Urmish Thakker

Urmish Thakker has 3 papers in our library, in 2023–2025, most of them on Language models & pretraining, Reasoning; often with Changran Hu, Chen Wu, Fenglu Hong.

3 papers in our library · 2023–2025

The profile is the library's match of the name; two people with one name are not always told apart.

Affiliations

🏛️ArmAustin ·

United States2016Employment since 2016 · Senior Research Engineer, ML Research Lab

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

Of its works in our library, with the number of works on each.

The most cited first (OpenAlex and our library).

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models (2025 · 39 citations)
LLM systems such as agents and domain-specific reasoners often improve by changing their input context rather than their weights.
Efficiently Adapting Pretrained Language Models To New Languages (2023 · 21 citations)
Open LLMs trained mostly on English often do poorly on lower-resource languages, and building a model for such a language from scratch requires more data and compute than is usually available.
SubgoalXL: Subgoal-based Expert Learning for Theorem Proving (2024 · 10 citations)
SubgoalXL targets two obstacles for LLM-based formal theorem proving in Isabelle: proof data in this domain is scarce, and models struggle with long multi-step reasoning.

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

7 co-authors with a page, the most papers together first.

Papers of our library cite their works 2,601 times (of the 149,439 papers whose bibliographies we read); 623 citing papers with a page here →.

Updated 3 November 2026