ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Kaixuan Huang

Kaixuan Huang

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, 1:13 AM AMS

9

papers

709

total citations

papers (9)

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

SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal

Fast Federated Learning in the Presence of Arbitrary Device Unavailability

NEURIPS 2021arXiv

Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective

NEURIPS 2020arXiv

Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement

NEURIPS 2023arXiv

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models

Optimal Gradient-based Algorithms for Non-concave Bandit Optimization

NEURIPS 2021arXiv

Going Beyond Linear RL: Sample Efficient Neural Function Approximation

NEURIPS 2021arXiv