Mingyu Jin
18 papers · 2024–2026 · 10 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 Conference Polyglot Β· Gold π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (31) π£ Hot Topic Early Bird π€ Dynamic Duo (12)
π
Renaissance Researcher
(5)
β
The Questioner
β‘
Prolific Year Β· Prolific
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(93)
Top co-authors
Research topics
Artificial Intelligence
(15)
Core AI
(15)
Machine Learning
(8)
Natural Language Processing
(6)
Learning Types Β· Machine Learning
(5)
Resources & Methods
(5)
Deep Learning
(3)
Application Areas
(3)
Core Methods
(2)
Learning Types Β· Deep Learning
(2)
Computer Vision
(1)
Knowledge & Reasoning
(1)
Security & Privacy
(1)
Applications
(1)
Generation
(1)
Keywords
large language model
(8)
sparse autoencoder
(2)
backdoor attack
(2)
adversarial attack
(2)
language model
(2)
visual question answering
(1)
memory recall
(1)
link prediction
(1)
self-supervised learning
(1)
video captioning
(1)
prompt engineering
(1)
information retrieval
(1)
contextual reasoning
(1)
factual knowledge
(1)
decision making
(1)
video understanding
(1)
privacy preservation
(1)
backdoor defense
(1)
multimodal interaction
(1)
explanation generation
(1)
Papers
SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models
EACL 2026
Data-centric NLP Backdoor Defense from the Lens of Memorization
NAACL 2025
Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities
ACL 2025
Disentangling Memory and Reasoning Ability in Large Language Models
ACL 2025
EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
NAACL 2025
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
COLING 2025
Exploring Fine-Grained Human Motion Video Captioning
COLING 2025
From Commands to Prompts: LLM-based Semantic File System for AIOS
ICLR 2025
Invisible Backdoor Attack against Self-supervised Learning
CVPR 2025
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
ICML 2025
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models
EMNLP 2025
Visual Agents as Fast and Slow Thinkers
ICLR 2025
Adaptive Axes: A Pipeline for In-domain Social Stereotype Analysis
EMNLP 2024
BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis
EMNLP 2024
Knowledge Graph Large Language Model (KG-LLM) for Link Prediction
ACML 2024
MathAttack: Attacking Large Language Models towards Math Solving Ability
AAAI 2024
The Impact of Reasoning Step Length on Large Language Models
ACL 2024
TrustAgent: Towards Safe and Trustworthy LLM-based Agents
EMNLP 2024