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 46 篇，第 1 / 1 页

1. NeurIPS 2025A Counterfactual Semantics for Hybrid Dynamical Systems
2. NeurIPS 2025A Latent Multilayer Graphical Model For Complex, Interdependent Systems
3. NeurIPS 2025A Theoretical Framework for Grokking: Interpolation followed by Riemannian Norm Minimisation
4. NeurIPS 2025Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
5. NeurIPS 2025Bounds on the computational complexity of neurons due to dendritic morphology
6. NeurIPS 2025Causal Discovery over Clusters of Variables in Markovian Systems
7. NeurIPS 2025Characterizing control between interacting subsystems with deep Jacobian estimation
8. NeurIPS 2025ChatbotID: Identifying Chatbots with Granger Causality Test
9. NeurIPS 2025Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems
10. NeurIPS 2025Efficient Spectral Control of Partially Observed Linear Dynamical Systems
11. NeurIPS 2025Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems
12. NeurIPS 2025Environment Inference for Learning Generalizable Dynamical System
13. NeurIPS 2025Federated Dialogue-Semantic Diffusion for Emotion Recognition under Incomplete Modalities
14. NeurIPS 2025Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
15. NeurIPS 2025Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control
16. NeurIPS 2025FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation
17. NeurIPS 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
18. NeurIPS 2025In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation
19. NeurIPS 2025Inferring stochastic dynamics with growth from cross-sectional data
20. NeurIPS 2025Information-Driven Design of Imaging Systems
21. NeurIPS 2025Learning Dynamics of RNNs in Closed-Loop Environments
22. NeurIPS 2025Max Entropy Moment Kalman Filter for Polynomial Systems with Arbitrary Noise
23. NeurIPS 2025Measuring and Controlling Solution Degeneracy across Task-Trained Recurrent Neural Networks
24. NeurIPS 2025Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab
25. NeurIPS 2025Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
26. NeurIPS 2025Modeling Neural Activity with Conditionally Linear Dynamical Systems
27. NeurIPS 2025MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
28. NeurIPS 2025MTRec: Learning to Align with User Preferences via Mental Reward Models
29. NeurIPS 2025Normalization in Attention Dynamics
30. NeurIPS 2025OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems
31. NeurIPS 2025Predictability Enables Parallelization of Nonlinear State Space Models
32. NeurIPS 2025Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme
33. NeurIPS 2025Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs
34. NeurIPS 2025Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems
35. NeurIPS 2025Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
36. NeurIPS 2025RNNs perform task computations by dynamically warping neural representations
37. NeurIPS 2025Safely Learning Controlled Stochastic Dynamics
38. NeurIPS 2025SING: SDE Inference via Natural Gradients
39. NeurIPS 2025Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems
40. NeurIPS 2025SpectraLDS: Provable Distillation for Linear Dynamical Systems
41. NeurIPS 2025Stabilizing LTI Systems under Partial Observability: Sample Complexity and Fundamental Limits
42. NeurIPS 2025Stable Port-Hamiltonian Neural Networks
43. NeurIPS 2025TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems
44. NeurIPS 2025UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal Systems
45. NeurIPS 2025Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time
46. NeurIPS 2025Validating LLM-as-a-Judge Systems under Rating Indeterminacy

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。