Ziheng Jia
6 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
(15)
⭐
Rising Star
(6)
Top co-authors
Research topics
Artificial Intelligence
(5)
Machine Learning
(5)
Core AI · Artificial Intelligence
(5)
Deep Learning
(4)
Application Areas
(3)
Models
(3)
Computer Vision
(2)
Learning Types
(2)
Techniques
(2)
Core AI · Computer Vision
(1)
Optimization & Theory · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Processing
(1)
Keywords
large multimodal model
(3)
video quality assessment
(2)
image quality assessment
(2)
benchmark evaluation
(2)
multimodal learning
(1)
video understanding
(1)
synthetic data generation
(1)
information density
(1)
reward function
(1)
downstream task
(1)
multimodal large language model
(1)
vision-language pre-training
(1)
video quality
(1)
out-of-distribution robustness
(1)
multi-task training
(1)
multi-stage training
(1)
model assessment
(1)
benchmark design
(1)
zero-shot performance
(1)
test evaluation
(1)
Papers
Refine-IQA: Multi-Stage Reinforcement Finetuning for Perceptual Image Quality Assessment
AAAI 2026
Scaling-up Perceptual Video Quality Assessment
AAAI 2026
VITAL: Vision-Encoder-centered Pre-training for LMMs in Visual Quality Assessment
CVPR 2026
Image Quality Assessment: From Human to Machine Preference
CVPR 2025
Information Density Principle for MLLM Benchmarks
ICCV 2025
Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs
CVPR 2025