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 107 篇，第 2 / 3 页

51. ICML 2025Position: Graph Matching Systems Deserve Better Benchmarks
52. ICML 2025Position: Retrieval-augmented systems can be dangerous medical communicators
53. ICML 2025Quadruple Attention in Many-body Systems for Accurate Molecular Property Predictions
54. ICML 2025Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization
55. ICML 2025Rethink the Role of Deep Learning towards Large-scale Quantum Systems
56. ICML 2025Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
57. ICML 2025Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks
58. ICML 2025SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language Models
59. ICML 2025Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From Data
60. ICML 2025Temperature-Annealed Boltzmann Generators
61. ICML 2025Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
62. NeurIPS 2025A Counterfactual Semantics for Hybrid Dynamical Systems
63. NeurIPS 2025A Latent Multilayer Graphical Model For Complex, Interdependent Systems
64. NeurIPS 2025A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
65. NeurIPS 2025Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
66. NeurIPS 2025Bounds on the computational complexity of neurons due to dendritic morphology
67. NeurIPS 2025Causal Discovery over Clusters of Variables in Markovian Systems
68. NeurIPS 2025Characterizing control between interacting subsystems with deep Jacobian estimation
69. NeurIPS 2025ChatbotID: Identifying Chatbots with Granger Causality Test
70. NeurIPS 2025Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems
71. NeurIPS 2025Efficient Spectral Control of Partially Observed Linear Dynamical Systems
72. NeurIPS 2025Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems
73. NeurIPS 2025Environment Inference for Learning Generalizable Dynamical System
74. NeurIPS 2025Federated Dialogue-Semantic Diffusion for Emotion Recognition under Incomplete Modalities
75. NeurIPS 2025Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
76. NeurIPS 2025Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control
77. NeurIPS 2025FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation
78. NeurIPS 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
79. NeurIPS 2025In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation
80. NeurIPS 2025Inferring stochastic dynamics with growth from cross-sectional data
81. NeurIPS 2025Information-Driven Design of Imaging Systems
82. NeurIPS 2025Learning Dynamics of RNNs in Closed-Loop Environments
83. NeurIPS 2025Max Entropy Moment Kalman Filter for Polynomial Systems with Arbitrary Noise
84. NeurIPS 2025Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks
85. NeurIPS 2025Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab
86. NeurIPS 2025Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
87. NeurIPS 2025Modeling Neural Activity with Conditionally Linear Dynamical Systems
88. NeurIPS 2025MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
89. NeurIPS 2025MTRec: Learning to Align with User Preferences via Mental Reward Models
90. NeurIPS 2025Normalization in Attention Dynamics
91. NeurIPS 2025OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems
92. NeurIPS 2025Predictability Enables Parallelization of Nonlinear State Space Models
93. NeurIPS 2025Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme
94. NeurIPS 2025Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs
95. NeurIPS 2025Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems
96. NeurIPS 2025Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
97. NeurIPS 2025RNNs perform task computations by dynamically warping neural representations
98. NeurIPS 2025Safely Learning Controlled Stochastic Dynamics
99. NeurIPS 2025SING: SDE Inference via Natural Gradients
100. NeurIPS 2025Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems

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。