Junyuan Hong
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11The Last Human-Written Paper: Agent-Native Research Artifacts
arXiv 2026
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models
arXiv 2025
LLMs Can Get "Brain Rot"!
arXiv 2025
SEAL: Steerable Reasoning Calibration of Large Language Models for Free
arXiv 2025
LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
arXiv 2025
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
arXiv 2024
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression
arXiv 2024
Understanding Deep Gradient Leakage via Inversion Influence Functions
understanding-deep-gradient-leakage-via
DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
arXiv 2023
Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
arXiv 2023
Safe and Robust Watermark Injection with a Single OoD Image
arXiv 2023
Affiliations
Frequent co-authors
10from 11 papers