Pooyan Fazli
7 papers · 2024–2026 · 5 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(14)
❓
The Questioner
Top co-authors
Research topics
Keywords
video understanding
(5)
multimodal large language model
(3)
multimodal learning
(2)
visual question answering
(1)
direct preference optimization
(1)
temporal reasoning
(1)
image captioning
(1)
explanation generation
(1)
visual reasoning
(1)
off-policy learning
(1)
benchmark dataset
(1)
credit assignment
(1)
token pruning
(1)
teacher-student framework
(1)
visual encoder
(1)
hallucination detection
(1)
spatial reasoning
(1)
multimodal reasoning
(1)
egocentric video
(1)
video-language model
(1)
Papers
AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video
CVPR 2026
ChartQA-X: Generating Explanations for Visual Chart Reasoning
WACV 2026
ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs
ACL 2026
VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
CVPR 2025
VideoPASTA: 7K Preference Pairs That Matter for Video-LLM Alignment
EMNLP 2025
VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
CVPR 2025
OSCaR: Object State Captioning and State Change Representation
NAACL 2024