Xinfeng Li
9 papers · 2024–2026 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(29)
🗃️
Keyword Collector
(57)
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI
(7)
Machine Learning
(5)
Deep Learning
(4)
Computer Vision
(2)
Natural Language Processing
(2)
Application Areas
(2)
Learning Types · Deep Learning
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Resources & Methods
(2)
Mathematics & Optimization
(1)
Analysis
(1)
Core Methods
(1)
Generation
(1)
Keywords
large language model
(4)
jailbreak attack
(2)
model security
(1)
self-supervised learning
(1)
multilingual nlp
(1)
named entity recognition
(1)
model safety
(1)
synthetic data
(1)
ai safety
(1)
safety alignment
(1)
optical flow
(1)
backdoor attack
(1)
adversarial attack
(1)
benchmark dataset
(1)
language model
(1)
fine-grained classification
(1)
energy-based model
(1)
text-to-image model
(1)
vision-language model
(1)
domain generalization
(1)
Papers
AutoDebias: An Automated Framework for Detecting and Mitigating Backdoor Biases in Text-to-Image Models
CVPR 2026
Dynamic Generation of Multi LLM Agents Communication Topologies with Graph Diffusion Models
ACL 2026
Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy
ACL 2026
DynamicNER: A Dynamic, Multilingual, and Fine-Grained Dataset for LLM-based Named Entity Recognition
EMNLP 2025
Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
ICCV 2025
Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis
EMNLP 2025
Safety in Large Reasoning Models: A Survey
EMNLP 2025
ADFactory: An Effective Framework for Generalizing Optical Flow with NeRF
CVPR 2024
RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
EMNLP 2024