pith. sign in

Afshin Dehghan

Identifiers

  • name variant Afshin Dehghan 0.60 · backfill

Papers (23)

  1. Weblica: Scalable and Reproducible Training Environments for Visual Web Agents cs.AI · 2026 · author #5
  2. (1D) Ordered Tokens Enable Efficient Test-Time Search cs.CV · 2026 · author #7
  3. VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization cs.CV · 2026 · author #8
  4. Apple Intelligence Foundation Language Models: Tech Report 2025 cs.LG · 2025 · author #90
  5. Language Models Improve When Pretraining Data Matches Target Tasks cs.CL · 2025 · author #10
  6. Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping cs.CV · 2025 · author #3
  7. UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation cs.CV · 2025 · author #8
  8. SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding cs.CV · 2025 · author #10
  9. MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs cs.CV · 2025 · author #10
  10. FlexTok: Resampling Images into 1D Token Sequences of Flexible Length cs.CV · 2025 · author #9
  11. Cubify Anything: Scaling Indoor 3D Object Detection cs.CV · 2024 · author #5
  12. MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning cs.CV · 2024 · author #21
  13. SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models cs.CV · 2024 · author #8
  14. Understanding Alignment in Multimodal LLMs: A Comprehensive Study cs.CV · 2024 · author #8
  15. 4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities cs.CV · 2024 · author #8
  16. 4M: Massively Multimodal Masked Modeling cs.CV · 2023 · author #6
  17. GAUDI: A Neural Architect for Immersive 3D Scene Generation cs.CV · 2022 · author #11
  18. ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data cs.CV · 2021 · author #3
  19. License Plate Detection and Recognition Using Deeply Learned Convolutional Neural Networks cs.CV · 2017 · author #3
  20. DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Network cs.CV · 2017 · author #1
  21. View Independent Vehicle Make, Model and Color Recognition Using Convolutional Neural Network cs.CV · 2017 · author #1
  22. Binary Quadratic Programing for Online Tracking of Hundreds of People in Extremely Crowded Scenes cs.CV · 2016 · author #1
  23. Deep Tracking: Visual Tracking Using Deep Convolutional Networks cs.CV · 2015 · author #3

Mentions

  • 2503.13111 #10 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2507.13575 #90 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2507.12466 #10 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2502.13967 #9 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2505.23756 #3 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2505.14682 #8 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2503.18943 #10 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2412.04458 #5 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2409.20566 #21 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2407.15841 #8 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2407.02477 #8 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2406.09406 #8 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2312.06647 #6 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2207.13751 #11 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 2111.08897 #3 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 1703.07330 #3 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 1603.09240 #1 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 1702.04280 #1 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 1702.01721 #1 · arxiv_oai · confidence 0.70 Afshin Dehghan
  • 1512.03993 #3 · arxiv_oai · confidence 0.70 Afshin Dehghan

Frequent Coauthors