Research index

Papers

Curated and annotated. Each entry states, in plain language, what the result is and why it moves general-purpose capability — not just benchmark numbers.

sort

tags

P-0004 2026-08-22 Language Models are Few-Shot Learners T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, et al. · NeurIPS Demonstrates that a 175B-parameter autoregressive language model performs a wide range of unseen tasks from instructions and a handful of examples in its context, with no gradient updates. This is the first large-scale evidence that generality can emerge from scale alone rather than from task-specific architecture. 2026-08-22 · P-0004 scaling+2
P-0003 2026-08-21 World Models D. Ha, J. Schmidhuber · NeurIPS Trains a compact generative model of an environment and then trains a controller almost entirely inside it. The demonstration that a policy learned in a learned simulation can transfer back to the real environment is the load-bearing result. 2026-08-21 · P-0003 world-models+2
P-0002 2026-08-21 Overcoming Catastrophic Forgetting in Neural Networks J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A. A. Rusu, et al. · PNAS Proposes elastic weight consolidation, which slows learning on weights that a Fisher information estimate marks as important to previously learned tasks. It is the clearest early statement that catastrophic forgetting is a constraint problem, not a capacity problem — and the framing survives even where the method does not. 2026-08-21 · P-0002 1memory+1
P-0001 2026-08-20 Attention Is All You Need A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, I. Polosukhin · NeurIPS Introduces the Transformer, a sequence model built entirely from attention and feed-forward layers with no recurrence or convolution. Its significance for general-purpose systems is less the translation result than the property that made it the substrate for everything since: it parallelises over sequence length, so capability became a question of scale rather than of architecture search. 2026-08-20 · P-0001 architecture+2