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.
- Online and replay-based (693)
- Domain and prompt-based (138)
- Class-incremental (450)
- Continual fine-tuning of LLMs (315)
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.
- Noisy labels (576)
- Zero-/few-shot and meta-learning (1,029)
- Test-time adaptation (437)
- OOD and anomaly detection (836)
- Recognition and long-tail (6,306)
- Semi-supervised learning (897)
- Self-supervised and contrastive (1,267)
- Domain adaptation and generalization (2,012)
- Knowledge distillation (783)
Probabilistic and scientific modeling · 9,481 papers
Bayesian and causal inference, uncertainty, dynamical systems, PDEs, and molecules.
- Dynamical systems (1,019)
- Uncertainty and Gaussian processes (1,421)
- Molecules and proteins (2,120)
- Variational and generative sampling (2,370)
- Treatment effects (468)
- Differential equations and PDEs (676)
- Causal discovery (973)
- Bayesian optimization (434)
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.
- Autoregressive and latent generation (2,100)
- GANs (780)
- Super-resolution (771)
- Editing and style transfer (1,430)
- Fast diffusion sampling (2,155)
- Image restoration (2,009)
- Text-to-image diffusion (1,916)
Graph learning · 5,185 papers
Graph neural networks, knowledge graphs and graph algorithms.
- Knowledge and temporal graphs (1,162)
- Graph algorithms and clustering (990)
- GNN architectures (1,634)
- Graph self-supervised learning (1,399)
Reinforcement learning · 6,414 papers
Policy learning, offline RL, imitation and learning from feedback.
- MDPs and planning (726)
- Visual and representation RL (2,264)
- Policy gradient and actor-critic (1,570)
- Imitation learning (450)
- RL from feedback (758)
- Offline RL (646)
Large language models · 9,881 papers
Reasoning, fine-tuning, retrieval, agents, alignment and safety of LLMs.
- Reasoning and chain of thought (1,574)
- Instruction and fine-tuning (888)
- Retrieval and knowledge (1,084)
- Agents, code and math (1,748)
- Alignment and preferences (672)
- AI and society (913)
- Language, safety and interpretability (3,002)
Detection and segmentation · 7,932 papers
Object detection, segmentation and tracking in images.
- Tracking (575)
- Open-set and few-shot detection (2,864)
- 3D detection and driving (761)
- CNN features (2,941)
- Weakly supervised detection and segmentation (791)
Optimization · 4,371 papers
Convergence, optimizers, distributed training and implicit bias.
- Distributed and compressed (388)
- Implicit bias and generalization (1,070)
- Nonconvex and smooth optimization (1,707)
- Optimizers (1,206)
Multi-agent systems and games · 3,786 papers
Multi-agent RL, equilibria, and LLM-based agents.
- LLM agents (1,294)
- Cooperative multi-agent RL (635)
- Games and equilibria (537)
- Human-AI and goal-conditioned (1,320)
Architectures and efficiency · 10,039 papers
Transformers, MoE, pruning, quantization and architecture search.
- Pruning and efficient tuning (1,335)
- Attention and transformers (2,598)
- Neural architecture search (548)
- Quantization (785)
- RNNs and normalization (3,071)
- Spiking networks (333)
- Mixture of experts (318)
- CNN design (1,051)
Vision-language and multimodal · 9,839 papers
Multimodal LLMs, CLIP-style models, VQA and embodied tasks.
- Human and embodied modeling (2,095)
- Visual question answering (711)
- Multimodal LLMs (3,132)
- Robot action and navigation (841)
- CLIP and zero-shot (1,294)
- Cross-modal learning (1,766)
3D vision · 11,404 papers
Reconstruction, NeRF, Gaussian splatting, pose and depth.
- Gaussian splatting (1,340)
- Human pose estimation (2,063)
- NeRF and radiance fields (733)
- 3D generation (2,448)
- Face and shape (2,246)
- Depth and stereo (2,574)
Video · 8,033 papers
Video understanding, action recognition and video generation.
- Video segmentation and tracking (2,850)
- Video-language understanding (1,681)
- Action recognition (1,325)
- Video generation (2,177)
Learning theory and algorithms · 11,342 papers
Sample complexity, kernels, fairness, clustering, optimal transport and algorithmic ML.
- Matrix and tensor methods (1,467)
- Sample complexity (1,553)
- Combinatorial and search optimization (1,576)
- Fairness (550)
- Submodular and game algorithms (1,064)
- Prediction and decision losses (2,400)
- Kernels and regression theory (1,272)
- Clustering (998)
- Optimal transport (462)
Adversarial robustness and security · 3,554 papers
Adversarial attacks and defenses, backdoors and poisoning.
- Certified and empirical robustness (1,356)
- Backdoor and poisoning (385)
- Black-box and transfer attacks (513)
- Attacks on text and graphs (1,300)
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.
