Avi Schwarzschild
~Avi_Schwarzschild1
15
论文总数
7.5
年均投稿
平均评分
接收情况9/15
会议分布
ICLR
8
NeurIPS
4
COLM
2
ICML
1
发表论文 (15 篇)
20256 篇
4
Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers
ICLR 2025Rejected
4
Extrapolation by Association: Length Generalization Transfer In Transformers
NeurIPS 2025Spotlight
4
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
ICML 2025Poster
5
Has My System Prompt Been Used? Large Language Model Prompt Membership Inference
ICLR 2025Rejected
-
Extracting Parameter Counts from Fine-Tuning APIs
ICLR 2025withdrawn
3
Antidistillation Sampling
NeurIPS 2025Poster
20249 篇
5
Rethinking LLM Memorization through the Lens of Adversarial Compression
NeurIPS 2024Poster
4
Algorithm Design for Learned Algorithms
ICLR 2024withdrawn
4
Forcing Diffuse Distributions out of Language Models
COLM 2024Poster
4
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
ICLR 2024Rejected
4
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
ICLR 2024Rejected
4
TOFU: A Task of Fictitious Unlearning for LLMs
COLM 2024Poster
4
Universal Guidance for Diffusion Models
ICLR 2024Poster
4
NEFTune: Noisy Embeddings Improve Instruction Finetuning
ICLR 2024Poster
3
Transformers Can Do Arithmetic with the Right Embeddings
NeurIPS 2024Poster