基础模型适配论文趋势 2023–2026

微调与适配

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,492 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

基础模型适配论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202381183624159
202494507056270
20251741497662461
202618218714291602

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

全部基础模型适配论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 602 篇，第 9 / 13 页

  1. ICML 2026TarGATE: Target-Aware Data Selection via Token-Attenuation Gates
  2. ICML 2026The Geometry of Narrow Fine-Tuning Degradation: Trajectory Lock-in and Spectral Bifurcation
  3. ICML 2026The Geometry of Sequential Learning: Lie-Bracket Prediction of Transfer Order
  4. ICML 2026Time-PEFT: Temporal and Multichannel Complexity-Based Fine-Tuning for Time-Series Foundation Models
  5. ICML 2026Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models
  6. ICML 2026Towards Understanding the Dynamics of Low-Rank Adaptation
  7. ICML 2026Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R
  8. ICML 2026TuneAhead: Predicting Fine-tuning Performance Before Training Begins
  9. ICML 2026UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models
  10. ICML 2026Uncovering the Latent Potential of Deep Intermediate Representations
  11. ICML 2026Universal Redundancies in Time Series Foundation Models
  12. ICML 2026Unveiling Prior-Data Fitted Networks on Causal Effect Estimation: Pre-Training or Fine-Tuning?
  13. ICML 2026Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
  14. ICML 2026Walrus: A Cross-domain Foundation Model for Continuum Dynamics
  15. ICML 2026Weight Updates as Activation Shifts: A Principled Framework for Steering
  16. ICML 2026When Do Graph Foundation Models Transfer? A Data-Centric Theory
  17. ICML 2026When More Data Doesn't Help: Limits of Adaptation in Multitask Learning
  18. ICML 2026When Tabular Foundation Models Meet Strategic Tabular Data: A Prior Alignment Approach
  19. ICML 2026WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
  20. ICML 2026Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis
  21. NeurIPS 2026(Mis)generalization of Helpful-Only Fine-Tuning
  22. NeurIPS 20263R-Adapter: Retrieval, Rewiring, and Refinement for Efficient Adaptation of 3D Reconstruction Model
  23. NeurIPS 2026A Graph Foundation Model for Unified Clustering
  24. NeurIPS 2026A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction
  25. NeurIPS 2026A unified pairwise distribution matching framework for graph domain adaptation under structure shift
  26. NeurIPS 2026ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective
  27. NeurIPS 2026AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation
  28. NeurIPS 2026Aligned LoRA Updates via Intrinsic Geometry for Federated Low-Rank Adaptation
  29. NeurIPS 2026Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning
  30. NeurIPS 2026Alignment Dynamics in LLM Fine-Tuning
  31. NeurIPS 2026AmbientFM: A Foundation Model for Ambient Sensing
  32. NeurIPS 2026An Analytical Model of Compute-limited Multistage Training Pipelines
  33. NeurIPS 2026An Open-Source Training Dataset for Foundation Models for Black-box Optimization
  34. NeurIPS 2026AR1-ZO: Topology-Aware Rank-1 Zeroth-Order Queries for High-Rank LoRA Fine-Tuning
  35. NeurIPS 2026Auditing Privacy Leakage in Tabular Foundation Model Embeddings
  36. NeurIPS 2026B[FM]$^2$: Brain Foundation Model via Flow Matching with SplitUNet
  37. NeurIPS 2026Barycentric Guidance: Turning Foundation Image Editors into Continuous Affective Controllers
  38. NeurIPS 2026Behavioral Foundation Models for Quality Diversity
  39. NeurIPS 2026Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
  40. NeurIPS 2026Benchmarking Fine-Grained Spatio-Temporal Awareness in Embodied Brain Models
  41. NeurIPS 2026Beyond IID: How General Are Tabular Foundation Models, Really?
  42. NeurIPS 2026Beyond LoRA vs. Full Fine-Tuning: Gradient-Guided Optimizer Routing for LLM Adaptation
  43. NeurIPS 2026Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction
  44. NeurIPS 2026BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning
  45. NeurIPS 2026C2FT: Enhancing Fine-Grained Perception in MLLMs via Confuse-then-Contrast Fine-Tuning
  46. NeurIPS 2026Calibrating Scientific Foundation Models with Inference-Time Stochastic Attention
  47. NeurIPS 2026CanViT: Toward Active-Vision Foundation Models
  48. NeurIPS 2026Certification-Enhanced Generalization Bounds
  49. NeurIPS 2026ChildPose: Foundation for Children Pose Modeling
  50. NeurIPS 2026CLEF: EEG Foundation Models for Learning Clinical Semantics

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 查基础模型适配在 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": "foundation-model-adaptation"}

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基础模型适配论文？
共 1,492 篇，按年份分别是 2023 年 159 篇、2024 年 270 篇、2025 年 461 篇、2026 年 602 篇。
NeurIPS 2026 有多少篇基础模型适配论文？
NeurIPS 2026 有 182 篇基础模型适配论文，上一届是 174 篇。
ICLR 2026 有多少篇基础模型适配论文？
ICLR 2026 有 187 篇基础模型适配论文，上一届是 149 篇。
ICML 2026 有多少篇基础模型适配论文？
ICML 2026 有 142 篇基础模型适配论文，上一届是 76 篇。
CVPR 2026 有多少篇基础模型适配论文？
CVPR 2026 有 91 篇基础模型适配论文，上一届是 62 篇。
哪个会议的基础模型适配论文最多？
NeurIPS，2023–2026 年共 531 篇。

「元学习与迁移」下的其他主题