Xinhao Li
11 papers · 2021–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π§ Keyword Pioneer π£ Hot Topic Early Bird π Conference Polyglot (6) π Renaissance Researcher (6)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(16)
π
Century Club
(11)
β‘
Prolific Year
(5)
Conferences
ECCV (4)
CVPR (2)
ICLR (2)
AAAI (1)
EMNLP (1)
ICML (1)
Top co-authors
Keywords
multimodal large language model
(2)
multimodal learning
(2)
vision-language model
(2)
video understanding
(1)
constraint satisfaction
(1)
generative model
(1)
vision language model
(1)
hallucination mitigation
(1)
task alignment
(1)
visual instruction tuning
(1)
drug discovery
(1)
property prediction
(1)
feature aggregation
(1)
visual encoder
(1)
object hallucination
(1)
video benchmark
(1)
molecule optimization
(1)
molecular sampling
(1)
memory bank
(1)
large language model
(1)
Papers
TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning
ICLR 2025
Online Video Understanding: OVBench and VideoChat-Online
CVPR 2025
Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
EMNLP 2025
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
ICML 2025
Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment
CVPR 2025
ZeroI2V: Zero-Cost Adaptation of Pre-Trained Transformers from Image to Video
ECCV 2024
VideoMamba: State Space Model for Efficient Video Understanding
ECCV 2024
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
ECCV 2024
InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
ICLR 2024
Interpretable Open-Set Domain Adaptation via Angular Margin Separation
ECCV 2022
MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization
AAAI 2021