基础模型适配论文趋势 2023–2026

主要结论

• 基础模型适配论文从 2023 年的 159 篇增长到 2026 年的 602 篇，三年间扩大到约 3.8 倍。
• NeurIPS 是发基础模型适配论文最多的会议，2023–2026 年共 531 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是深度学习 · foundation models：同时属于两个主题的论文从 2023 年的 7 篇增至 2026 年的 66 篇。
• 在「元学习与迁移」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的持续学习是 1.7 倍，基础模型适配是 3.8 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 2026(Mis)generalization of Helpful-Only Fine-Tuning
• ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
• ICLR 2026Benchmarking ECG Foundational Models: A Reality Check Across Clinical Tasks
• CVPR 2026CD-Buffer Complementary Dual-Buffer Framework for Test-Time Adaptation in Adverse Weather
• NeurIPS 2025An Investigation of Memorization Risk in Healthcare Foundation Models
• ICML 2025A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints
• ICLR 2025Better autoregressive regression with LLMs via regression-aware fine-tuning
• CVPR 20255%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks
• NeurIPS 2024Instruction Tuning Large Language Models to Understand Electronic Health Records
• ICML 2024By Tying Embeddings You Are Assuming the Distributional Hypothesis
• ICLR 2024A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
• CVPR 2024DePT: Decoupled Prompt Tuning
• NeurIPS 2023A Fast and Accurate Estimator for Large Scale Linear Model via Data Averaging
• ICML 2023Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations
• ICLR 2023A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
• CVPR 2023A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting
• NeurIPS 2026A Graph Foundation Model for Unified Clustering
• ICML 2026AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments
• ICLR 2026Bridging Radiology and Pathology Foundation Models via Concept-Based Multimodal Co-Adaptation
• CVPR 2026Fed-ADE Adaptive Learning Rate for Federated Post-adaptation under Distribution Shift

全部基础模型适配论文

共 602 篇，第 7 / 13 页

301. ICML 2026Can We Build a Monolithic Model for Fake Image Detection? SICA: Semantic-Induced Constrained Adaptation for Unified-Yet-Discriminative Artifact Feature Space Reconstruction
302. ICML 2026Causal Fine-Tuning under Latent Confounded Shift
303. ICML 2026ChaosNexus: A Foundation Model for ODE-based Chaotic System Forecasting with Hierarchical Multi-scale Awareness
304. ICML 2026COBRA: Contribution-Based Bayesian Rank Allocation for Parameter-Efficient Fine-Tuning
305. ICML 2026CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
306. ICML 2026Collaborative and Efficient Fine-tuning: Leveraging Task Similarity
307. ICML 2026Compression as Adaptation: Implicit Visual Representation with Diffusion Foundation Models
308. ICML 2026ConFlux: Multivariate Time Series in Flux, One Unified Forecast in Confluence
309. ICML 2026Constrained Flow Optimization via Sequential Fine-Tuning for Molecular Design
310. ICML 2026Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm
311. ICML 2026CSPLoRA: Confidence-Guided Structure Planning for Low-Rank Adaptation
312. ICML 2026Cure-SFT: Diagnostic-Guided Data Curation for Instruction Tuning
313. ICML 2026Data Difficulty and the Generalization–Extrapolation Tradeoff in LLM Fine-Tuning
314. ICML 2026Decoupled Low-Rank Adaptation for Robust Federated Fine-Tuning
315. ICML 2026Decoupled Training with Local Reinforcement Fine-Tuning in Federated Learning
316. ICML 2026DiP-G: Discrete Prompting for Graph Neural Networks
317. ICML 2026Distilling Linearized Behavior into Non-linear Fine-Tuning for Effective Task Arithmetic
318. ICML 2026Distribution Transformers: Fast Approximate Bayesian Inference With On-The-Fly Prior Adaptation
319. ICML 2026Diversity-aware Weight Perturbation Promotes Robust Adaptation
320. ICML 2026Don't Reinvent the Wheel, Just Realign the Spokes: Resource-Efficient Federated Fine-Tuning via Rank-Wise Expert Assembly
321. ICML 2026DTop-p MoE: Sparsity-Controlled Dynamic Top-p MoE for Foundation Model Pre-training
322. ICML 2026EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning
323. ICML 2026EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Analyses of EEG Foundation Models
324. ICML 2026EmBrace: A Collective Knowledge Fusion Framework Toward Unified EEG Foundation Models
325. ICML 2026End-to-End Compression for Tabular Foundation Models
326. ICML 2026Energy-Structured Low-Rank Adaptation for Continual Learning
327. ICML 2026Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning
328. ICML 2026FedHera: Towards Drift-Resilient Federated Fine-tuning with Heterogeneous Resources
329. ICML 2026FedPissa: Towards Federated Personalized Adaptation of Foundation Models via LoRA Subspace Mapping
330. ICML 2026FedTreeLoRA: Reconciling Statistical and Functional Heterogeneity in Federated LoRA Fine-Tuning
331. ICML 2026Fine-Tuning of Transformer models with Frames
332. ICML 2026Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
333. ICML 2026Fingerprinting Pre-trained Encoders under Arbitrary Downstream Fine-Tuning via Adversarial Shifting
334. ICML 2026FIRE: Multi-Fidelity Regression with Distribution-Conditioned In-Context Learning Using Tabular Foundation Models
335. ICML 2026FiX: Introducing Fine-grained Forget Gate into Softmax Attention
336. ICML 2026Foundation Inference Models for Ordinary Differential Equations
337. ICML 2026From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning
338. ICML 2026Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR
339. ICML 2026GFMate: Empowering Graph Foundation Models with Test-time Prompt Tuning
340. ICML 2026GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data
341. ICML 2026GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language Models
342. ICML 2026GR-LoRA: Gradient-Recycling Low-Rank Adaptation for Class-Incremental Learning
343. ICML 2026Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Control
344. ICML 2026ICR-RL: Deep Reinforcement Learning via In-Context-Regression
345. ICML 2026iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
346. ICML 2026Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models
347. ICML 2026JANUS-LORA: A Balanced Low-Rank Adaptation for Continual Learning
348. ICML 2026KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices
349. ICML 2026Learning a Zeroth-Order Optimizer for Fine-Tuning LLMs
350. ICML 2026Learning Graph Foundation Models on Riemannian Graph-of-Graphs

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。