Models, methods, and the machinery of intelligence.
From the archiveYou are reading the September 30, 2026 edition. Read the latest
arXiv
Verdict: NotableReinforcement learning can turn one language model into several specialists, each excellent at a single skill such as mathematics, coding or following instructions, but users need one model with all of these skills.
Symbolic models make melody, harmony, rhythm, and form explicit but typically stop before a finished recording; audio models produce complete songs while leaving composition implicit.
Vision-language-action (VLA) and world-action (WAM) models map observations and instructions directly to robot actions.
Looped transformers have demonstrated promising parameter efficiency by reusing layers for latent computation.
Answering questions about long videos often requires connecting events involving the same objects across hours or days.
Video diffusion models are increasingly developed into specialized models for diverse downstream tasks, and this development often includes a distillation stage, for example to accelerate ....
General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action.
As large language models advance, AI agents are moving beyond isolated, domain-specific tasks toward long-horizon, cross-domain workflows.
Scaling test-time computation is a powerful way to improve language-model reasoning, and is particularly appealing for small reasoning models (sRMs) that are cheap to serve.