John Kirchenbauer
9 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (12) π Renaissance Researcher (6)
πΊοΈ
Taxonomy Completionist
(24)
π£
Hot Topic Early Bird
Conferences
NIPS (4)
ICLR (2)
ICML (2)
ICCV (1)
Top co-authors
Research topics
Keywords
large language model
(3)
generative model
(2)
copyright protection
(2)
knowledge distillation
(1)
neural network optimization
(1)
discrete optimization
(1)
text generation
(1)
graph transformer
(1)
node classification
(1)
next-token prediction
(1)
training objective
(1)
privacy protection
(1)
hard prompt
(1)
memorization mitigation
(1)
privacy risk
(1)
prompt engineering
(1)
vision encoder
(1)
prompt tuning
(1)
position embedding
(1)
gradient-based optimization
(1)
Papers
Zero-Shot Vision Encoder Grafting via LLM Surrogates
ICCV 2025
NEFTune: Noisy Embeddings Improve Instruction Finetuning
ICLR 2024
On the Reliability of Watermarks for Large Language Models
ICLR 2024
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
NIPS 2024
Transformers Can Do Arithmetic with the Right Embeddings
NIPS 2024
GOAT: A Global Transformer on Large-scale Graphs
ICML 2023
Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images
NIPS 2023
A Watermark for Large Language Models
ICML 2023
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
NIPS 2023