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 2 / 4 页

51. ICML 2025Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan
52. ICML 2025Reward Translation via Reward Machine in Semi-Alignable MDPs
53. NeurIPS 2025Alias-Free ViT: Fractional Shift Invariance via Linear Attention
54. NeurIPS 2025Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
55. NeurIPS 2025Calibrating Translation Decoding with Quality Estimation on LLMs
56. NeurIPS 2025Equi-mRNA: Protein Translation Equivariant Encoding for mRNA Language Models
57. NeurIPS 2025Exploring the Translation Mechanism of Large Language Models
58. NeurIPS 2025Fractional Diffusion Bridge Models
59. NeurIPS 2025GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow
60. NeurIPS 2025Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation
61. NeurIPS 2025MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining
62. NeurIPS 2025PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation
63. NeurIPS 2025QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation
64. NeurIPS 2025QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code
65. NeurIPS 2025ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge
66. NeurIPS 2025SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation
67. CVPR 2024GenN2N: Generative NeRF2NeRF Translation
68. CVPR 2024LLMs are Good Sign Language Translators
69. CVPR 2024Revisiting Global Translation Estimation with Feature Tracks
70. CVPR 2024StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation
71. ICLR 2024A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
72. ICLR 2024An interpretable error correction method for enhancing code-to-code translation
73. ICLR 2024Guess & Sketch: Language Model Guided Transpilation
74. ICLR 2024Multilingual Jailbreak Challenges in Large Language Models
75. ICLR 2024On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection
76. ICLR 2024PolyVoice: Language Models for Speech to Speech Translation
77. ICLR 2024Quantifying the Plausibility of Context Reliance in Neural Machine Translation
78. ICLR 2024Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation
79. ICLR 2024Sparse MoE with Language Guided Routing for Multilingual Machine Translation
80. ICLR 2024Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns
81. ICLR 2024The Reasonableness Behind Unreasonable Translation Capability of Large Language Model
82. ICLR 2024Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
83. ICLR 2024Transferring Labels to Solve Annotation Mismatches Across Object Detection Datasets
84. ICLR 2024Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation
85. ICLR 2024Unpaired Image-to-Image Translation via Neural Schrödinger Bridge
86. ICML 2024Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation
87. ICML 2024Translation Equivariant Transformer Neural Processes
88. NeurIPS 2024Consistency Diffusion Bridge Models
89. NeurIPS 2024Expert-level protocol translation for self-driving labs
90. NeurIPS 2024How do Large Language Models Handle Multilingualism?
91. NeurIPS 2024Improving Gloss-free Sign Language Translation by Reducing Representation Density
92. NeurIPS 2024Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
93. NeurIPS 2024QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation
94. NeurIPS 2024Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards
95. NeurIPS 2024Schrodinger Bridge Flow for Unpaired Data Translation
96. NeurIPS 2024Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
97. NeurIPS 2024The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
98. NeurIPS 2024Towards Explainable Evaluation Metrics for Machine Translation
99. NeurIPS 2024TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation
100. CVPR 20233D-Aware Multi-Class Image-to-Image Translation With NeRFs

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。