MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents

Kaixin Ma, Di Feng, Alexander Metz +3

The paper introduces MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents that handle multi-image, multi-turn tasks across hundreds of too…

Deep Tracking: Visual Tracking Using Deep Convolutional Networks

Meera Hahn, Si Chen, Afshin Dehghan

GAUDI: A Neural Architect for Immersive 3D Scene Generation

Miguel Angel Bautista, Pengsheng Guo, Samira Abnar +9

Language Models Improve When Pretraining Data Matches Target Tasks

David Mizrahi, Anders Boesen Lindbo Larsen, Jesse Allardice +7

Binary Quadratic Programing for Online Tracking of Hundreds of People in Extremely Crowded Scenes

Afshin Dehghan, Mubarak Shah

Apple Intelligence Foundation Language Models: Tech Report 2025

Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang +395

SO-Bench: A Structural Output Evaluation of Multimodal LLMs

Di Feng, Kaixin Ma, Feng Nan +9

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

Roman Bachmann, Jesse Allardice, David Mizrahi +6

SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

Mingze Xu, Mingfei Gao, Zhe Gan +5

VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

Andrei Atanov, Jesse Allardice, Roman Bachmann +6

StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

Haibo Wang, Bo Feng, Zhengfeng Lai +6

DAGER: Deep Age, Gender and Emotion Recognition Using Convolutional Neural Network

Afshin Dehghan, Enrique G. Ortiz, Guang Shu +1

Cubify Anything: Scaling Indoor 3D Object Detection

Justin Lazarow, David Griffiths, Gefen Kohavi +2

UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation

Rui Tian, Mingfei Gao, Mingze Xu +5

MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities

Mingqiao Ye, Zhaochong An, Zhitong Gao +11

Weblica: Scalable and Reproducible Training Environments for Visual Web Agents

Oğuzhan Fatih Kar, Roman Bachmann, Yuanzheng Gong +2

Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping

Justin Lazarow, Kai Kang, Afshin Dehghan

(1D) Ordered Tokens Enable Efficient Test-Time Search

Zhitong Gao, Parham Rezaei, Ali Cy +7

ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data

Gilad Baruch, Zhuoyuan Chen, Afshin Dehghan +8

SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding

Mingze Xu, Mingfei Gao, Shiyu Li +7

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities

Roman Bachmann, Oğuzhan Fatih Kar, David Mizrahi +6

AToken: A Unified Tokenizer for Vision

Jiasen Lu, Liangchen Song, Mingze Xu +5

UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning

Rui Tian, Mingfei Gao, Haiming Gang +5

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Haotian Zhang, Mingfei Gao, Zhe Gan +20

4M: Massively Multimodal Masked Modeling

David Mizrahi, Roman Bachmann, Oğuzhan Fatih Kar +4

View Independent Vehicle Make, Model and Color Recognition Using Convolutional Neural Network

Afshin Dehghan, Syed Zain Masood, Guang Shu +1

License Plate Detection and Recognition Using Deeply Learned Convolutional Neural Networks

Syed Zain Masood, Guang Shu, Afshin Dehghan +1

MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs

Erik Daxberger, Nina Wenzel, David Griffiths +8

Understanding Alignment in Multimodal LLMs: A Comprehensive Study

Elmira Amirloo, Jean-Philippe Fauconnier, Christoph Roesmann +8