Zhe Gan

Scaling Synthetic Task Generation for Agents via Exploration

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

UltraCUA: Scaling Computer Use Agent through GUI and Programmatic Control

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents

Where Did the Reasoning Go Wrong? A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection

GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing

DeepMMSearch-R1: Empowering Multimodal LLMs in Multi-Modal Web Search

Contrastive Localized Language-Image Pre-Training

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

Understanding Alignment in Multimodal LLMs: A Comprehensive Study

Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms

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

MIA-Bench: Towards Better Instruction Following Evaluation of Multimodal LLMs

Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models

MMEgo: Towards Building Egocentric Multimodal LLMs for Video QA

SlowFast-LLaVA: A strong training-free baseline for video large language models

Contrastive Localized Language-Image Pre-Training

Improve Vision Language Model Chain-of-thought Reasoning

Pixelated Instructions: Can Multimodal Large Language Models Follow Printed Instructions in Images?