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 189 篇，第 3 / 4 页

101. NeurIPS 2025Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules
102. NeurIPS 2025Modeling Neural Activity with Conditionally Linear Dynamical Systems
103. NeurIPS 2025MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
104. NeurIPS 2025MTRec: Learning to Align with User Preferences via Mental Reward Models
105. NeurIPS 2025Normalization in Attention Dynamics
106. NeurIPS 2025OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems
107. NeurIPS 2025Predictability Enables Parallelization of Nonlinear State Space Models
108. NeurIPS 2025Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme
109. NeurIPS 2025Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs
110. NeurIPS 2025Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems
111. NeurIPS 2025Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
112. NeurIPS 2025RNNs perform task computations by dynamically warping neural representations
113. NeurIPS 2025Safely Learning Controlled Stochastic Dynamics
114. NeurIPS 2025SING: SDE Inference via Natural Gradients
115. NeurIPS 2025Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems
116. NeurIPS 2025SpectraLDS: Provable Distillation for Linear Dynamical Systems
117. NeurIPS 2025Stabilizing LTI Systems under Partial Observability: Sample Complexity and Fundamental Limits
118. NeurIPS 2025Stable Port-Hamiltonian Neural Networks
119. NeurIPS 2025TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems
120. NeurIPS 2025UnCLe: Towards Scalable Dynamic Causal Discovery in Non-linear Temporal Systems
121. NeurIPS 2025Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time
122. NeurIPS 2025Validating LLM-as-a-Judge Systems under Rating Indeterminacy
123. NeurIPS 2024A Full-duplex Speech Dialogue Scheme Based On Large Language Model
124. NeurIPS 2024A scalable generative model for dynamical system reconstruction from neuroimaging data
125. NeurIPS 2024A Walsh Hadamard Derived Linear Vector Symbolic Architecture
126. NeurIPS 2024Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists
127. NeurIPS 2024Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
128. NeurIPS 2024An Analysis of Elo Rating Systems via Markov Chains
129. NeurIPS 2024Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems
130. NeurIPS 2024Automatically Learning Hybrid Digital Twins of Dynamical Systems
131. NeurIPS 2024Barely Random Algorithms and Collective Metrical Task Systems
132. NeurIPS 2024Bayesian Identification of the Hamiltonian Inductive Bias in Dynamical Systems
133. NeurIPS 2024Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data
134. NeurIPS 2024Comprehensive Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for the Polish Language
135. NeurIPS 2024Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets
136. NeurIPS 2024ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
137. NeurIPS 2024Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models
138. NeurIPS 2024Disentangled Representation Learning in Non-Markovian Causal Systems
139. NeurIPS 2024Disentangling the Roles of Distinct Cell Classes with Cell-Type Dynamical Systems
140. NeurIPS 2024Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems
141. NeurIPS 2024eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling
142. NeurIPS 2024FairJob: A Real-World Dataset for Fairness in Online Systems
143. NeurIPS 2024Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure
144. NeurIPS 2024Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems
145. NeurIPS 2024HHD-GP: Incorporating Helmholtz-Hodge Decomposition into Gaussian Processes for Learning Dynamical Systems
146. NeurIPS 2024How Does Message Passing Improve Collaborative Filtering?
147. NeurIPS 2024Identifiability Analysis of Linear ODE Systems with Hidden Confounders
148. NeurIPS 2024Identification of Analytic Nonlinear Dynamical Systems with Non-asymptotic Guarantees
149. NeurIPS 2024Identifying Equivalent Training Dynamics
150. NeurIPS 2024Initializing Services in Interactive ML Systems for Diverse Users

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。