BWhat changed
Documented and released bilingual pretrained/chat research models with cascaded data deduplication and filtering, manually verified instruction data, and context/depth adaptation experiments in one model-family resource.
Scientific scope
Documented and released bilingual pretrained/chat research models with cascaded data deduplication and filtering, manually verified instruction data, and context/depth adaptation experiments in one model-family resource. Transformer/Llama architecture, visual instruction alignment and depth upscaling have predecessors. Initial base models were released in November 2023; the 2024 report also describes later extensions. Retrieval probes do not establish general long-context reasoning.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Transformer/Llama architecture, visual instruction alignment and depth upscaling have predecessors. Initial base models were released in November 2023; the 2024 report also describes later extensions. Retrieval probes do not establish general long-context reasoning.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- Yi: Open Foundation Models by 01.AI
- 01.AI: Yi bilingual foundation-model research resource — official research provenance
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction