Noam Wies
7 papers · 2020–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15) ❓ The Questioner
🔥
Unstoppable
(5)
Conferences
ICLR (3)
ICML (2)
NIPS (2)
Top co-authors
Keywords
transformer architecture
(1)
attention mechanism
(1)
in-context learning
(1)
sample complexity
(1)
pac learning
(1)
task identification
(1)
network depth
(1)
network width
(1)
finite sample complexity
(1)
large language model
(1)
pretraining phase
(1)
vocabulary size
(1)
depth efficiency
(1)
pretraining distribution
(1)
depth-to-width ratio
(1)
embedding rank bottleneck
(1)
latent task identification
(1)
Papers
Fundamental Limitations of Alignment in Large Language Models
ICML 2024
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
ICLR 2024
Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks
ICLR 2023
The Learnability of In-Context Learning
NIPS 2023
The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design
ICLR 2022
Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
ICML 2021
Limits to Depth Efficiencies of Self-Attention
NIPS 2020