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 116 篇，第 2 / 3 页

51. ICML 2026Universal Learning of Nonlinear Dynamics
52. ICML 2026User-Aware Active Knowledge Acquisition for Emotional Support Dialogue
53. ICML 2026VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems
54. ICML 2026Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
55. ICML 2025A Dynamical Systems-Inspired Pruning Strategy for Addressing Oversmoothing in Graph Attention Networks
56. ICML 2025Accurate Identification of Communication Between Multiple Interacting Neural Populations
57. ICML 2025Aligning Spoken Dialogue Models from User Interactions
58. ICML 2025Dialogue Without Limits: Constant-Sized KV Caches for Extended Response in LLMs
59. ICML 2025Discovering Physics Laws of Dynamical Systems via Invariant Function Learning
60. ICML 2025Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems
61. ICML 2025Guided Structural Inference: Leveraging Priors with Soft Gating Mechanisms
62. ICML 2025Identifying Neural Dynamics Using Interventional State Space Models
63. ICML 2025KoopSTD: Reliable Similarity Analysis between Dynamical Systems via Approximating Koopman Spectrum with Timescale Decoupling
64. ICML 2025Position: Graph Matching Systems Deserve Better Benchmarks
65. ICML 2025Position: Retrieval-augmented systems can be dangerous medical communicators
66. ICML 2025Quadruple Attention in Many-body Systems for Accurate Molecular Property Predictions
67. ICML 2025Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization
68. ICML 2025Rethink the Role of Deep Learning towards Large-scale Quantum Systems
69. ICML 2025Revolve: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization
70. ICML 2025Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks
71. ICML 2025SHARP-Distill: A 68× Faster Recommender System with Hypergraph Neural Networks and Language Models
72. ICML 2025Skip the Equations: Learning Behavior of Personalized Dynamical Systems Directly From Data
73. ICML 2025Temperature-Annealed Boltzmann Generators
74. ICML 2025Unisoma: A Unified Transformer-based Solver for Multi-Solid Systems
75. ICML 2024Amortized Equation Discovery in Hybrid Dynamical Systems
76. ICML 2024An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems
77. ICML 2024Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities
78. ICML 2024Consistent Long-Term Forecasting of Ergodic Dynamical Systems
79. ICML 2024Designing Decision Support Systems using Counterfactual Prediction Sets
80. ICML 2024Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution
81. ICML 2024DynSyn: Dynamical Synergistic Representation for Efficient Learning and Control in Overactuated Embodied Systems
82. ICML 2024DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems
83. ICML 2024Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks
84. ICML 2024From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems
85. ICML 2024Hyperbolic Optimizer as a Dynamical System
86. ICML 2024Infinite-Horizon Distributionally Robust Regret-Optimal Control
87. ICML 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?
88. ICML 2024Learning the Uncertainty Sets of Linear Control Systems via Set Membership: A Non-asymptotic Analysis
89. ICML 2024Mean-field Chaos Diffusion Models
90. ICML 2024Nesting Particle Filters for Experimental Design in Dynamical Systems
91. ICML 2024On the Identifiability of Switching Dynamical Systems
92. ICML 2024On the Independence Assumption in Neurosymbolic Learning
93. ICML 2024Optimal Recurrent Network Topologies for Dynamical Systems Reconstruction
94. ICML 2024Out-of-Domain Generalization in Dynamical Systems Reconstruction
95. ICML 2024PAPM: A Physics-aware Proxy Model for Process Systems
96. ICML 2024Position: A Roadmap to Pluralistic Alignment
97. ICML 2024Position: Explain to Question not to Justify
98. ICML 2024Position: Intent-aligned AI Systems Must Optimize for Agency Preservation
99. ICML 2024Reshape and Adapt for Output Quantization (RAOQ): Quantization-aware Training for In-memory Computing Systems
100. ICML 2024Scaling Tractable Probabilistic Circuits: A Systems Perspective

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。