ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Kaiyue Wen

Kaiyue Wen

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 3:11 AM AMS

5

papers

162

total citations

papers (5)

RNNs are not Transformers (Yet): The Key Bottleneck on In-Context Retrieval

Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization

NEURIPS 2023arXiv

Overtrained Language Models Are Harder to Fine-Tune

Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars

NEURIPS 2023arXiv

Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?