Yangsibo Huang
~Yangsibo_Huang2
19
论文总数
9.5
年均投稿
平均评分
接收情况16/19
会议分布
ICLR
11
ICML
4
NeurIPS
2
COLM
2
发表论文 (19 篇)
202515 篇
3
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
ICML 2025Oral
3
Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
ICLR 2025Poster
4
Quantifying Cross-Modality Memorization in Vision-Language Models
NeurIPS 2025Poster
3
Scaling Laws for Differentially Private Language Models
ICML 2025Poster
4
Fantastic Copyrighted Beasts and How (Not) to Generate Them
ICLR 2025Poster
4
On Memorization of Large Language Models in Logical Reasoning
ICLR 2025Rejected
5
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
ICLR 2025Poster
4
Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
COLM 2025Poster
3
Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models
ICLR 2025Rejected
4
On Evaluating the Durability of Safeguards for Open-Weight LLMs
ICLR 2025Poster
5
Scaling Embedding Layers in Language Models
NeurIPS 2025Poster
4
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal
ICLR 2025Poster
4
GMValuator: Similarity-based Data Valuation for Generative Models
ICLR 2025Poster
4
Scaling Embedding Layers in Language Models
ICML 2025Rejected
4
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
ICML 2025Poster
20244 篇
4
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
ICLR 2024Spotlight
4
LabelDP-Pro: Learning with Label Differential Privacy via Projections
ICLR 2024Poster
3
Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning
COLM 2024Poster
4
Detecting Pretraining Data from Large Language Models
ICLR 2024Poster