Models, methods, and the machinery of intelligence.
arXiv
Verdict: NotableArtificial general intelligence (AGI) requires a method that can understand, generate, reason, and act across diverse domains and modalities.
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts.
General-purpose robot policies must work across robots, tasks, and environments, yet the variation that makes physical trials informative also makes them difficult to reproduce.
Harness evolution from a common base exhibits Locality, Complementarity, and Nonstationarity: variants repair different failures, and their utility changes as the policy learns.
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows.
Speculative decoding accelerates memory-bound LLM decoding with a lightweight drafter, and parallel drafters extend this speedup by drafting a whole block in one forward pass.
Autoregressive approaches with large language models, such as long chain-of-thought reasoning, have become the default for new AI applications because they reach higher accuracy on a wide ....
Traditional image cropping assumes the photograph already contains the composition worth keeping, and asks only where to crop.
GUI web agents require realistic and interactive environments that remain stable during both evaluation and training.