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

192 papers, page 4 of 4

151. NeurIPS 2024S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
152. NeurIPS 2024Scaling Law for Time Series Forecasting
153. NeurIPS 2024Scaling White-Box Transformers for Vision
154. NeurIPS 2024Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
155. NeurIPS 2024Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations
156. NeurIPS 2024Selective Attention: Enhancing Transformer through Principled Context Control
157. NeurIPS 2024Separations in the Representational Capabilities of Transformers and Recurrent Architectures
158. NeurIPS 2024Set-based Neural Network Encoding Without Weight Tying
159. NeurIPS 2024ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
160. NeurIPS 2024SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
161. NeurIPS 2024Single Image Reflection Separation via Dual-Stream Interactive Transformers
162. NeurIPS 2024Slot State Space Models
163. NeurIPS 2024SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
164. NeurIPS 2024Spectral Adapter: Fine-Tuning in Spectral Space
165. NeurIPS 2024Spiking Token Mixer: An event-driven friendly Former structure for spiking neural networks
166. NeurIPS 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
167. NeurIPS 2024Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
168. NeurIPS 2024SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
169. NeurIPS 2024SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
170. NeurIPS 2024The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
171. NeurIPS 2024The Expressive Capacity of State Space Models: A Formal Language Perspective
172. NeurIPS 2024The Mamba in the Llama: Distilling and Accelerating Hybrid Models
173. NeurIPS 2024The Selective $G$-Bispectrum and its Inversion: Applications to $G$-Invariant Networks
174. NeurIPS 2024Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
175. NeurIPS 2024Theoretical Foundations of Deep Selective State-Space Models
176. NeurIPS 2024TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
177. NeurIPS 2024Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
178. NeurIPS 2024Towards Croppable Implicit Neural Representations
179. NeurIPS 2024Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
180. NeurIPS 2024Understanding and Minimising Outlier Features in Transformer Training
181. NeurIPS 2024Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
182. NeurIPS 2024Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
183. NeurIPS 2024Understanding Transformer Reasoning Capabilities via Graph Algorithms
184. NeurIPS 2024UNIT: Unifying Image and Text Recognition in One Vision Encoder
185. NeurIPS 2024UniTS: A Unified Multi-Task Time Series Model
186. NeurIPS 2024Universal Neural Functionals
187. NeurIPS 2024Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
188. NeurIPS 2024VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
189. NeurIPS 2024Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
190. NeurIPS 2024xLSTM: Extended Long Short-Term Memory
191. NeurIPS 2024YOLOv10: Real-Time End-to-End Object Detection
192. NeurIPS 2024You Only Cache Once: Decoder-Decoder Architectures for Language Models

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.