Junfeng Fang
29 papers · 2023–2026 · 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 (37) π Conference Polyglot Β· Silver π Keyword Champion (2) π€ Dynamic Duo (11)
π
Grand Slam
ποΈ
Keyword Collector
(134)
β
The Questioner
β‘
Prolific Year Β· Absurd
π
Century Club Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(23)
Core AI
(23)
Deep Learning
(15)
Machine Learning
(11)
Natural Language Processing
(9)
Architectures
(9)
Resources & Methods
(9)
Models
(6)
Learning Types Β· Deep Learning
(5)
Core Methods
(4)
Learning Types Β· Machine Learning
(4)
Optimization & Theory
(4)
Application Areas
(2)
Reinforcement Learning
(1)
Methods
(1)
Keywords
knowledge editing
(8)
large language model
(7)
graph neural network
(6)
vision-language model
(5)
language model
(4)
diffusion model
(3)
model editing
(3)
hallucination mitigation
(3)
parameter update
(2)
attention mechanism
(2)
direct preference optimization
(2)
large vision-language model
(2)
null space projection
(2)
jailbreak attack
(2)
molecular relational learning
(2)
multimodal learning
(2)
multimodal large language model
(2)
knowledge distillation
(1)
transfer learning
(1)
model security
(1)
Papers
Hierarchical Semantic Alignment for Image Clustering
AAAI 2026
Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation
ACL 2026
Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models
CVPR 2026
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
ICLR 2025
AnyEdit: Edit Any Knowledge Encoded in Language Models
ICML 2025
Context-DPO: Aligning Language Models for Context-Faithfulness
ACL 2025
Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
ACL 2025
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
ICML 2025
Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts
ACL 2025
DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector
ICLR 2025
Dynamic Multimodal Prototype Learning in Vision-Language Models
ICCV 2025
Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models
ACL 2025
G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks
ICML 2025
Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
ICLR 2025
Iterative Substructure Extraction for Molecular Relational Learning with Interactive Graph Information Bottleneck
ICLR 2025
Knowledge Graph-Driven Memory Editing with Directional Interventions
EMNLP 2025
Multi-agent Architecture Search via Agentic Supernet
ICML 2025
Neuron-Level Sequential Editing for Large Language Models
ACL 2025
NExT-Mol: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation
ICLR 2025
On the Role of Attention Heads in Large Language Model Safety
ICLR 2025
Reinforced Lifelong Editing for Language Models
ICML 2025
Safety in Large Reasoning Models: A Survey
EMNLP 2025
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
EMNLP 2025
MMGNN: A Molecular Merged Graph Neural Network for Explainable Solvation Free Energy Prediction
IJCAI 2024
MolTC: Towards Molecular Relational Modeling In Language Models
ACL 2024
Towards Neuron Attributions in Multi-Modal Large Language Models
NeurIPS 2024
Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
ICML 2024
Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis
NeurIPS 2023
Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective
ICLR 2023