Yunzhen Feng
6 papers · 2024–2025 · 2 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐บ๏ธ
Taxonomy Completionist
(13)
โ
The Questioner
Top co-authors
Research topics
Keywords
model collapse
(3)
large language model
(2)
scaling law
(2)
synthetic data
(2)
dynamic programming
(1)
bilevel optimization
(1)
linear classifier
(1)
random projection
(1)
dataset distillation
(1)
backpropagation through time
(1)
linear transformer
(1)
gradient variance
(1)
gaussian mixture
(1)
synthesized data
(1)
model size
(1)
sparse transformer
(1)
arithmetic task
(1)
synthetic training sample
(1)
chain-of-thoughts
(1)
llama 2
(1)
Papers
Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
ICLR 2025
PILAF: Optimal Human Preference Sampling for Reward Modeling
ICML 2025
Strong Model Collapse
ICLR 2025
A Tale of Tails: Model Collapse as a Change of Scaling Laws
ICML 2024
Do Efficient Transformers Really Save Computation?
ICML 2024
Embarrassingly Simple Dataset Distillation
ICLR 2024