ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Mengzhou Xia

Mengzhou Xia

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 14, 2026, 11:22 PM AMS

7

papers

1,558

total citations

papers (7)

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

LESS: Selecting Influential Data for Targeted Instruction Tuning

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

NEURIPS 2025arXiv

Language Models as Science Tutors

Trainable Transformer in Transformer