Yangsibo Huang
24 papers · 2020–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🌍 Conference Polyglot (6) 🏃 Academic Marathon (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird
🐝
Cross-Pollinator
(12)
🌈
Renaissance Researcher
(5)
🌉
Interdisciplinary Bridge
👑
Triple Crown
🤝
Dynamic Duo
(11)
👥
Mega-Team
(23)
⚡
Prolific Year
(11)
🔥
Unstoppable
(6)
💎
Century Club
(24)
Conferences
ICLR (9)
ICML (6)
NIPS (5)
EMNLP (2)
AACL (1)
IJCNLP (1)
Top co-authors
Keywords
federated learning
(4)
large language model
(3)
logical reasoning
(2)
differential privacy
(2)
gradient attack
(2)
data privacy
(2)
visual concept
(1)
language understanding
(1)
image generation
(1)
privacy preservation
(1)
distributed learning
(1)
benchmark evaluation
(1)
text reconstruction
(1)
gradient compression
(1)
language model
(1)
model training
(1)
vision language model
(1)
text-to-image model
(1)
model fine-tuning
(1)
visual question answering
(1)
Papers
On Memorization of Large Language Models in Logical Reasoning
IJCNLP 2025
On Memorization of Large Language Models in Logical Reasoning
AACL 2025
On Evaluating the Durability of Safeguards for Open-Weight LLMs
ICLR 2025
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
ICLR 2025
Fantastic Copyrighted Beasts and How (Not) to Generate Them
ICLR 2025
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
ICLR 2025
GMValuator: Similarity-based Data Valuation for Generative Models
ICLR 2025
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
ICLR 2025
MATH-Perturb: Benchmarking LLMs’ Math Reasoning Abilities against Hard Perturbations
ICML 2025
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
ICML 2025
Scaling Laws for Differentially Private Language Models
ICML 2025
LabelDP-Pro: Learning with Label Differential Privacy via Projections
ICLR 2024
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
NIPS 2024
Evaluating Copyright Takedown Methods for Language Models
NIPS 2024
Position: A Safe Harbor for AI Evaluation and Red Teaming
ICML 2024
Detecting Pretraining Data from Large Language Models
ICLR 2024
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
ICLR 2024
Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
ICML 2024
Sparsity-Preserving Differentially Private Training of Large Embedding Models
NIPS 2023
Privacy Implications of Retrieval-Based Language Models
EMNLP 2023
Recovering Private Text in Federated Learning of Language Models
NIPS 2022
Evaluating Gradient Inversion Attacks and Defenses in Federated Learning
NIPS 2021
InstaHide: Instance-hiding Schemes for Private Distributed Learning
ICML 2020
TextHide: Tackling Data Privacy in Language Understanding Tasks
EMNLP 2020