressive Machine Translation
48. ICML 2025Diversified Flow Matching with Translation Identifiability
49. ICML 2025Learning from others' mistakes: Finetuning machine translation models with span-level error annotations
50. ICML 2025Learning the RoPEs: Better 2D and 3D Position Encodings with STRING

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。