Yingcong Li
10 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (31) π£ Hot Topic Early Bird π Cross-Pollinator (13) π Renaissance Researcher (5) π Interdisciplinary Bridge
π§
Keyword Pioneer
π
Conference Polyglot
(4)
π€
Dynamic Duo
(10)
β‘
Prolific Year
(5)
π
Century Club
(10)
Conferences
AAAI (3)
NIPS (3)
AISTATS (2)
ICML (2)
Top co-authors
Keywords
in-context learning
(3)
gradient descent
(3)
attention mechanism
(2)
neural network
(2)
generalization bound
(2)
sparse learning
(1)
token selection
(1)
sample complexity
(1)
hierarchical clustering
(1)
feature correlation
(1)
multitask learning
(1)
stability analysis
(1)
model pruning
(1)
support vector machine
(1)
sparse model
(1)
regret bound
(1)
contextual bandit
(1)
algorithm learning
(1)
language model
(1)
implicit bia
(1)
Papers
Provable Benefits of Task-Specific Prompts for In-context Learning
AISTATS 2025
From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
ICML 2024
Mechanics of Next Token Prediction with Self-Attention
AISTATS 2024
Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond
NIPS 2024
Transformers as Algorithms: Generalization and Stability in In-context Learning
ICML 2023
Stochastic Contextual Bandits with Long Horizon Rewards
AAAI 2023
Max-Margin Token Selection in Attention Mechanism
NIPS 2023
Provable Pathways: Learning Multiple Tasks over Multiple Paths
AAAI 2023
Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning
NIPS 2023
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
AAAI 2021