Xiangru Tang

A strong open-model and data-centric page because his work sits close to the infrastructure that made OLMo and Dolma useful to the broader research community rather than just another benchmark-driven model release.

A useful page because it turns an otherwise stray RWKV byline into a visible builder profile: his public work is less about academic publishing and more about making efficient models, AI agents, and production RWKV systems usable in practice.

Worth keeping because he is one of the original RWKV coauthors who clearly did not stop there: his public work moves into production AI for crisis intelligence, security-aware infrastructure tooling, and later open-LLM experimentation.

A useful long-tail page because he is present on both the original RWKV paper and Eagle/Finch, then shows up again on multilingual embedding evaluation work, which makes him more than a one-paper launch contributor.

A useful page because his public trail moved well beyond the original RWKV paper into reasoning, in-context learning, and decoder-only model design, which makes him one of the stronger later-follow-up names from that original author list.

Worth tracking if you care about alternatives to the standard transformer playbook, especially the line of work trying to keep strong language-model performance while making inference and memory use much cheaper.