Jun Bai
11 papers · 2021–2026 · 6 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (32) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
ποΈ
Keyword Collector
(59)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
π
Trend Setter
Top co-authors
Research topics
Machine Learning
(10)
Natural Language Processing
(8)
Artificial Intelligence
(7)
Core AI
(6)
Learning Types
(6)
Resources & Methods
(5)
Optimization & Theory
(4)
Deep Learning
(3)
Applications
(3)
Application Areas
(2)
Architectures
(2)
Core Methods
(2)
Generation
(2)
Learning Paradigms
(2)
Bayesian & Probabilistic
(1)
Keywords
large language model
(3)
transferability estimation
(2)
model selection
(2)
variational autoencoder
(2)
variational inference
(2)
representation learning
(2)
pre-trained language model
(2)
privacy leakage
(2)
mathematical reasoning
(1)
text generation
(1)
reinforcement learning
(1)
information retrieval
(1)
query reformulation
(1)
semantic representation
(1)
question answering
(1)
latent representation
(1)
in-context learning
(1)
generative model
(1)
hilbert-schmidt independence criterion
(1)
preference alignment
(1)
Papers
Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models
AAAI 2026
CogAtom: From Cognitive Atoms to Olympiad-level Mathematical Reasoning in Large Language Models
EMNLP 2025
Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment
COLING 2025
Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks
EMNLP 2025
Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching
ACL 2025
Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs
EMNLP 2025
FedInverse: Evaluating Privacy Leakage in Federated Learning
ICLR 2024
Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking
EMNLP 2024
How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey
EMNLP 2023
Improving Variational Autoencoders with Density Gap-based Regularization
NeurIPS 2022
Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval
EMNLP 2021