Yicheng Li
16 papers · 2018–2025 · 8 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 (26) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Triple Crown
π
Grand Slam
π
Keyword Champion
(2)
π
Renaissance Researcher
(5)
β‘
Prolific Year Β· Productive
π
Conference Pioneer
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(64)
Top co-authors
Research topics
Machine Learning
(14)
Optimization & Theory Β· Machine Learning
(11)
Core Methods
(8)
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI
(4)
Application Areas
(3)
Learning Types
(3)
Learning Paradigms
(2)
Optimization & Theory Β· Deep Learning
(2)
Computer Science
(1)
Knowledge & Reasoning
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Applications
(1)
Keywords
kernel ridge regression
(5)
minimax optimality
(3)
neural tangent kernel
(3)
reproducing kernel hilbert space
(3)
gradient descent
(3)
generalization error
(2)
statistical learning theory
(2)
small language model
(2)
eigenvalue decay
(2)
knowledge distillation
(2)
spectral algorithm
(2)
kernel regression
(2)
source condition
(2)
sample complexity
(1)
intrinsic dimension
(1)
chain-of-thought reasoning
(1)
gaussian process
(1)
power-law decay
(1)
instruction tuning
(1)
curse of dimensionality
(1)
Papers
Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension
ICML 2025
Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions
JMLR 2025
Improving Adaptivity via Over-Parameterization in Sequence Models
NeurIPS 2024
Mixed Distillation Helps Smaller Language Models Reason Better
EMNLP 2024
On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
JMLR 2024
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
NeurIPS 2024
On the Optimality of Misspecified Spectral Algorithms
JMLR 2024
On the Saturation Effects of Spectral Algorithms in Large Dimensions
NeurIPS 2024
Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search
EMNLP 2024
Teaching Small Language Models Reasoning through Counterfactual Distillation
EMNLP 2024
Towards Autonomous Tool Utilization in Language Models: A Unified, Efficient and Scalable Framework
COLING 2024
On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay
NeurIPS 2023
On the Optimality of Misspecified Kernel Ridge Regression
ICML 2023
On the Saturation Effect of Kernel Ridge Regression
ICLR 2023
An Integrated Enhancement Solution for 24-Hour Colorful Imaging
AAAI 2020
Instance-level Human Parsing via Part Grouping Network
ECCV 2018