anlak storytelling
All kinds
Document kinds
Loading document kinds...

Primary corpus lens for browsing and insights. Selection lives in the URL.

All formats
Orientation
Loading formats...

Landscape, portrait, square, or unknown document geometry.

Unlock
slides · global inventory

All filtered slides

Global slide inventory for the active corpus filters, with each row opening the slide detail view.

Search Insights JSON Unlock
Corpus coverage

319,975 slides

319,974 are described (100%), so the treemap can explain the corpus instead of just counting files.

Total slides
319,975
Described
319,974
Pending
1

Slide type composition

dynamicclickable
Slide type

Showing 319,974 described slides — 100.0% of 319,975 rendered pages

+Context & problem43,76713.7% · 6,592 docs+Data & charts72,62022.7% · 8,666 docs+Meta & navigation45,93614.4% · 9,739 docs+Recommend & act67,04121.0% · 9,324 docs+Cases & evidence31,2569.8% · 6,067 docs+Frameworks2,1230.7% · 1,232 docs+Appendix35,68211.2% · 6,614 docs+Other21,5496.7% · 5,566 docs

Tile area is proportional to slide count. Click a category to open its subtype map.

all document kinds · all orientations
18 30 60

Slide collection

54,061-54,090 of 319,975

filter-aware
16
The chart compares 'Frozen Pretrained Transformer' vs 'Full Transformer' vs 'Full LSTM' across 7 benchmarks.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
17
The slide highlights a shift in research focus back to non-transformer architectures like MLP-Mixer and convolutional models.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
18
The slide explains the technical mechanism of NeRF and mentions GIRAFFE as a generative variant.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
19
The chart shows CASP14 performance metrics comparing AlphaFold (G427) against other participants.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
20
Includes a technical diagram of the RoseTTAFold architecture and two bar charts comparing performance benchmarks.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
21
The slide uses a combination of a process diagram and two charts (bar and line) to validate the efficacy of AI-generated proteins.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
22
The slide uses a metaphor of 'grammaticality' (viability) vs 'semantic change' (antigenic variation) to explain viral evolution.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
23
The slide highlights a specific AI application in structural biology.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
24
The chart shows the exponential growth of cryo-EM structures in the Protein Data Bank (PDBe) over time, segmented by resolution.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
25
The slide describes a specific machine learning architecture (likely 'CPA' or Compositional Perturbation Autoencoder) for drug discovery.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
26
The slide contrasts a traditional 'Brute Force' approach with a 'MolPAL' (Molecular Pool-based Active Learning) approach.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
27
The slide compares various machine learning approaches for predicting Buchwald-Hartwig reaction yields using bar charts and line graphs.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
28
The slide uses a timeline-like visual to show the progression of DeepMind's algorithms (AlphaGo, AlphaGo Zero, AlphaZero, MuZero) and their capabilities.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
29
The slide compares DreamerV2 against IQN, Rainbow, C51, and DQN across four performance metrics (Gamer Median, Gamer Mean, Record Mean, Clipped Record Mean) over 200 million steps.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
30
The slide highlights the XLand environment and Population Based Training as key enablers for zero-shot generalization in RL.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
31
The slide uses three line charts with trend lines to show the impact of AI on human performance.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
32
The slide includes two charts: a scatter plot showing the decline in the number of runs over time and a density plot showing the distribution of reported median scores.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
33
Includes a comparison diagram of existing methods vs. ClipBERT and a performance table.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)1 hit
34
The slide highlights the trade-off between model capacity and language resource density in ASR.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)1 hit
35
Includes a process diagram of the GSLM architecture.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)1 hit
36
The slide explains the technical shift from GANs to diffusion models in AI research.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Aha Moment1 hit
37
Includes a technical diagram of the contrastive learning architecture and the loss function formula.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Aha Moment1 hit
38
The slide explains the CLIP architecture using a three-step process diagram.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Aha Moment1 hit
39
Includes visual examples of DALL-E outputs for specific text prompts.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Aha Moment1 hit
40
The slide details the VLiD architecture, showing training and inference workflows.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Aha Moment1 hit
41
The slide uses a visual example of a prompt-to-code workflow.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
42
Includes a visual example of a coding problem (H-Index) and a bar chart comparing model performance across difficulty levels.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
43
The slide contrasts formal theorem proving datasets with the new MATH dataset, highlighting the difficulty of the latter even for humans.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
44
Includes a qualitative example of model responses to tricky questions as model size increases.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit
45
The slide references a CMU survey of 60+ papers. It includes a table comparing four paradigms: Fully Supervised (Non-Neural), Fully Supervised (Neural), Pre-train/Fine-tune, and Pre-train/Prompt/Predict.2021 Air Street Capital The State of AI Report 2021 · Air Street Capital
Consulting deck VC research Beat · The Facts (What)Loop · Pattern Hunter1 hit