Ziwei Huang
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 · Gold
🗺️
Taxonomy Completionist
(18)
⭐
Rising Star
(7)
🌈
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(4)
Deep Learning
(4)
Core AI
(4)
Learning Types
(4)
Computer Vision
(3)
Machine Learning
(2)
Mathematics & Optimization
(2)
Natural Language Processing
(2)
Applications · Natural Language Processing
(2)
Generation
(2)
Models
(2)
Optimization
(2)
Computer Science
(1)
Applications · Computer Science
(1)
Architectures
(1)
Keywords
combinatorial optimization
(2)
reinforcement learning
(2)
image generation
(2)
visual question answering
(2)
direct preference optimization
(1)
text-to-image synthesis
(1)
factuality evaluation
(1)
multimodal learning
(1)
document understanding
(1)
text-to-image generation
(1)
out-of-distribution generalization
(1)
generative model
(1)
diffusion model
(1)
autoregressive model
(1)
text-to-image model
(1)
vision-language model
(1)
multimodal large language model
(1)
reward shaping
(1)
evolutionary algorithm
(1)
large vision-language model
(1)
Papers
From Competition to Synergy: Unlocking Reinforcement Learning for Subject-Driven Image Generation
ACL 2026
From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding
ACL 2026
PEOAT: Personalization-Guided Evolutionary Question Assembly for One-Shot Adaptive Testing
AAAI 2026
Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback
AAAI 2025
MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis
AAAI 2025
Rethinking Light Decoder-based Solvers for Vehicle Routing Problems
ICLR 2025
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
ACL 2025