Institution profile

Tehran Institute for Advanced Studies

Academic institutionasia · ir
Official website
Research library24linked papers
Opportunities0open roles
Selected work

Representative Papers

GhazalBench: Usage-Grounded Evaluation of LLMs on Persian Ghazals

Feb 06, 2026

While current large language models demonstrate a capacity to comprehend the poetic essence of Persian ghazal poetry, they struggle to reproduce its culturally normative surface form in open-ended generation. This work proposes GhazalBench, a novel evaluation benchmark that, for the first time, incorporates the ability to generate culturally conformant textual forms as a core assessment dimension. The benchmark introduces two tasks: prose-to-poetry comprehension and cue-guided reconstruction of normative verses, complemented by a comparative experiment using English sonnets. Findings reveal that mainstream multilingual models generally excel at semantic understanding but underperform in open-generation of structurally and culturally compliant ghazals. Discriminative tasks notably narrow the performance gap, and the observed limitations are primarily attributed to insufficient coverage of relevant training data rather than inherent architectural constraints.

2 citationsRead paper

Distributed Dominating Set With Optimal Rounds and Message Size in Bounded Arboricity Graphs

Jun 13, 2026

This work addresses the distributed minimum dominating set problem on graphs with bounded arboricity. For graphs of arboricity α, the paper proposes a deterministic distributed algorithm that achieves an O(α log Δ / log log Δ)-approximation, where Δ is the maximum node degree. Notably, the algorithm requires only the knowledge of Δ as prior information—without needing to know α—and operates with messages of just one bit per round over O(log Δ / log log Δ) communication rounds. This approach is the first to simultaneously attain optimal round complexity and unit message size, significantly improving upon prior methods that either required Ω(log n) rounds or larger message sizes, thereby simplifying and enhancing the best-known results in this setting.

0 citationsRead paper
Recent publications

Latest Papers

Distributed Dominating Set With Optimal Rounds and Message Size in Bounded Arboricity Graphs

Jun 13, 2026

This work addresses the distributed minimum dominating set problem on graphs with bounded arboricity. For graphs of arboricity α, the paper proposes a deterministic distributed algorithm that achieves an O(α log Δ / log log Δ)-approximation, where Δ is the maximum node degree. Notably, the algorithm requires only the knowledge of Δ as prior information—without needing to know α—and operates with messages of just one bit per round over O(log Δ / log log Δ) communication rounds. This approach is the first to simultaneously attain optimal round complexity and unit message size, significantly improving upon prior methods that either required Ω(log n) rounds or larger message sizes, thereby simplifying and enhancing the best-known results in this setting.

0 citationsRead paper

scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement

May 18, 2026

This work addresses a critical challenge in single-cell RNA sequencing data integration: the tendency of conventional whole-transcriptome harmonization approaches to over-correct, thereby compromising the preservation of genuine biological signals while removing batch effects. To overcome this limitation, the authors propose an adaptive integration framework that explicitly decouples genes at the input layer into domain-invariant Anchors and domain-sensitive Variants. The method employs an asymmetric dual-stream sparse diffusion encoder, enhanced with a stop-gradient graph cache, multi-scale structural representation learning, and a bounded residual gating mechanism to effectively prevent shortcut learning. Through an asymmetric Align-Refine-Fuse protocol, the approach consistently outperforms state-of-the-art methods across multiple benchmarks, achieving robust batch correction while faithfully retaining subtle biological clustering structures.

0 citationsRead paper