AI Paper Atlas

Research map / Architectures and efficiency

RNNs and normalization: research map

3,071 papers on RNNs and normalization in Architectures and efficiency, from ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR (2016–2026), grouped into 6 clusters and 28 approaches. The busiest year so far is 2026.

What it is

A broad topic about the building blocks and behaviour of networks: recurrent networks and LSTMs, normalisation layers, how depth and width matter, scaling laws, brain-inspired learning rules and interpretability of internal representations.

Terms you will see on this page:

Batch normalization
normalising layer activations with batch statistics to stabilise training.
Scaling laws
regular relationships between model size, data, compute and performance.
RNN
recurrent neural network, which processes a sequence one step at a time with a hidden state.

Start reading with the most cited papers here:

Within Architectures and efficiency, its share shrank from 33.3% in 2023–24 to 26.4% in 2025–26 (651 → 934 papers at ICML, NeurIPS, ICLR, CVPR and AAAI, the venues with data for all four years).

2016: 84162017: 139172018: 201182019: 216192020: 220202021: 276212022: 247222023: 335232024: 381242025: 431252026: 54126

Explore RNNs and normalization in the interactive map

Working on something in this topic? Describe your idea in scime atlas to see which approach it falls under, the closest papers by meaning and how crowded the spot has become.

What changed recently

Approaches whose share of the topic moved most between 2023–24 and 2025–26 (ICML, NeurIPS, ICLR, CVPR and AAAI):

Papers from 2025–2026 that are already cited most:

Approaches and key papers

Scaling, compression and efficient training · 1,012 papers
Keywords: memory, scaling, cost

Approaches in this cluster:

Most cited and most cited since 2024:

Depth, width and representations · 966 papers
Keywords: layer, activation, functions

Approaches in this cluster:

Most cited and most cited since 2024:

Differentiable layers and structured models · 483 papers
Keywords: end, differentiable, translation

Approaches in this cluster:

Most cited and most cited since 2024:

Recurrent networks · 332 papers
Keywords: rnn, long, term

Approaches in this cluster:

Most cited and most cited since 2024:

Brain-inspired learning · 155 papers
Keywords: brain, biological, feedback

Approaches in this cluster:

Most cited and most cited since 2024:

Normalization layers · 123 papers
Keywords: normalization, bn, mini

Approaches in this cluster:

Most cited and most cited since 2024:

Related topics in Architectures and efficiency

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