Wei Suo
8 papers · 2021–2026 · 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 · Bronze
🗺️
Taxonomy Completionist
(18)
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Artificial Intelligence
(4)
Deep Learning
(4)
Machine Learning
(4)
Core AI
(4)
Learning Types · Machine Learning
(3)
Natural Language Processing
(2)
Architectures
(2)
Learning Types · Deep Learning
(2)
Computer Vision
(1)
Analysis
(1)
Application Areas
(1)
Applications
(1)
Models
(1)
Optimization & Theory
(1)
Resources & Methods
(1)
Keywords
hallucination mitigation
(2)
large vision-language model
(2)
vision-language model
(2)
multimodal learning
(1)
visual reasoning
(1)
visual grounding
(1)
model pruning
(1)
token pruning
(1)
inference efficiency
(1)
multimodal reasoning
(1)
referring expression comprehension
(1)
layer pruning
(1)
natural language explanation
(1)
dynamic decoding
(1)
data generation
(1)
contrastive decoding
(1)
multimodal chain-of-thought
(1)
vision-language instruction tuning
(1)
large language model
(1)
decoding intervention
(1)
Papers
Understanding and Mitigating Hallucinations in Multimodal Chain-of-Thought Models
CVPR 2026
Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding
CVPR 2025
Pruning All-Rounder: Rethinking and Improving Inference Efficiency for Large Vision Language Models
ICCV 2025
C3L: Content Correlated Vision-Language Instruction Tuning Data Generation via Contrastive Learning
IJCAI 2024
Rethinking and Improving Visual Prompt Selection for In-Context Learning Segmentation Framework
ECCV 2024
S3C: Semi-Supervised VQA Natural Language Explanation via Self-Critical Learning
CVPR 2023
A Simple and Robust Correlation Filtering Method for Text-Based Person Search
ECCV 2022
Proposal-free One-stage Referring Expression via Grid-Word Cross-Attention
IJCAI 2021