Avi Schwarzschild
13 papers · 2020–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (25) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π€
Dynamic Duo
(11)
π
Triple Crown
π§
Keyword Pioneer
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
(3)
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(64)
Venues
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(8)
Core AI
(7)
Deep Learning
(6)
Optimization & Theory
(5)
Architectures
(4)
Learning Types Β· Machine Learning
(4)
Natural Language Processing
(3)
Application Areas
(2)
Core Methods
(2)
Learning Types Β· Deep Learning
(2)
Models
(2)
Resources & Methods
(2)
Computer Vision
(1)
Security & Privacy
(1)
Keywords
large language model
(3)
recurrent network
(2)
adversarial robustness
(1)
data poisoning
(1)
transfer learning
(1)
logical reasoning
(1)
in-context learning
(1)
neural network optimization
(1)
batch normalization
(1)
model evaluation
(1)
text generation
(1)
item response theory
(1)
transformer
(1)
conditional generation
(1)
multimodal guidance
(1)
data augmentation
(1)
loss landscape
(1)
instruction tuning
(1)
reinforcement learning from human feedback
(1)
image generation
(1)
Papers
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
ICML 2025
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
NeurIPS 2024
NEFTune: Noisy Embeddings Improve Instruction Finetuning
ICLR 2024
Rethinking LLM Memorization through the Lens of Adversarial Compression
NeurIPS 2024
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
ICML 2024
Transformers Can Do Arithmetic with the Right Embeddings
NeurIPS 2024
Universal Guidance for Diffusion Models
ICLR 2024
Transfer Learning with Deep Tabular Models
ICLR 2023
End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking
NeurIPS 2022
The Uncanny Similarity of Recurrence and Depth
ICLR 2022
Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks
NeurIPS 2021
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
ICML 2021
Truth or backpropaganda? An empirical investigation of deep learning theory
ICLR 2020