Foundation Model Adaptation papers, 2023–2026

Key findings

• Foundation Model Adaptation went from 159 papers in 2023 to 602 in 2026, roughly 3.8x in three years.
• NeurIPS publishes the most Foundation Model Adaptation work: 531 papers from 2023 to 2026, 36% of the four-venue total.
• The fastest-growing overlap is with Deep learning · foundation models: papers tagged with both rose from 7 in 2023 to 66 in 2026.
• Among the 5 topics under Meta-Learning and Transfer, it ranks #1 by 2026 paper count; the fastest grower in the group, Continual Learning, is up 1.7x versus 3.8x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Foundation Model Adaptation papers

602 papers, page 6 of 13

251. ICLR 2026Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts
252. ICLR 2026Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models
253. ICLR 2026Task-Aware Data Selection via Proxy-Label Enhanced Distribution Matching for LLM Finetuning
254. ICLR 2026TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
255. ICLR 2026Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models
256. ICLR 2026The Forecast After the Forecast: A Post-Processing Shift in Time Series
257. ICLR 2026The Softmax Bottleneck Does Not Limit the Probabilities of the Most Likely Tokens
258. ICLR 2026Thompson Sampling via Fine-Tuning of LLMs
259. ICLR 2026Three Forward, One Backward: Memory-Efficient Full-Rank Fine-Tuning of Large Models via Extra Forward Passes
260. ICLR 2026Token-level Data Selection for Safe LLM Fine-tuning
261. ICLR 2026TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token Ditching
262. ICLR 2026TokMem: Tokenized Procedural Memory for Large Language Models
263. ICLR 2026Towards a Foundation Model for Crowdsourced Label Aggregation
264. ICLR 2026TRAC: Tensor-Train based Across-layer Compression for Parameter-Efficient Fine-Tuning
265. ICLR 2026Train-before-Test Harmonizes Language Model Rankings
266. ICLR 2026Training Large Language Models To Reason In Parallel With Global Forking Tokens
267. ICLR 2026Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match
268. ICLR 2026Transducing Language Models
269. ICLR 2026TS$^2$: Training with Sparsemax+, Testing with Softmax for Accurate and Diverse LLM Fine-Tuning
270. ICLR 2026TSPulse: Tiny Pre-Trained Models with Disentangled Representations for Rapid Time-Series Analysis
271. ICLR 2026Type-Compliant Adaptation Cascades
272. ICLR 2026Uni-NTFM: A Unified Foundation Model for EEG Signal Representation Learning
273. ICLR 2026UniCA: Unified Covariate Adaptation for Time Series Foundation Model
274. ICLR 2026Universal Properties of Activation Sparsity in Modern Large Language Models
275. ICLR 2026VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
276. ICLR 2026Why Attention Patterns Exist: A Unifying Temporal Perspective Analysis
277. ICLR 2026Why Reinforcement Fine-Tuning Enables MLLMs Preserve Prior Knowledge Better: A Data Perspective
278. ICLR 2026Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics
279. ICML 2026A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn’t)
280. ICML 2026A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search
281. ICML 2026A Risk Decomposition Framework for Pre-hoc Fine-tuning Prediction
282. ICML 2026A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning
283. ICML 2026ACO-MoE-LoRA: Evolving-while-Training for Adapting Segment Anything Model 2 to Specialized Domains
284. ICML 2026Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance
285. ICML 2026AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments
286. ICML 2026Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating
287. ICML 2026AGZO: Activation-Guided Zeroth-Order Optimization for LLM Fine-Tuning
288. ICML 2026Annotations Mitigate Post-Training Mode Collapse
289. ICML 2026Are Common Substructures Transferable? Riemannian Graph Foundation Model with Neural Vector Bundles
290. ICML 2026AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
291. ICML 2026Baguan-TS: dual in-context learning model for time series forecasting with covariates
292. ICML 2026Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
293. ICML 2026Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models
294. ICML 2026Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
295. ICML 2026Beyond Static Allocation: Dynamic Sensitivity-Aware Fine-Tuning for Vision Transformers
296. ICML 2026Beyond Temperature: Hyperfitting as a Late-Stage Geometric Expansion
297. ICML 2026BIOARC: Discovering Optimal Neural Architectures for Biological Foundation Models
298. ICML 2026Black-Box Assisted Regression: Phase Transitions and Minimax Optimality
299. ICML 2026CalM: A Self-Supervised Foundation Model for Population Dynamics in Calcium Imaging Data
300. ICML 2026Can Muon Fine-tune Adam-Pretrained Models?

FAQ

How many Foundation Model Adaptation papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

1,492 in total: 159 in 2023, 270 in 2024, 461 in 2025, 602 in 2026.

How many Foundation Model Adaptation papers are at NeurIPS 2026?

NeurIPS 2026 has 182 Foundation Model Adaptation papers, versus 174 the year before.

How many Foundation Model Adaptation papers are at ICLR 2026?

ICLR 2026 has 187 Foundation Model Adaptation papers, versus 149 the year before.

How many Foundation Model Adaptation papers are at ICML 2026?

ICML 2026 has 142 Foundation Model Adaptation papers, versus 76 the year before.

How many Foundation Model Adaptation papers are at CVPR 2026?

CVPR 2026 has 91 Foundation Model Adaptation papers, versus 62 the year before.

Which conference publishes the most Foundation Model Adaptation papers?

NeurIPS, with 531 papers from 2023 to 2026.