Video & Image Sense Lab

university

https://ivi.fnwi.uva.nl/vislab/

AI & ML interests

Computer Vision, Generative Models, World Models, Multimodality

Recent Activity

Dheerraa authored a paper 25 days ago

Your Transformer Is Secretly Elastic

Dheerraa authored a paper 25 days ago

PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence

Dheerraa authored a paper 25 days ago

Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It

View all activity

Papers

Your Transformer Is Secretly Elastic

PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence

View all Papers

authored 4 papers 25 days ago

Your Transformer Is Secretly Elastic

Paper • 2610.20588 • Published 27 days ago • 4

PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence

Paper • 2610.07127 • Published Oct 5 • 1

Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It

Paper • 2507.13328 • Published Jul 17, 2025

NeoBabel: A Multilingual Open Tower for Visual Generation

Paper • 2507.06137 • Published Jul 8, 2025 • 5

submitted a paper to Daily Papers 25 days ago

Your Transformer Is Secretly Elastic

Paper • 2610.20588 • Published 27 days ago • 4

submitted a paper to Daily Papers 29 days ago

Less from More: Reinforcing Sparse Video Reasoning from Dense References

Paper • 2610.10893 • Published Oct 7 • 9

authored a paper about 1 month ago

Less from More: Reinforcing Sparse Video Reasoning from Dense References

Paper • 2610.10893 • Published Oct 7 • 9

updated a collection about 1 month ago

LiFT

2 items • Updated Oct 9

authored a paper about 1 month ago

LiFT: Loop Flow Transformers

Paper • 2610.05538 • Published Oct 4 • 10

authored 3 papers about 1 month ago

QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain

Paper • 2411.19534 • Published Dec 15, 2025 • 1

IPO: Interpretable Prompt Optimization for Vision-Language Models

Paper • 2410.15397 • Published Oct 20, 2024

RegionReasoner: Region-Grounded Multi-Round Visual Reasoning

Paper • 2602.03733 • Published Feb 3 • 1

submitted a paper to Daily Papers about 1 month ago

LiFT: Loop Flow Transformers

Paper • 2610.05538 • Published Oct 4 • 10

updated a Space about 1 month ago

README

published a Space about 1 month ago

README

authored 2 papers 6 months ago

MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention

Paper • 2512.01738 • Published Mar 9 • 1

Follow the Mean: Reference-Guided Flow Matching

Paper • 2605.10302 • Published May 12 • 3

submitted a paper to Daily Papers 6 months ago

Follow the Mean: Reference-Guided Flow Matching

Paper • 2605.10302 • Published May 12 • 3

authored a paper about 1 year ago

Reproducibility Study of "Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents"

Paper • 2505.09289 • Published May 14, 2025