Chang Ma
12 papers · 2013–2026 · 9 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 ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (42) π Academic Marathon Β· Half π£ Hot Topic Early Bird π Conference Polyglot Β· Silver
π
Grand Slam
π
Conference Pioneer
β
The Questioner
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(71)
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(8)
Deep Learning
(7)
Learning Types Β· Machine Learning
(7)
Optimization & Theory
(6)
Natural Language Processing
(5)
Core AI
(5)
Models
(4)
Application Areas
(3)
Learning Paradigms
(3)
Learning Types Β· Deep Learning
(3)
Resources & Methods
(3)
Core Methods
(2)
Generation
(2)
Computer Vision
(1)
Keywords
large language model
(3)
language model
(2)
unsupervised learning
(2)
few-shot learning
(2)
transfer learning
(2)
unsupervised domain adaptation
(1)
attention mechanism
(1)
lottery ticket hypothesis
(1)
object detection
(1)
text classification
(1)
adversarial robustness
(1)
language modeling
(1)
natural language processing
(1)
low-resource learning
(1)
feature representation
(1)
model predictive control
(1)
exploration-exploitation tradeoff
(1)
mutual information
(1)
protein structure prediction
(1)
domain adaptation
(1)
Papers
How Can Synthetic Data Improve Multilingual Language Model Pretraining? A Data Quality Perspective
ACL 2026
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
ACL 2025
KS-Lottery: Finding Certified Lottery Tickets for Multilingual Transfer in Large Language Models
NAACL 2025
Non-myopic Generation of Language Models for Reasoning and Planning
ICLR 2025
π-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
ACL 2025
Achilles-Bench: A Challenging Benchmark for Low-Resource Evaluation
ACL 2024
AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
NeurIPS 2024
Retrieved Sequence Augmentation for Protein Representation Learning
EMNLP 2024
Certified Robustness Against Natural Language Attacks by Causal Intervention
ICML 2022
Domain Adaptation via Maximizing Surrogate Mutual Information
IJCAI 2022
Switch-GPT: An Effective Method for Constrained Text Generation under Few-Shot Settings (Student Abstract)
AAAI 2022
A Method of Perceptual-Based Shape Decomposition
ICCV 2013