Yanhong Li
10 papers · 2023–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (14) π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (5) π Renaissance Researcher (5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(22)
β‘
Prolific Year
(5)
β
The Questioner
Conferences
EMNLP (3)
AAAI (2)
ACL (2)
NAACL (2)
ICLR (1)
Top co-authors
Keywords
layer-wise gradient
(2)
large language model
(2)
multimodal learning
(1)
knowledge unlearning
(1)
video transformer
(1)
time series prediction
(1)
time series forecasting
(1)
self-supervised pretraining
(1)
gradient-based method
(1)
singular value decomposition
(1)
nuclear norm
(1)
long short-term memory
(1)
parameter-efficient fine-tuning
(1)
training stability
(1)
data quality
(1)
episodic memory
(1)
retrieval augmentation
(1)
reasoning capability
(1)
gaussian mixture
(1)
sign language translation
(1)
Papers
How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
ACL 2026
What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
ACL 2025
Text or Pixels? Evaluating Efficiency and Understanding of LLMs with Visual Text Inputs
EMNLP 2025
Forget for Get: A Lightweight Two-phase Gradient Method for Knowledge Editing in Large Language Models
EMNLP 2025
Chunk-Distilled Language Modeling
ICLR 2025
Context-Efficient Retrieval with Factual Decomposition
NAACL 2025
Learning from Polar Representation: An Extreme-Adaptive Model for Long-Term Time Series Forecasting
AAAI 2024
When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models
NAACL 2024
TTICβs Submission to WMT-SLT 23
EMNLP 2023
An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks
AAAI 2023