用户建模论文趋势 2023–2026

偏好与行为建模

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 335 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

用户建模论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023101614949
2024181220454
20254217201190
202651403219142

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

全部用户建模论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 85 篇，第 1 / 2 页

  1. ICLR 2026A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction
  2. ICLR 2026Ads that Stick: Near-Optimal Ad Optimization through Psychological Behavior Models
  3. ICLR 2026Behavior Learning (BL)
  4. ICLR 2026Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback
  5. ICLR 2026Beyond Markovian Drifts: Action-Biased Geometric Walks with Memory for Personalized Summarization
  6. ICLR 2026Beyond Pairwise: Empowering LLM Alignment With (Ranked) Choice Modeling
  7. ICLR 2026Causally Robust Preference Learning with Reasons
  8. ICLR 2026Chessformer: A Unified Architecture for Chess Modeling
  9. ICLR 2026ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks
  10. ICLR 2026Disentangling Length Bias in Preference Learning via Response-Conditioned Modeling
  11. ICLR 2026DRIFT: Learning from Abundant User Dissatisfaction in Real-World Preference Learning
  12. ICLR 2026DynaGuard: A Dynamic Guardian Model With User-Defined Policies
  13. ICLR 2026Flipping the Dialogue: Training and Evaluating User Language Models
  14. ICLR 2026From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents
  15. ICLR 2026iFusion: Integrating Dynamic Interest Streams via Diffusion Model for Click-Through Rate Prediction
  16. ICLR 2026Lean Finder: Semantic Search for Mathlib That Understands User Intents
  17. ICLR 2026Learned Meta-Tokens for Language Modeling
  18. ICLR 2026Learning Human Habits with Rule-Guided Active Inference
  19. ICLR 2026Learning to summarize user information for personalized reinforcement learning from human feedback
  20. ICLR 2026Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts
  21. ICLR 2026Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders
  22. ICLR 2026MENLO: From Preferences to Proficiency – Evaluating and Modeling Native-like Quality Across 47 Languages
  23. ICLR 2026MIMIC-Bench: Exploring the User-Like Thinking and Mimicking Capabilities of Multimodal Large Language Models
  24. ICLR 2026Model-Guided Microstimulation Steers Primate Visual Behavior
  25. ICLR 2026More Than What Was Chosen: LLM-based Explainable Recommendation Beyond Noisy User Preferences
  26. ICLR 2026NextQuill: Causal Preference Modeling for Enhancing LLM Personalization
  27. ICLR 2026Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
  28. ICLR 2026PGRF-Net: A Prototype-Guided Relational Fusion Network for Diagnostic Multivariate Time-Series Anomaly Detection
  29. ICLR 2026Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling
  30. ICLR 2026ProPerSim: Developing Proactive and Personalized AI Assistants through User-Assistant Simulation
  31. ICLR 2026REAL: Reading Out Transformer Activations for Precise Localization in Language Model Steering
  32. ICLR 2026Robust Preference Alignment via Directional Neighborhood Consensus
  33. ICLR 2026Routing, Cascades, and User Choice for LLMs
  34. ICLR 2026Steerable Adversarial Scenario Generation through Test-Time Preference Alignment
  35. ICLR 2026Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback
  36. ICLR 2026Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap
  37. ICLR 2026Towards Cognitively-Faithful Decision-Making Models to Improve AI Alignment
  38. ICLR 2026Towards Persistent Noise-Tolerant Active Learning of Regular Languages with Class Query
  39. ICLR 2026What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data
  40. ICLR 2026Your Language Model Secretly Contains Personality Subnetworks
  41. ICLR 2025BLEND: Behavior-guided Neural Population Dynamics Modeling via Privileged Knowledge Distillation
  42. ICLR 2025BRAID: Input-driven Nonlinear Dynamical Modeling of Neural-Behavioral Data
  43. ICLR 2025Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization
  44. ICLR 2025Causally Motivated Sycophancy Mitigation for Large Language Models
  45. ICLR 2025Finally Rank-Breaking Conquers MNL Bandits: Optimal and Efficient Algorithms for MNL Assortment
  46. ICLR 2025Fine-Grained Verifiers: Preference Modeling as Next-token Prediction in Vision-Language Alignment
  47. ICLR 2025Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective
  48. ICLR 2025Framer: Interactive Frame Interpolation
  49. ICLR 2025HelpSteer2-Preference: Complementing Ratings with Preferences
  50. ICLR 2025Language Representations Can be What Recommenders Need: Findings and Potentials

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查用户建模在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "user-modeling"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇用户建模论文？
共 335 篇，按年份分别是 2023 年 49 篇、2024 年 54 篇、2025 年 90 篇、2026 年 142 篇。
NeurIPS 2026 有多少篇用户建模论文？
NeurIPS 2026 有 51 篇用户建模论文，上一届是 42 篇。
ICLR 2026 有多少篇用户建模论文？
ICLR 2026 有 40 篇用户建模论文，上一届是 17 篇。
ICML 2026 有多少篇用户建模论文？
ICML 2026 有 32 篇用户建模论文，上一届是 20 篇。
CVPR 2026 有多少篇用户建模论文？
CVPR 2026 有 19 篇用户建模论文，上一届是 11 篇。
哪个会议的用户建模论文最多？
NeurIPS，2023–2026 年共 121 篇。

「教育与交互」下的其他主题