Deep learning · representation learning papers, 2023–2026

Key findings

• Deep learning · representation learning fell from 259 papers in 2023 to 214 in 2026, so interest is cooling.
• NeurIPS publishes the most Deep learning · representation learning work: 279 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 11 in 2023 to 28 in 2026.
• Among the 11 topics under Deep Learning, it ranks #7 by 2026 paper count; the fastest grower in the group, Diffusion Models, is up 4.1x versus 0.8x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Active Learning as Nullspace Regulation: A Spectral Representation Perspective
• ICML 2026Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learning
• ICLR 2026Boosting Open Set Recognition Performance through Modulated Representation Learning
• CVPR 2026CanonCGT Reference-Based Color Grading via Canonical Pivot Representation
• NeurIPS 2025Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features
• ICML 2025Banyan: Improved Representation Learning with Explicit Structure
• ICLR 2025Edge-aware Image Smoothing with Relative Wavelet Domain Representation
• CVPR 20253D-SLNR: A Super Lightweight Neural Representation for Large-scale 3D Mapping
• NeurIPS 2024GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning
• ICML 2024Data-free Neural Representation Compression with Riemannian Neural Dynamics
• ICLR 2024$\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation
• CVPR 2024Disentangled Prompt Representation for Domain Generalization
• NeurIPS 2023[Re] CrossWalk: Fairness-enhanced Node Representation Learning
• ICML 2023A theory of representation learning gives a deep generalisation of kernel methods
• ICLR 2023Bispectral Neural Networks
• CVPR 2023AnyFlow: Arbitrary Scale Optical Flow With Implicit Neural Representation
• NeurIPS 2026Approximation in Contrastive Representation Learning
• ICML 2026Amortized Maximum Inner Product Search with Learned Support Functions
• ICLR 2026Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement
• CVPR 2026Enhancing Visual Representation with Textual Semantics Textual Semantics-Powered Prototypes for

All Deep learning · representation learning papers

279 papers, page 2 of 6

51. NeurIPS 2026Representation Learning Enables Scalable Multitask Deep Reinforcement Learning
52. NeurIPS 2026Representation Preconditioning for Efficient Diffusion Model Training
53. NeurIPS 2026Self-Distillation of Hidden Layers for Masked Self-Supervised Representation Learning
54. NeurIPS 2026Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
55. NeurIPS 2026The Bayesian Origin of the Probability Weighting Function in Human Representation of Probabilities
56. NeurIPS 2026The Geometry of Agent Skills: Non-Commutative Composition in Representation Space
57. NeurIPS 2026TopoPrune: Robust Data Pruning via Unified Latent Space Topology
58. NeurIPS 2026TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders
59. NeurIPS 2026What Does the Brain See? Multiview Neural Representation to Demystify the Brain-Visual Alignment
60. NeurIPS 2025$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
61. NeurIPS 2025Adv-SSL: Adversarial Self-Supervised Representation Learning with Theoretical Guarantees
62. NeurIPS 2025Anti-Aliased 2D Gaussian Splatting
63. NeurIPS 2025Auto-Compressing Networks
64. NeurIPS 2025Beyond Modality Collapse: Representation Blending for Multimodal Dataset Distillation
65. NeurIPS 2025Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features
66. NeurIPS 2025Conditional Representation Learning for Customized Tasks
67. NeurIPS 2025Connecting Neural Models Latent Geometries with Relative Geodesic Representations
68. NeurIPS 2025DISCO: Disentangled Communication Steering for Large Language Models
69. NeurIPS 2025Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision
70. NeurIPS 2025Disentangled Representation Learning via Modular Compositional Bias
71. NeurIPS 2025Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions
72. NeurIPS 2025EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation
73. NeurIPS 2025FORLA: Federated Object-centric Representation Learning with Slot Attention
74. NeurIPS 2025GAMMA: Gated Multi-hop Message Passing for Homophily-Agnostic Node Representation in GNNs
75. NeurIPS 2025Global Minimizers of Sigmoid Contrastive Loss
76. NeurIPS 2025Grids Often Outperform Implicit Neural Representation at Compressing Dense Signals
77. NeurIPS 2025H3D-DGS: Exploring Heterogeneous 3D Motion Representation for Deformable 3D Gaussian Splatting
78. NeurIPS 2025How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
79. NeurIPS 2025Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning
80. NeurIPS 2025Learning Differential Pyramid Representation for Tone Mapping
81. NeurIPS 2025Learning Generalizable Shape Completion with SIM(3) Equivariance
82. NeurIPS 2025Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
83. NeurIPS 2025LLM Interpretability with Identifiable Temporal-Instantaneous Representation
84. NeurIPS 2025MaxSup: Overcoming Representation Collapse in Label Smoothing
85. NeurIPS 2025Measure-Theoretic Anti-Causal Representation Learning
86. NeurIPS 2025Mitigating Spurious Features in Contrastive Learning with Spectral Regularization
87. NeurIPS 2025More of the Same: Persistent Representational Harms Under Increased Representation
88. NeurIPS 2025NegoCollab: A Common Representation Negotiation Approach for Heterogeneous Collaborative Perception
89. NeurIPS 2025On the Value of Cross-Modal Misalignment in Multimodal Representation Learning
90. NeurIPS 2025Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning
91. NeurIPS 2025PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation
92. NeurIPS 2025Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings
93. NeurIPS 2025PoLAR: Polar-Decomposed Low-Rank Adapter Representation
94. NeurIPS 2025Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning
95. NeurIPS 2025Random Forest Autoencoders for Guided Representation Learning
96. NeurIPS 2025REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
97. NeurIPS 2025Reward-oriented Causal Representation Learning
98. NeurIPS 2025S-Crescendo: A Nested Transformer Weaving Framework for Scalable Nonlinear System in S-Domain Representation
99. NeurIPS 2025Scaling Language-centric Omnimodal Representation Learning
100. NeurIPS 2025Symmetry-Preserving Conformer Ensemble Networks for Molecular Representation Learning

FAQ

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

802 in total: 259 in 2023, 177 in 2024, 152 in 2025, 214 in 2026.

How many Deep learning · representation learning papers are at NeurIPS 2026?

NeurIPS 2026 has 59 Deep learning · representation learning papers, versus 54 the year before.

How many Deep learning · representation learning papers are at ICLR 2026?

ICLR 2026 has 39 Deep learning · representation learning papers, versus 37 the year before.

How many Deep learning · representation learning papers are at ICML 2026?

ICML 2026 has 74 Deep learning · representation learning papers, versus 35 the year before.

How many Deep learning · representation learning papers are at CVPR 2026?

CVPR 2026 has 42 Deep learning · representation learning papers, versus 26 the year before.

Which conference publishes the most Deep learning · representation learning papers?

NeurIPS, with 279 papers from 2023 to 2026.