Preetum Nakkiran
21 papers · 2019–2025 · 5 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 9 separate collaboration groups - the largest holds only 38% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which Preetum Nakkiran?
3 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Joshua M. Susskind, Etai Littwin, Omid Saremi
8 papers
· 2024–2025
· ICLR, ICML, AISTATS
Hide ▲
A Formal Framework for Understanding Length Generalization in Transformers
ICLR 2025
Composition and Control with Distilled Energy Diffusion Models and Sequential Monte Carlo
AISTATS 2025
Mechanisms of Projective Composition of Diffusion Models
ICML 2025
Normalizing Flows are Capable Generative Models
ICML 2025
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
NeurIPS 2024
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
ICLR 2024
Vanishing Gradients in Reinforcement Finetuning of Language Models
ICLR 2024
What Algorithms can Transformers Learn? A Study in Length Generalization
ICLR 2024
6 papers whose co-authors appear nowhere else under this name
When is Multicalibration Post-Processing Necessary?
NeurIPS 2024
Benign, Tempered, or Catastrophic: Toward a Refined Taxonomy of Overfitting
NeurIPS 2022
What You See is What You Get: Principled Deep Learning via Distributional Generalization
NeurIPS 2022
Optimal Regularization can Mitigate Double Descent
ICLR 2021
The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers
ICLR 2021
Computational Limitations in Robust Classification and Win-Win Results
COLT 2019