Cyril Zhang
26 papers · 2017–2025 · 6 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 (62) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Triple Crown
π
Trend Setter
ποΈ
Keyword Collector
(137)
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Renaissance Researcher
(7)
Top co-authors
Research topics
Machine Learning
(23)
Optimization & Theory Β· Machine Learning
(19)
Deep Learning
(12)
Artificial Intelligence
(10)
Core AI
(10)
Mathematics & Optimization
(8)
Core Methods
(8)
Learning Types Β· Machine Learning
(8)
Optimization
(8)
Optimization & Theory Β· Deep Learning
(7)
Natural Language Processing
(4)
Architectures
(3)
Generation
(2)
Learning Types Β· Deep Learning
(2)
Computer Science
(1)
Keywords
linear dynamical system
(4)
regret bound
(4)
stochastic gradient descent
(3)
large language model
(3)
inductive bia
(3)
convex optimization
(2)
online learning
(2)
stochastic optimization
(2)
autoregressive filter
(2)
spectral filtering
(2)
sample complexity
(2)
time series prediction
(2)
computational complexity
(2)
decision making
(1)
reinforcement learning
(1)
non-convex optimization
(1)
contrastive learning
(1)
representation learning
(1)
neural network training
(1)
language modeling
(1)
Papers
On the Query Complexity of Verifier-Assisted Language Generation
ICML 2025
Self-Improvement in Language Models: The Sharpening Mechanism
ICLR 2025
ASL STEM Wiki: Dataset and Benchmark for Interpreting STEM Articles
EMNLP 2024
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
ICLR 2024
Can large language models explore in-context?
NeurIPS 2024
Exposing Attention Glitches with Flip-Flop Language Modeling
NeurIPS 2023
Learning Hidden Markov Models Using Conditional Samples
COLT 2023
Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck
NeurIPS 2023
Transformers Learn Shortcuts to Automata
ICLR 2023
Anti-Concentrated Confidence Bonuses For Scalable Exploration
ICLR 2022
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
NeurIPS 2022
Inductive Biases and Variable Creation in Self-Attention Mechanisms
ICML 2022
Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms
NeurIPS 2022
Sparsity in Partially Controllable Linear Systems
ICML 2022
Understanding Contrastive Learning Requires Incorporating Inductive Biases
ICML 2022
Acceleration via Fractal Learning Rate Schedules
ICML 2021
Calibration, Entropy Rates, and Memory in Language Models
ICML 2020
Extreme Tensoring for Low-Memory Preconditioning
ICLR 2020
No-Regret Prediction in Marginally Stable Systems
COLT 2020
Robust guarantees for learning an autoregressive filter
ALT 2020
Stochastic Optimization with Laggard Data Pipelines
NeurIPS 2020
Efficient Full-Matrix Adaptive Regularization
ICML 2019
Not-So-Random Features
ICLR 2018
Spectral Filtering for General Linear Dynamical Systems
NeurIPS 2018
Efficient Regret Minimization in Non-Convex Games
ICML 2017
Learning Linear Dynamical Systems via Spectral Filtering
NeurIPS 2017