AI Paper Atlas

AI research map: machine learning and computer vision in 20 areas, 111 topics, 137,217 papers

A map of every paper at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR from 2016 to 2026, grouped by meaning into research areas, topics and approaches. Each page shows yearly counts, how the topic's share changed, its approaches and its most cited papers.

Place your research idea on the map

Continual learning · 1,596 papers

Learning new tasks or classes over time without forgetting old ones.

Label-efficient and robust learning · 14,143 papers

Learning with few, noisy or unlabeled data and under distribution shift: semi- and self-supervised learning, domain adaptation, OOD detection, noisy labels.

Probabilistic and scientific modeling · 9,481 papers

Bayesian and causal inference, uncertainty, dynamical systems, PDEs, and molecules.

Bandits and online learning · 2,385 papers

Regret-minimizing decisions under uncertainty, from multi-armed bandits to RL theory.

Image generation · 11,161 papers

Diffusion, GANs and autoregressive models for images, plus editing, super-resolution and restoration.

Graph learning · 5,185 papers

Graph neural networks, knowledge graphs and graph algorithms.

Reinforcement learning · 6,414 papers

Policy learning, offline RL, imitation and learning from feedback.

Large language models · 9,881 papers

Reasoning, fine-tuning, retrieval, agents, alignment and safety of LLMs.

Detection and segmentation · 7,932 papers

Object detection, segmentation and tracking in images.

Optimization · 4,371 papers

Convergence, optimizers, distributed training and implicit bias.

Multi-agent systems and games · 3,786 papers

Multi-agent RL, equilibria, and LLM-based agents.

Architectures and efficiency · 10,039 papers

Transformers, MoE, pruning, quantization and architecture search.

Vision-language and multimodal · 9,839 papers

Multimodal LLMs, CLIP-style models, VQA and embodied tasks.

3D vision · 11,404 papers

Reconstruction, NeRF, Gaussian splatting, pose and depth.

Video · 8,033 papers

Video understanding, action recognition and video generation.

Learning theory and algorithms · 11,342 papers

Sample complexity, kernels, fairness, clustering, optimal transport and algorithmic ML.

Adversarial robustness and security · 3,554 papers

Adversarial attacks and defenses, backdoors and poisoning.

Federated learning and privacy · 2,557 papers

Federated training, differential privacy and privacy attacks.

Point clouds · 2,494 papers

Learning on 3D point clouds: classification, registration, segmentation, completion.

Time series · 1,620 papers

Forecasting, anomaly detection and foundation models for time series.

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy