Shuang Ma
16 papers · 2017–2025 · 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (37) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π₯ Mega-Team Β· Squad
π§¬
Topic Evolution
ποΈ
Keyword Collector
(83)
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Conference Pioneer
π
Renaissance Researcher
(5)
π
Century Club Β· Bronze
Top co-authors
Research topics
Machine Learning
(11)
Learning Types Β· Machine Learning
(10)
Artificial Intelligence
(8)
Core AI
(8)
Deep Learning
(6)
Learning Paradigms
(4)
Models
(4)
Core Methods
(3)
Computer Vision
(2)
Reinforcement Learning
(2)
Learning Types Β· Deep Learning
(2)
Methods
(2)
Techniques
(2)
Natural Language Processing
(1)
Robotics
(1)
Keywords
large language model
(3)
contrastive learning
(3)
imitation learning
(2)
generative adversarial network
(2)
style transfer
(2)
representation learning
(2)
self-supervised learning
(2)
continuous control
(2)
tool use
(2)
adversarial learning
(2)
zero-shot learning
(1)
domain adaptation
(1)
causal discovery
(1)
reinforcement learning
(1)
speech synthesis
(1)
multi-task learning
(1)
attention mechanism
(1)
benchmark evaluation
(1)
video classification
(1)
sequential decision making
(1)
Papers
MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains
NAACL 2025
Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo
ICLR 2025
ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities
NAACL 2025
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
ICML 2024
TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning
NeurIPS 2023
Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training
ICCV 2023
SMART: Self-supervised Multi-task pretrAining with contRol Transformers
ICLR 2023
CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning
CLeaR 2022
Active Contrastive Learning of Audio-Visual Video Representations
ICLR 2021
Contrastive Learning of Global and Local Video Representations
NeurIPS 2021
Multi-Reference Neural TTS Stylization with Adversarial Cycle Consistency
Interspeech 2020
Characterizing Bias in Classifiers using Generative Models
NeurIPS 2019
Neural TTS Stylization with Adversarial and Collaborative Games
ICLR 2019
Unpaired Image-to-Speech Synthesis With Multimodal Information Bottleneck
ICCV 2019
DA-GAN: Instance-Level Image Translation by Deep Attention Generative Adversarial Networks
CVPR 2018
A-Lamp: Adaptive Layout-Aware Multi-Patch Deep Convolutional Neural Network for Photo Aesthetic Assessment
CVPR 2017