International Conference on Learning Representations
Fraction of papers covering each topic over time
Topics over-represented at ICLR vs. the field average (2025)
| Year | Title | Citations | Links |
|---|---|---|---|
| 2020 | An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | 57,099 | S2 · arXiv |
| 2021 | LoRA: Low-Rank Adaptation of Large Language Models | 16,298 | S2 · arXiv |
| 2020 | Denoising Diffusion Implicit Models | 10,648 | S2 · arXiv |
| 2020 | Score-Based Generative Modeling through Stochastic Differential Equations | 9,315 | S2 · arXiv |
| 2019 | BERTScore: Evaluating Text Generation with BERT | 7,723 | S2 · arXiv |
| 2019 | ALBERT: A Lite BERT for Self-supervised Learning of Language Representations | 7,224 | S2 · arXiv |
| 2020 | Measuring Massive Multitask Language Understanding | 7,014 | S2 · arXiv |
| 2020 | Deformable DETR: Deformable Transformers for End-to-End Object Detection | 6,837 | S2 · arXiv |
| 2022 | Self-Consistency Improves Chain of Thought Reasoning in Language Models | 5,926 | S2 · arXiv |
| 2022 | ReAct: Synergizing Reasoning and Acting in Language Models | 5,876 | S2 · arXiv |
| 2021 | Finetuned Language Models Are Zero-Shot Learners | 4,744 | S2 · arXiv |
| 2019 | Benchmarking Neural Network Robustness to Common Corruptions and Perturbations | 4,051 | S2 · arXiv |
| 2023 | SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis | 4,009 | S2 · arXiv |
| 2019 | The Curious Case of Neural Text Degeneration | 3,868 | S2 · arXiv |
| 2020 | Fourier Neural Operator for Parametric Partial Differential Equations | 3,511 | S2 · arXiv |
| 2020 | DeBERTa: Decoding-enhanced BERT with Disentangled Attention | 3,490 | S2 · arXiv |
| 2021 | BEiT: BERT Pre-Training of Image Transformers | 3,457 | S2 · arXiv |
| 2022 | Flow Matching for Generative Modeling | 3,240 | S2 · arXiv |
| 2022 | DreamFusion: Text-to-3D using 2D Diffusion | 3,227 | S2 · arXiv |
| 2021 | Efficiently Modeling Long Sequences with Structured State Spaces | 3,029 | S2 · arXiv |