Zhixiong Zeng
5 papers · 2020–2026 · 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(16)
❓
The Questioner
Venues
Top co-authors
Research topics
Artificial Intelligence
(4)
Core AI
(4)
Natural Language Processing
(3)
Applications
(3)
Deep Learning
(2)
Machine Learning
(2)
Learning Types · Deep Learning
(2)
Computer Vision
(1)
Interdisciplinary
(1)
Application Areas
(1)
Domain-Specific
(1)
Learning Types · Machine Learning
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Social
(1)
Keywords
large language model
(2)
reinforcement learning
(2)
question answering
(1)
multimodal learning
(1)
sarcasm detection
(1)
model merging
(1)
reward hacking
(1)
vision-language model
(1)
supervised fine-tuning
(1)
graph reasoning
(1)
multimodal reasoning
(1)
social media
(1)
multimodal sarcasm detection
(1)
semantic association
(1)
optical character recognition
(1)
parameter merging
(1)
neural network
(1)
visual graph
(1)
text-image fusion
(1)
cross-modality contrast
(1)
Papers
Perceptual-Evidence Anchored Reinforced Learning for Multimodal Reasoning
CVPR 2026
Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR
CVPR 2026
GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning
NeurIPS 2024
Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
EMNLP 2024
Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association
ACL 2020