Kaiyuan Liu
5 papers · 2023–2026 · 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
(15)
Venues
Top co-authors
Research topics
Artificial Intelligence
(3)
Core AI
(3)
Computer Vision
(2)
Machine Learning
(2)
Computer Science
(1)
Deep Learning
(1)
Natural Language Processing
(1)
Analysis
(1)
Application Areas
(1)
Applications · Computer Science
(1)
Applications · Natural Language Processing
(1)
Domain-Specific
(1)
Generation
(1)
Learning Paradigms
(1)
Learning Types
(1)
Keywords
causal inference
(1)
attention mechanism
(1)
code generation
(1)
diffusion model
(1)
temporal action segmentation
(1)
foundation model
(1)
text-to-image model
(1)
counterfactual reasoning
(1)
multimodal large language model
(1)
text-to-image diffusion
(1)
hallucination detection
(1)
automated evaluation
(1)
dense caption
(1)
label bia
(1)
timestamp supervision
(1)
model fairness
(1)
lexical bia
(1)
spoken question answering
(1)
toxic language detection
(1)
human image generation
(1)
Papers
CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
AAAI 2026
ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation
ACL 2025
CosmicMan: A Text-to-Image Foundation Model for Humans
CVPR 2024
Take Its Essence, Discard Its Dross! Debiasing for Toxic Language Detection via Counterfactual Causal Effect
COLING 2024
Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation
CVPR 2023