ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Junyuan Hong

Junyuan Hong

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, 9:46 PM AMS

9

papers

311

total citations

papers (9)

Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

SEAL: Steerable Reasoning Calibration of Large Language Models for Free

Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork

NEURIPS 2022arXiv

Understanding Deep Gradient Leakage via Inversion Influence Functions

NEURIPS 2023arXiv

Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling

NEURIPS 2022arXiv

More is Less: The Pitfalls of Multi-Model Synthetic Preference Data in DPO Safety Alignment

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning