对话系统论文趋势 2023–2026

主要结论

• 对话系统论文从 2023 年的 49 篇增长到 2026 年的 171 篇，三年间扩大到约 3.5 倍。
• NeurIPS 是发对话系统论文最多的会议，2023–2026 年共 189 篇，占四个会议总量的 45%。
• 交叉方向里涨得最快的是多智能体 RL：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 17 篇。
• 在「自然语言」的 5 个主题里，它的 2026 年论文数排第 4；同组增长最快的检索增强生成是 5.4 倍，对话系统是 3.5 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 2026A Quantitative Visual Taxonomy of Worldwide Writing Systems
• ICML 2026An Exponential Separation Between Quantum and Quantum-Inspired Classical Algorithms for Linear Systems
• ICLR 2026A Spectral-Grassmann Wasserstein metric for operator representations of dynamical systems
• CVPR 2026Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
• NeurIPS 2025FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation
• ICML 2025Discovering Physics Laws of Dynamical Systems via Invariant Function Learning
• ICLR 2025ContextGNN: Beyond Two-Tower Recommendation Systems
• CVPR 2025Efficient Depth Estimation for Unstable Stereo Camera Systems on AR Glasses
• NeurIPS 2024Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data
• ICML 2024Amortized Equation Discovery in Hybrid Dynamical Systems
• ICLR 2024Safe Collaborative Filtering
• NeurIPS 2023Moral Responsibility for AI Systems
• ICML 2023Graph Switching Dynamical Systems
• ICLR 2023An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation
• CVPR 2023expOSE: Accurate Initialization-Free Projective Factorization Using Exponential Regularization
• NeurIPS 2026Adaptive auditing of AI systems with anytime-valid guarantees
• ICML 2026Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control
• ICLR 2026ClarifyVC: Clarifying Ambiguous Commands in Vehicle Control with a Hybrid Data Augmentation Pipeline
• CVPR 2026Task-Driven Implicit Representations for Automated Design of LiDAR Systems
• NeurIPS 2025In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation

全部对话系统论文

共 92 篇，第 2 / 2 页

51. NeurIPS 2024Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data
52. NeurIPS 2024Comprehensive Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for the Polish Language
53. NeurIPS 2024Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets
54. NeurIPS 2024ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
55. NeurIPS 2024Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models
56. NeurIPS 2024Disentangled Representation Learning in Non-Markovian Causal Systems
57. NeurIPS 2024Disentangling the Roles of Distinct Cell Classes with Cell-Type Dynamical Systems
58. NeurIPS 2024Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems
59. NeurIPS 2024eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling
60. NeurIPS 2024FairJob: A Real-World Dataset for Fairness in Online Systems
61. NeurIPS 2024Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure
62. NeurIPS 2024Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems
63. NeurIPS 2024HHD-GP: Incorporating Helmholtz-Hodge Decomposition into Gaussian Processes for Learning Dynamical Systems
64. NeurIPS 2024How Does Message Passing Improve Collaborative Filtering?
65. NeurIPS 2024Identifiability Analysis of Linear ODE Systems with Hidden Confounders
66. NeurIPS 2024Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees
67. NeurIPS 2024Identifying Equivalent Training Dynamics
68. NeurIPS 2024Initializing Services in Interactive ML Systems for Diverse Users
69. NeurIPS 2024Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
70. NeurIPS 2024Marrying Causal Representation Learning with Dynamical Systems for Science
71. NeurIPS 2024NN4SysBench: Characterizing Neural Network Verification for Computer Systems
72. NeurIPS 2024No Free Delivery Service: Epistemic limits of passive data collection in complex social systems
73. NeurIPS 2024On the Role of Attention Masks and LayerNorm in Transformers
74. NeurIPS 2024Online Control with Adversarial Disturbance for Continuous-time Linear Systems
75. NeurIPS 2024Overcoming Common Flaws in the Evaluation of Selective Classification Systems
76. NeurIPS 2024Parametric model reduction of mean-field and stochastic systems via higher-order action matching
77. NeurIPS 2024Performative Control for Linear Dynamical Systems
78. NeurIPS 2024PowerPM: Foundation Model for Power Systems
79. NeurIPS 2024Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
80. NeurIPS 2024ProgressGym: Alignment with a Millennium of Moral Progress
81. NeurIPS 2024PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation
82. NeurIPS 2024Queueing Matching Bandits with Preference Feedback
83. NeurIPS 2024Recurrent neural network dynamical systems for biological vision
84. NeurIPS 2024Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems
85. NeurIPS 2024SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
86. NeurIPS 2024SGLang: Efficient Execution of Structured Language Model Programs
87. NeurIPS 2024Spectral Learning of Shared Dynamics Between Generalized-Linear Processes
88. NeurIPS 2024Structural Inference of Dynamical Systems with Conjoined State Space Models
89. NeurIPS 2024Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems
90. NeurIPS 2024Unconditional stability of a recurrent neural circuit implementing divisive normalization
91. NeurIPS 2024User-Creator Feature Polarization in Recommender Systems with Dual Influence
92. NeurIPS 2024When are dynamical systems learned from time series data statistically accurate?

常见问题

2023–2026 年四大会议一共有多少篇对话系统论文？

共 419 篇，按年份分别是 2023 年 49 篇、2024 年 92 篇、2025 年 107 篇、2026 年 171 篇。

NeurIPS 2026 有多少篇对话系统论文？

NeurIPS 2026 有 76 篇对话系统论文，上一届是 46 篇。

ICLR 2026 有多少篇对话系统论文？

ICLR 2026 有 36 篇对话系统论文，上一届是 34 篇。

ICML 2026 有多少篇对话系统论文？

ICML 2026 有 54 篇对话系统论文，上一届是 20 篇。

CVPR 2026 有多少篇对话系统论文？

CVPR 2026 有 5 篇对话系统论文，上一届是 7 篇。

哪个会议的对话系统论文最多？

NeurIPS，2023–2026 年共 189 篇。