Chi-Heng Lin
17 papers · 2020–2026 · 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 ↓+4 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (45) 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
🗃️
Keyword Collector
(84)
Top co-authors
Research topics
Machine Learning
(17)
Deep Learning
(11)
Optimization & Theory · Machine Learning
(11)
Application Areas
(7)
Artificial Intelligence
(5)
Core AI
(5)
Learning Types · Machine Learning
(5)
Optimization & Theory · Deep Learning
(5)
Mathematics & Optimization
(4)
Core Methods
(4)
Learning Types · Deep Learning
(4)
Optimization
(4)
Natural Language Processing
(3)
Architectures
(3)
Generation
(2)
Keywords
large language model
(4)
model compression
(3)
self-supervised learning
(3)
neural network optimization
(3)
non-convex optimization
(2)
gradient descent
(2)
optimal transport
(2)
language model
(2)
distribution alignment
(2)
data augmentation
(2)
model architecture
(1)
ridge regression
(1)
language modeling
(1)
stochastic gradient descent
(1)
transformer architecture
(1)
spectral regularization
(1)
contrastive learning
(1)
message passing
(1)
global optimization
(1)
synthetic data generation
(1)
Papers
VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs
ACL 2026
FlexiGPT: Pruning and Extending Large Language Models with Low-Rank Weight Sharing
NAACL 2025
MoDeGPT: Modular Decomposition for Large Language Model Compression
ICLR 2025
MossNet: Mixture of State-Space Experts is a Multi-Head Attention
IJCNLP 2025
Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
ICML 2024
DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
NeurIPS 2024
DynaMo: Accelerating Language Model Inference with Dynamic Multi-Token Sampling
NAACL 2024
SLiM: Speculative Decoding with Hypothesis Reduction
NAACL 2024
The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective
JMLR 2024
Your contrastive learning problem is secretly a distribution alignment problem
NeurIPS 2024
Half-Hop: A graph upsampling approach for slowing down message passing
ICML 2023
Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out
ICML 2022
A Modular Analysis of Provable Acceleration via Polyak’s Momentum: Training a Wide ReLU Network and a Deep Linear Network
ICML 2021
Bayesian optimization for modular black-box systems with switching costs
UAI 2021
Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity
NeurIPS 2021
Making transport more robust and interpretable by moving data through a small number of anchor points
ICML 2021
Escaping Saddle Points Faster with Stochastic Momentum
ICLR 2020