Shang-Tse Chen
12 papers · 2014–2026 · 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (34) 🌍 Conference Polyglot · Silver
🏆
Grand Slam
🗃️
Keyword Collector
(73)
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(9)
Artificial Intelligence
(7)
Application Areas
(7)
Core AI
(7)
Deep Learning
(6)
Learning Types · Machine Learning
(6)
Optimization & Theory
(5)
Natural Language Processing
(3)
Learning Types · Deep Learning
(3)
Security & Privacy
(2)
Architectures
(2)
Privacy
(2)
Resources & Methods
(2)
Techniques
(2)
Computer Vision
(1)
Keywords
large language model
(2)
neural network
(2)
certified robustness
(2)
model merging
(2)
domain adaptation
(1)
model calibration
(1)
adversarial learning
(1)
knowledge representation
(1)
online learning
(1)
distributed learning
(1)
privacy preservation
(1)
automatic speech recognition
(1)
adversarial training
(1)
prompt engineering
(1)
label smoothing
(1)
model safety
(1)
llm defense
(1)
reinforcement learning from human feedback
(1)
formal verification
(1)
direct preference optimization
(1)
Papers
Adaptive Helpfulness–Harmlessness Alignment with Preference Vectors
EACL 2026
DRAG: Data Reconstruction Attack using Guided Diffusion
ICML 2025
Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss
ICML 2025
Jailbreaking with Universal Multi-Prompts
NAACL 2025
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
EMNLP 2025
Annealing Self-Distillation Rectification Improves Adversarial Training
ICLR 2024
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition
EMNLP 2024
Towards Large Certified Radius in Randomized Smoothing Using Quasiconcave Optimization
AAAI 2024
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
NeurIPS 2024
Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialogue
ACL 2023
Communication Efficient Distributed Agnostic Boosting
AISTATS 2016
Boosting with Online Binary Learners for the Multiclass Bandit Problem
ICML 2014