Kai-Po Chang
8 papers · 2024–2026 · 5 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(19)
Top co-authors
Research topics
Machine Learning
(5)
Learning Types · Machine Learning
(4)
Artificial Intelligence
(3)
Computer Vision
(3)
Natural Language Processing
(3)
Core AI
(3)
Deep Learning
(2)
Application Areas
(2)
Generation
(2)
Learning Types · Deep Learning
(2)
Resources & Methods
(2)
Applications
(1)
Models
(1)
Processing
(1)
Keywords
hallucination mitigation
(2)
large language model
(2)
video understanding
(2)
visual question answering
(1)
video captioning
(1)
knowledge distillation
(1)
knowledge editing
(1)
lifelong learning
(1)
diffusion model
(1)
mixture of expert
(1)
vision-language model
(1)
multimodal large language model
(1)
text-to-video generation
(1)
subject customization
(1)
moment retrieval
(1)
video-language model
(1)
natural language explanation
(1)
contrastive decoding
(1)
knowledge update
(1)
activation routing
(1)
Papers
Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment
WACV 2026
SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding
CVPR 2026
TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors
WACV 2026
Serial Lifelong Editing via Mixture of Knowledge Experts
ACL 2025
VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models
CVPR 2025
RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering
ICLR 2024
Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers
ECCV 2024
Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models
ECCV 2024