Soheil Feizi
~Soheil_Feizi2
21
论文总数
10.5
年均投稿
平均评分
接收情况15/21
会议分布
ICLR
13
NeurIPS
6
COLM
2
发表论文 (21 篇)
20259 篇
4
How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings
ICLR 2025Poster
4
What do we learn from inverting CLIP models?
ICLR 2025withdrawn
4
Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text
NeurIPS 2025Poster
3
On Mechanistic Circuits for Extractive Question-Answering
COLM 2025Poster
4
Understanding and Enhancing Context-Augmented Language Models Through Mechanistic Circuits
ICLR 2025Rejected
4
Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models
ICLR 2025Poster
3
Localizing Knowledge in Diffusion Transformers
NeurIPS 2025Poster
4
Mitigating Compositional Issues in Text-to-Image Generative Models via Enhanced Text Embeddings
ICLR 2025withdrawn
4
Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models
ICLR 2025Poster
202412 篇
5
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
NeurIPS 2024Poster
4
Localizing and Editing Knowledge In Text-to-Image Generative Models
ICLR 2024Poster
5
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
ICLR 2024Poster
4
PRIME: Prioritizing Interpretability in Failure Mode Extraction
ICLR 2024Poster
4
Loki: Low-rank Keys for Efficient Sparse Attention
NeurIPS 2024Poster
3
Can AI-Generated Text be Reliably Detected?
ICLR 2024Rejected
4
Understanding Information Storage and Transfer in Multi-Modal Large Language Models
NeurIPS 2024Poster
4
Certifying LLM Safety against Adversarial Prompting
COLM 2024Poster
4
Certifying LLM Safety against Adversarial Prompting
ICLR 2024Rejected
4
LLM-Check: Investigating Detection of Hallucinations in Large Language Models
NeurIPS 2024Poster
4
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
ICLR 2024Poster
4
Benchmarking Diffusion Based Text-Guided Image Editing Methods
ICLR 2024Rejected