Cihang Xie

GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset

Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization

MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards

Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails

Bagel-World: Towards High-Quality Visual Question-Visual Answering

LightBagel: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation

Where in the World? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales

When Visualizing is the First Step to Reasoning: MIRA, a Benchmark for Visual Chain-of-Thought

AHELM: A Holistic Evaluation of Audio-Language Models

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Autoregressive Pretraining with Mamba in Vision

HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

What If We Recaption Billions of Web Images with LLaMA-3?

What If We Recaption Billions of Web Images with LLaMA-3?

Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More

Causal Image Modeling for Efficient Visual Understanding

Mamba-Reg: Vision Mamba Also Needs Registers

AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation

M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation

A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?

ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning