Yicheng Li
16 papers · 2018–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Conference Polyglot (8) π Academic Marathon (7) π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (12)
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(7)
πΊοΈ
Taxonomy Completionist
(28)
π
Keyword Champion
(2)
π
Grand Slam
π
Triple Crown
ποΈ
Keyword Collector
(56)
π
Century Club
(16)
π
Trend Setter
β‘
Prolific Year
(9)
π
Conference Pioneer
Conferences
NIPS (4)
EMNLP (3)
JMLR (3)
ICML (2)
AAAI (1)
COLING (1)
ECCV (1)
ICLR (1)
Top co-authors
Research topics
Keywords
kernel ridge regression
(4)
neural tangent kernel
(3)
reproducing kernel hilbert space
(3)
gradient descent
(3)
minimax optimality
(3)
kernel regression
(2)
generalization error
(2)
knowledge distillation
(2)
eigenvalue decay
(2)
source condition
(2)
small language model
(2)
spectral algorithm
(2)
excess risk
(1)
chain-of-thought reasoning
(1)
statistical learning theory
(1)
gaussian process
(1)
regularization parameter
(1)
instruction tuning
(1)
power-law decay
(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
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
NIPS 2024
Improving Adaptivity via Over-Parameterization in Sequence Models
NIPS 2024
Towards Autonomous Tool Utilization in Language Models: A Unified, Efficient and Scalable Framework
COLING 2024
Teaching Small Language Models Reasoning through Counterfactual Distillation
EMNLP 2024
Mixed Distillation Helps Smaller Language Models Reason Better
EMNLP 2024
On the Saturation Effects of Spectral Algorithms in Large Dimensions
NIPS 2024
Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search
EMNLP 2024
On the Eigenvalue Decay Rates of a Class of Neural-Network Related Kernel Functions Defined on General Domains
JMLR 2024
On the Optimality of Misspecified Spectral Algorithms
JMLR 2024
On the Optimality of Misspecified Kernel Ridge Regression
ICML 2023
On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay
NIPS 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