Xiangyu Zeng
10 papers · 2018–2025 · 7 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (34)
π
Keyword Champion
(2)
ποΈ
Keyword Collector
(60)
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(7)
Machine Learning
(7)
Core AI
(7)
Deep Learning
(5)
Computer Vision
(3)
Natural Language Processing
(3)
Application Areas
(3)
Core Methods
(3)
Learning Types Β· Machine Learning
(3)
Learning Types Β· Deep Learning
(3)
Applications
(2)
Architectures
(2)
Processing
(2)
Resources & Methods
(2)
Interdisciplinary
(1)
Keywords
multimodal large language model
(3)
spoken language understanding
(2)
long-term memory
(2)
multimodal learning
(2)
knowledge transfer
(2)
question answering
(2)
multi-task learning
(1)
zero-shot learning
(1)
transformer architecture
(1)
token selection
(1)
instruction tuning
(1)
video understanding
(1)
human pose estimation
(1)
working memory
(1)
catastrophic forgetting
(1)
intent detection
(1)
progressive learning
(1)
temporal grounding
(1)
logical reasoning
(1)
continual learning
(1)
Papers
Deduction with Induction: Combining Knowledge Discovery and Reasoning for Interpretable Deep Reinforcement Learning
IJCAI 2025
Make Your Training Flexible: Towards Deployment-Efficient Video Models
ICCV 2025
Online Video Understanding: OVBench and VideoChat-Online
CVPR 2025
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
CVPR 2025
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
ICLR 2025
A Framework for Inference Inspired by Human Memory Mechanisms
ICLR 2024
SDMTR: A Brain-inspired Transformer for Relation Inference
AISTATS 2024
Single View Physical Distance Estimation Using Human Pose
ICCV 2021
A Progressive Model to Enable Continual Learning for Semantic Slot Filling
EMNLP 2019
User Information Augmented Semantic Frame Parsing Using Progressive Neural Networks
Interspeech 2018