Shujian Zhang
24 papers · 2020–2026 · 7 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (51) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Triple Crown
π€
Dynamic Duo
(13)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(121)
Top co-authors
Research topics
Machine Learning
(15)
Deep Learning
(13)
Artificial Intelligence
(9)
Learning Types Β· Machine Learning
(9)
Learning Types Β· Deep Learning
(7)
Natural Language Processing
(6)
Optimization & Theory
(6)
Application Areas
(5)
Core AI
(5)
Models
(5)
Reinforcement Learning
(4)
Generation
(4)
Methods
(4)
Architectures
(3)
Bayesian & Probabilistic
(3)
Keywords
uncertainty estimation
(3)
diffusion model
(3)
variational inference
(3)
preference optimization
(2)
adversarial robustness
(2)
offline reinforcement learning
(2)
stochastic attention
(2)
reinforcement learning from human feedback
(2)
ordinary differential equation
(2)
text generation
(2)
instruction following
(2)
model-based reinforcement learning
(2)
large language model
(2)
multi-label learning
(1)
bayesian inference
(1)
domain adaptation
(1)
bayesian learning
(1)
few-shot learning
(1)
image classification
(1)
fact verification
(1)
Papers
SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe
ACL 2026
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
ICLR 2025
Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models
ICLR 2025
Statistical Advantages of Perturbing Cosine Router in Mixture of Experts
ICLR 2025
T-REG: Preference Optimization with Token-Level Reward Regularization
ACL 2025
LanguageFlow: Advancing Diffusion Language Generation with Probabilistic Flows
NAACL 2024
Sliced Wasserstein with Random-Path Projecting Directions
ICML 2024
Switchable Decision: Dynamic Neural Generation Networks
ICML 2024
WPO: Enhancing RLHF with Weighted Preference Optimization
EMNLP 2024
Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems
ICLR 2023
FlowGrad: Controlling the Output of Generative ODEs With Gradients
CVPR 2023
POUF: Prompt-Oriented Unsupervised Fine-tuning for Large Pre-trained Models
ICML 2023
Preference-grounded Token-level Guidance for Language Model Fine-tuning
NeurIPS 2023
ALLSH: Active Learning Guided by Local Sensitivity and Hardness
NAACL 2022
A Unified Framework for Alternating Offline Model Training and Policy Learning
NeurIPS 2022
Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models
EMNLP 2022
Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning
ICML 2022
Alignment Attention by Matching Key and Query Distributions
NeurIPS 2021
A Prototype-Oriented Framework for Unsupervised Domain Adaptation
NeurIPS 2021
Bayesian Attention Belief Networks
ICML 2021
Contextual Dropout: An Efficient Sample-Dependent Dropout Module
ICLR 2021
Knowing More About Questions Can Help: Improving Calibration in Question Answering
ACL 2021
Learning with Different Amounts of Annotation: From Zero to Many Labels
EMNLP 2021
Bayesian Attention Modules
NeurIPS 2020