Dingli Yu
12 papers · 2020–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (20) π Cross-Pollinator (12) π Renaissance Researcher (5) π Interdisciplinary Bridge π§ Keyword Pioneer
π
Conference Polyglot
(3)
π
Academic Marathon
(5)
β‘
Prolific Year
(5)
β
The Questioner
(2)
π
Century Club
(12)
Conferences
NIPS (5)
ICLR (4)
ICML (3)
Top co-authors
Keywords
neural tangent kernel
(1)
stochastic gradient descent
(1)
benchmark evaluation
(1)
image generation
(1)
visual question answering
(1)
feature attribution
(1)
compositional generalization
(1)
model interpretability
(1)
safety alignment
(1)
distribution shift
(1)
mixing time
(1)
visual concept
(1)
learning rate
(1)
language model
(1)
vision language model
(1)
parameter-efficient fine-tuning
(1)
stochastic differential equation
(1)
weight decay
(1)
text-to-image model
(1)
model fine-tuning
(1)
Papers
Weak-to-Strong Generalization Even in Random Feature Networks, Provably
ICML 2025
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
ICML 2025
Can Models Learn Skill Composition from Examples?
NIPS 2024
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
NIPS 2024
SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models
ICLR 2024
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
NIPS 2024
Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks
ICLR 2024
A Kernel-Based View of Language Model Fine-Tuning
ICML 2023
Fast Mixing of Stochastic Gradient Descent with Normalization and Weight Decay
NIPS 2022
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound
NIPS 2022
Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee
ICLR 2020
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
ICLR 2020