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 6 / 30 页

  1. ICLR 2026Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
  2. ICLR 2026Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
  3. ICLR 2026Task-Aware Data Selection via Proxy-Label Enhanced Distribution Matching for LLM Finetuning
  4. ICLR 2026TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
  5. ICLR 2026Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models
  6. ICLR 2026The Forecast After the Forecast: A Post-Processing Shift in Time Series
  7. ICLR 2026The Softmax Bottleneck Does Not Limit the Probabilities of the Most Likely Tokens
  8. ICLR 2026Thompson Sampling via Fine-Tuning of LLMs
  9. ICLR 2026Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward Passes
  10. ICLR 2026Token-level Data Selection for Safe LLM Fine-tuning
  11. ICLR 2026TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
  12. ICLR 2026TokMem: Tokenized Procedural Memory for Large Language Models
  13. ICLR 2026Towards a Foundation Model for Crowdsourced Label Aggregation
  14. ICLR 2026TRAC: Tensor-Train based Across-layer Compression for Parameter-Efficient Fine-Tuning
  15. ICLR 2026Train-before-Test Harmonizes Language Model Rankings
  16. ICLR 2026Training Large Language Models To Reason In Parallel With Global Forking Tokens
  17. ICLR 2026Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
  18. ICLR 2026Transducing Language Models
  19. ICLR 2026TS$^2$: Training with Sparsemax+, Testing with Softmax for Accurate and Diverse LLM Fine-Tuning
  20. ICLR 2026TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis
  21. ICLR 2026Type-Compliant Adaptation Cascades
  22. ICLR 2026Uni-NTFM: A Unified Foundation Model for EEG Signal Representation Learning
  23. ICLR 2026UniCA: Unified Covariate Adaptation for Time Series Foundation Model
  24. ICLR 2026Universal Properties of Activation Sparsity in Modern Large Language Models
  25. ICLR 2026VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
  26. ICLR 2026Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis
  27. ICLR 2026Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective
  28. ICLR 2026Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics
  29. ICML 2026A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn’t)
  30. ICML 2026A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search
  31. ICML 2026A Risk Decomposition Framework for Pre-hoc Fine-tuning Prediction
  32. ICML 2026A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
  33. ICML 2026ACO-MoE-LoRA: Evolving-while-Training for Adapting Segment Anything Model 2 to Specialized Domains
  34. ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
  35. ICML 2026AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments
  36. ICML 2026Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
  37. ICML 2026AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
  38. ICML 2026Annotations Mitigate Post-Training Mode Collapse
  39. ICML 2026Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles
  40. ICML 2026AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
  41. ICML 2026Baguan-TS: dual in-context learning model for time series forecasting with covariates
  42. ICML 2026Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
  43. ICML 2026Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
  44. ICML 2026Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
  45. ICML 2026Beyond Static Allocation: Dynamic Sensitivity-Aware Fine-Tuning for Vision Transformers
  46. ICML 2026Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
  47. ICML 2026BIOARC: Discovering Optimal Neural Architectures for Biological Foundation Models
  48. ICML 2026Black-Box Assisted Regression: Phase Transitions and Minimax Optimality
  49. ICML 2026CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data
  50. ICML 2026Can Muon Fine-tune Adam-Pretrained Models?

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