Mingyu Jin
18 papers · 2024–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Cross-Pollinator (12) π Conference Polyglot (9) π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (6)
πΊοΈ
Taxonomy Completionist
(28)
π
Interdisciplinary Bridge
π€
Dynamic Duo
(12)
β
The Questioner
β‘
Prolific Year
(11)
ποΈ
Keyword Collector
(73)
π
Century Club
(17)
Conferences
EMNLP (4)
ACL (3)
COLING (2)
ICLR (2)
NAACL (2)
AAAI (1)
ACML (1)
CVPR (1)
EACL (1)
ICML (1)
Top co-authors
Research topics
Keywords
large language model
(7)
sparse autoencoder
(2)
backdoor attack
(2)
adversarial attack
(2)
language model
(2)
self-supervised learning
(1)
video captioning
(1)
memory recall
(1)
explanation generation
(1)
factual knowledge
(1)
privacy preservation
(1)
video understanding
(1)
multimodal interaction
(1)
text understanding
(1)
backdoor defense
(1)
human motion
(1)
safety alignment
(1)
contextual reasoning
(1)
machine learning security
(1)
contextual representation
(1)
Papers
SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models
EACL 2026
Visual Agents as Fast and Slow Thinkers
ICLR 2025
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
ICML 2025
EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs
NAACL 2025
Data-centric NLP Backdoor Defense from the Lens of Memorization
NAACL 2025
Exploring Fine-Grained Human Motion Video Captioning
COLING 2025
Invisible Backdoor Attack against Self-supervised Learning
CVPR 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
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
COLING 2025
From Commands to Prompts: LLM-based Semantic File System for AIOS
ICLR 2025
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models
EMNLP 2025
BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysis
EMNLP 2024
The Impact of Reasoning Step Length on Large Language Models
ACL 2024
Knowledge Graph Large Language Model (KG-LLM) for Link Prediction
ACML 2024
Adaptive Axes: A Pipeline for In-domain Social Stereotype Analysis
EMNLP 2024
MathAttack: Attacking Large Language Models towards Math Solving Ability
AAAI 2024
TrustAgent: Towards Safe and Trustworthy LLM-based Agents
EMNLP 2024