Avi Schwarzschild
13 papers · 2020–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Conference Polyglot (3) π Academic Marathon (5) π§ Keyword Pioneer π Interdisciplinary Bridge π Renaissance Researcher (5)
πΊοΈ
Taxonomy Completionist
(15)
π£
Hot Topic Early Bird
π
Interdisciplinary Bridge
π
Triple Crown
π€
Dynamic Duo
(11)
β
The Questioner
(3)
β‘
Prolific Year
(6)
π₯
Unstoppable
(6)
π
Century Club
(13)
Conferences
ICLR (5)
NIPS (5)
ICML (3)
Top co-authors
Research topics
Keywords
large language model
(2)
adversarial robustness
(1)
data poisoning
(1)
logical reasoning
(1)
in-context learning
(1)
model evaluation
(1)
item response theory
(1)
neural network optimization
(1)
data privacy
(1)
backdoor attack
(1)
benchmark dataset
(1)
llm memorization
(1)
adversarial compression
(1)
data usage
(1)
progressive training
(1)
reasoning capability
(1)
position embedding
(1)
algorithm synthesis
(1)
numerical reasoning
(1)
recurrent network
(1)
Papers
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
ICML 2025
Universal Guidance for Diffusion Models
ICLR 2024
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
NIPS 2024
Rethinking LLM Memorization through the Lens of Adversarial Compression
NIPS 2024
Transformers Can Do Arithmetic with the Right Embeddings
NIPS 2024
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
ICML 2024
NEFTune: Noisy Embeddings Improve Instruction Finetuning
ICLR 2024
Transfer Learning with Deep Tabular Models
ICLR 2023
The Uncanny Similarity of Recurrence and Depth
ICLR 2022
End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking
NIPS 2022
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
ICML 2021
Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks
NIPS 2021
Truth or backpropaganda? An empirical investigation of deep learning theory
ICLR 2020