Scholar

Keyu Wang

Google Scholar ID: cUtPGu4AAAAJ

McGill University, Mila, Harvard

AI safetyTrustworthy MLMechanistic Interpretability

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

15

H-index

1

i10-index

1

Publications

3

Co-authors

0

Contact

No contact links provided.

Publications

10 items

One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs

2026

Cited

0

TaCo: A Benchmark for Lossless and Lossy Codecs of Heterogeneous Tactile Data

2026

Cited

0

CORE: Code-based Inverse Self-Training Framework with Graph Expansion for Virtual Agents

arXiv.org · 2026

Cited

0

When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs

2025

Cited

0

Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning

2025

Cited

0

D3Grasp: Diverse and Deformable Dexterous Grasping for General Objects

2025

Cited

0

OmniVTLA: Vision-Tactile-Language-Action Model with Semantic-Aligned Tactile Sensing

2025

Cited

0

When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models

2025

Cited

0

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)