Skip to content
The methodOpen data

Follow your curiosity.

Different disciplines. Unexpected connections. One good place to start.

21 of 21 topics

Machine learning

368 papersIncluding Language Models are Few-Shot Learners

Language models

318 papersIncluding Sparks of Artificial General Intelligence: Early experiments with GPT-4

Algorithms

227 papersIncluding Copy-and-Patch Compilation: A fast compilation algorithm for high-level languages and bytecode

Psychology

222 papersIncluding Sparks of Artificial General Intelligence: Early experiments with GPT-4

Statistics & probability

186 papersIncluding Dissolving the Fermi Paradox

Other research

163 papersIncluding Geophysical constraints on the reliability of solar and wind power worldwide

Physics

146 papersIncluding The Ghost in the Quantum Turing Machine

Mathematics

105 papersIncluding On proof and progress in mathematics

Biology & medicine

92 papersIncluding NP-complete Problems and Physical Reality

Computer vision

88 papersIncluding Understanding deep learning requires rethinking generalization

Security & cryptography

81 papersIncluding Design Patterns for Securing LLM Agents against Prompt Injections

Economics

74 papersIncluding Statistical Consequences of Fat Tails: Real World Preasymptotics, Epistemology, and Applications

Programming languages

73 papersIncluding Copy-and-Patch Compilation: A fast compilation algorithm for high-level languages and bytecode

Distributed systems

63 papersIncluding A Critique of the CAP Theorem

Neuroscience

48 papersIncluding The Ghost in the Quantum Turing Machine

Databases

45 papersIncluding The Case for Learned Index Structures

Science & research

42 papersIncluding Dissolving the Fermi Paradox

Computer systems

36 papersIncluding Mesh: Compacting Memory Management for C/C++ Applications

Networks

25 papersIncluding Dynamic Routing Between Capsules

Robotics

25 papersIncluding Generative Agents: Interactive Simulacra of Human Behavior

Human–computer interaction

11 papersIncluding Why Johnny Still, Still Can't Encrypt: Evaluating the Usability of a Modern PGP Client

Topics come from transparent keyword rules, with up to three per paper. They are a starting point, not a formal research taxonomy. How topics are assigned