Deep learning · foundation models papers, 2023–2026

Key findings

• Deep learning · foundation models went from 72 papers in 2023 to 177 in 2026, roughly 2.5x in three years.
• NeurIPS publishes the most Deep learning · foundation models work: 299 papers from 2023 to 2026, 56% of the four-venue total.
• The fastest-growing overlap is with Foundation Model Adaptation: papers tagged with both rose from 7 in 2023 to 66 in 2026.
• Among the 11 topics under Deep Learning, it ranks #8 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 2.5x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Inferotemporal Cortex Collaborates Before It Codes: Non-Serial Inter-Area Synergy in the Macaque Ventral Stream
• ICML 2026ACO-MoE-LoRA: Evolving-while-Training for Adapting Segment Anything Model 2 to Specialized Domains
• ICLR 2026Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization
• CVPR 2026Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression
• NeurIPS 2025An Investigation of Memorization Risk in Healthcare Foundation Models
• ICML 2025Contrastive Localized Language-Image Pre-Training
• ICLR 2025Revisiting Convolution Architecture in the Realm of DNA Foundation Models
• CVPR 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matching
• NeurIPS 2024$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
• ICML 2024Position: On the Societal Impact of Open Foundation Models
• CVPR 20243D-LFM: Lifting Foundation Model
• NeurIPS 2023Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
• ICML 2023Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models
• NeurIPS 2026Do Pathology Foundation Models Encode Disease Progression? A Pseudotime Analysis of Visual Representations
• ICML 2026Alethia: a Foundational Encoder for Voice Deepfakes
• ICLR 2026DND: Boosting Large Language Models with Dynamic Nested Depth
• CVPR 2026UniSER A Foundation Model for Unified Soft Effects Removal
• NeurIPS 2025ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibiltiy Data
• ICML 2025Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
• ICLR 2025Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

All Deep learning · foundation models papers

299 papers, page 3 of 6

101. NeurIPS 2024ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
102. NeurIPS 2024einspace: Searching for Neural Architectures from Fundamental Operations
103. NeurIPS 2024ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer
104. NeurIPS 2024Elliptical Attention
105. NeurIPS 2024Error Correction Output Codes for Robust Neural Networks against Weight-errors: A Neural Tangent Kernel Point of View
106. NeurIPS 2024Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
107. NeurIPS 2024Facilitating Multimodal Classification via Dynamically Learning Modality Gap
108. NeurIPS 2024FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological Sensing
109. NeurIPS 2024Federated Transformer: Multi-Party Vertical Federated Learning on Practical Fuzzily Linked Data
110. NeurIPS 2024FilterNet: Harnessing Frequency Filters for Time Series Forecasting
111. NeurIPS 2024FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models
112. NeurIPS 2024Frequency Adaptive Normalization For Non-stationary Time Series Forecasting
113. NeurIPS 2024From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
114. NeurIPS 2024From Similarity to Superiority: Channel Clustering for Time Series Forecasting
115. NeurIPS 2024FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
116. NeurIPS 2024Graph Convolutions Enrich the Self-Attention in Transformers!
117. NeurIPS 2024Group and Shuffle: Efficient Structured Orthogonal Parametrization
118. NeurIPS 2024How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers
119. NeurIPS 2024Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
120. NeurIPS 2024Improving Generalization of Dynamic Graph Learning via Environment Prompt
121. NeurIPS 2024Improving Neural ODE Training with Temporal Adaptive Batch Normalization
122. NeurIPS 2024In Pursuit of Causal Label Correlations for Multi-label Image Recognition
123. NeurIPS 2024Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery
124. NeurIPS 2024Infinite-Dimensional Feature Interaction
125. NeurIPS 2024Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformation
126. NeurIPS 2024Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting
127. NeurIPS 2024Is Multiple Object Tracking a Matter of Specialization?
128. NeurIPS 2024Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference
129. NeurIPS 2024L-TTA: Lightweight Test-Time Adaptation Using a Versatile Stem Layer
130. NeurIPS 2024LaSCal: Label-Shift Calibration without target labels
131. NeurIPS 2024Latent Functional Maps: a spectral framework for representation alignment
132. NeurIPS 2024Learning diverse causally emergent representations from time series data
133. NeurIPS 2024Learning from Highly Sparse Spatio-temporal Data
134. NeurIPS 2024Learning Group Actions on Latent Representations
135. NeurIPS 2024Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
136. NeurIPS 2024Learning symmetries via weight-sharing with doubly stochastic tensors
137. NeurIPS 2024Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
138. NeurIPS 2024Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models
139. NeurIPS 2024LinNet: Linear Network for Efficient Point Cloud Representation Learning
140. NeurIPS 2024LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
141. NeurIPS 2024MambaTree: Tree Topology is All You Need in State Space Model
142. NeurIPS 2024Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
143. NeurIPS 2024MatFormer: Nested Transformer for Elastic Inference
144. NeurIPS 2024MatrixNet: Learning over symmetry groups using learned group representations
145. NeurIPS 2024Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
146. NeurIPS 2024MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers
147. NeurIPS 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
148. NeurIPS 2024Meta-Learning Universal Priors Using Non-Injective Change of Variables
149. NeurIPS 2024MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
150. NeurIPS 2024Mixtures of Experts for Audio-Visual Learning

FAQ

How many Deep learning · foundation models papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

536 in total: 72 in 2023, 209 in 2024, 78 in 2025, 177 in 2026.

How many Deep learning · foundation models papers are at NeurIPS 2026?

NeurIPS 2026 has 27 Deep learning · foundation models papers, versus 15 the year before.

How many Deep learning · foundation models papers are at ICLR 2026?

ICLR 2026 has 8 Deep learning · foundation models papers, versus 6 the year before.

How many Deep learning · foundation models papers are at ICML 2026?

ICML 2026 has 135 Deep learning · foundation models papers, versus 53 the year before.

How many Deep learning · foundation models papers are at CVPR 2026?

CVPR 2026 has 7 Deep learning · foundation models papers, versus 4 the year before.

Which conference publishes the most Deep learning · foundation models papers?

NeurIPS, with 299 papers from 2023 to 2026.