Rajat Koner
7 papers · 2022–2026 · 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 ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (12) π£ Hot Topic Early Bird π₯ Unstoppable Β· Bronze
β
The Questioner
Top co-authors
Research topics
Keywords
multimodal learning
(2)
transformer architecture
(2)
robustness
(1)
image captioning
(1)
image reconstruction
(1)
video understanding
(1)
text-to-image generation
(1)
video instance segmentation
(1)
vision-language model
(1)
multimodal large language model
(1)
inference acceleration
(1)
temporal coherence
(1)
spatio-temporal attention
(1)
cross attention
(1)
video question answering
(1)
self attention
(1)
visual token pruning
(1)
online processing
(1)
centerline detection
(1)
cross-modal understanding
(1)
Papers
EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models
WACV 2026
Perceive Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries
WACV 2025
LookupViT: Compressing visual information to a limited number of tokens
ECCV 2024
Do DALL-E and Flamingo Understand Each Other?
ICCV 2023
InstanceFormer: An Online Video Instance Segmentation Framework
AAAI 2023
Vesselformer: Towards Complete 3D Vessel Graph Generation from Images
MIDL 2023
Relationformer: A Unified Framework for Image-to-Graph Generation
ECCV 2022