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 1,492 篇，第 21 / 30 页

  1. NeurIPS 2025On the Loss of Context Awareness in General Instruction Fine-tuning
  2. NeurIPS 2025One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
  3. NeurIPS 2025Optimization Inspired Few-Shot Adaptation for Large Language Models
  4. NeurIPS 2025Parameter Efficient Fine-tuning via Explained Variance Adaptation
  5. NeurIPS 2025PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization
  6. NeurIPS 2025Pay Attention to Small Weights
  7. NeurIPS 2025PaZO: Preconditioned Accelerated Zeroth-Order Optimization for Fine-Tuning LLMs
  8. NeurIPS 2025PoLAR: Polar-Decomposed Low-Rank Adapter Representation
  9. NeurIPS 2025Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward
  10. NeurIPS 2025Prompt Tuning Transformers for Data Memorization
  11. NeurIPS 2025Provable Meta-Learning with Low-Rank Adaptations
  12. NeurIPS 2025Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
  13. NeurIPS 2025QBasicVSR: Temporal Awareness Adaptation Quantization for Video Super-Resolution
  14. NeurIPS 2025Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning
  15. NeurIPS 2025RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models
  16. NeurIPS 2025REVE: A Foundation Model for EEG - Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
  17. NeurIPS 2025Revisiting Semi-Supervised Learning in the Era of Foundation Models
  18. NeurIPS 2025RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models
  19. NeurIPS 2025RoFt-Mol: Benchmarking Robust Fine-tuning with Molecular Graph Foundation Models
  20. NeurIPS 2025RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
  21. NeurIPS 2025S'MoRE: Structural Mixture of Residual Experts for Parameter-Efficient LLM Fine-tuning
  22. NeurIPS 2025Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies
  23. NeurIPS 2025Self-Improving Embodied Foundation Models
  24. NeurIPS 2025SEMPO: Lightweight Foundation Models for Time Series Forecasting
  25. NeurIPS 2025SensorLM: Learning the Language of Wearable Sensors
  26. NeurIPS 2025Sheetpedia: A 300K-Spreadsheet Corpus for Spreadsheet Intelligence and LLM Fine-Tuning
  27. NeurIPS 2025Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis
  28. NeurIPS 2025SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models
  29. NeurIPS 2025Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning
  30. NeurIPS 2025Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping
  31. NeurIPS 2025StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold
  32. NeurIPS 2025Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning
  33. NeurIPS 2025TabDPT: Scaling Tabular Foundation Models on Real Data
  34. NeurIPS 2025TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields
  35. NeurIPS 2025Tabula: A Tabular Self-Supervised Foundation Model for Single-Cell Transcriptomics
  36. NeurIPS 2025Test-Time Adaptive Object Detection with Foundation Model
  37. NeurIPS 2025Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
  38. NeurIPS 2025The Best Instruction-Tuning Data are Those That Fit
  39. NeurIPS 2025The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
  40. NeurIPS 2025The Primacy of Magnitude in Low-Rank Adaptation
  41. NeurIPS 2025This Time is Different: An Observability Perspective on Time Series Foundation Models
  42. NeurIPS 2025To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning
  43. NeurIPS 2025Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper
  44. NeurIPS 2025Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement
  45. NeurIPS 2025Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs
  46. NeurIPS 2025Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning
  47. NeurIPS 2025Towards the Resistance of Neural Network Fingerprinting to Fine-tuning
  48. NeurIPS 2025Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning
  49. NeurIPS 2025Triplets Better Than Pairs: Towards Stable and Effective Self-Play Fine-Tuning for LLMs
  50. NeurIPS 2025TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition

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