Junkai Chen
7 papers · 2025–2026 · 3 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
(16)
⭐
Rising Star
(7)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI
(6)
Deep Learning
(2)
Natural Language Processing
(2)
Learning Types
(2)
Computer Science
(1)
Computer Vision
(1)
Machine Learning
(1)
Analysis
(1)
Application Areas
(1)
Applications · Natural Language Processing
(1)
Applications · Computer Science
(1)
Generation
(1)
Models
(1)
Keywords
reinforcement learning
(1)
benchmark evaluation
(1)
curriculum learning
(1)
attention mechanism
(1)
multimodal learning
(1)
confidence calibration
(1)
model safety
(1)
machine unlearning
(1)
scene graph
(1)
multimodal large language model
(1)
feed-forward network
(1)
large vision-language model
(1)
security evaluation
(1)
hallucination detection
(1)
object hallucination
(1)
code agent
(1)
visual token
(1)
multi-head attention
(1)
generation quality
(1)
secure coding
(1)
Papers
SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
ACL 2026
SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios
ACL 2026
Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens
CVPR 2025
Fast Large Language Model Collaborative Decoding via Speculation
ICML 2025
Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
ICML 2025
Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models
ACL 2025
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
ACL 2025