papers

Publications (17)

cs.CV2026

Cambrian-P: Pose-Grounded Video Understanding

Jihan Yang, Zifan Zhao, Xichen Pan +6

Camera pose matters. The position and orientation of each viewpoint define a shared spatial coordinate frame that relates observations across video frames. Yet this signal is large…

cs.CV2024

Learning Temporal Distribution and Spatial Correlation Towards Universal Moving Object Segmentation

Guanfang Dong, Chenqiu Zhao, Xichen Pan +1

The goal of moving object segmentation is separating moving objects from stationary backgrounds in videos. One major challenge in this problem is how to develop a universal model f…

cs.GR2024

Image Sculpting: Precise Object Editing with 3D Geometry Control

Jiraphon Yenphraphai, Xichen Pan, Sainan Liu +2

We present Image Sculpting, a new framework for editing 2D images by incorporating tools from 3D geometry and graphics. This approach differs markedly from existing methods, which…

cs.CV2025

BLIP3o-NEXT: Next Frontier of Native Image Generation

Jiuhai Chen, Le Xue, Zhiyang Xu +12

We present BLIP3o-NEXT, a fully open-source foundation model in the BLIP3 series that advances the next frontier of native image generation. BLIP3o-NEXT unifies text-to-image gener…

cs.CV2025

Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis

Bingda Tang, Boyang Zheng, Xichen Pan +2

This paper does not describe a new method; instead, it provides a thorough exploration of an important yet understudied design space related to recent advances in text-to-image syn…

cs.CV2026

V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising

Han Lin, Xichen Pan, Zun Wang +4

Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel…

cs.AI2026

Think Then Embed: Generative Context Improves Multimodal Embedding

Xuanming Cui, Jianpeng Cheng, Hong-you Chen +11

There is a growing interest in Universal Multimodal Embeddings (UME), where models are required to generate task-specific representations. While recent studies show that Multimodal…

cs.CV2025

PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop

Chenyu Li, Oscar Michel, Xichen Pan +3

Large-scale pre-trained video generation models excel in content creation but are not reliable as physically accurate world simulators out of the box. This work studies the process…

cs.CV2022

Synthesizing Coherent Story with Auto-Regressive Latent Diffusion Models

Xichen Pan, Pengda Qin, Yuhong Li +2

Conditioned diffusion models have demonstrated state-of-the-art text-to-image synthesis capacity. Recently, most works focus on synthesizing independent images; While for real-worl…

cs.CV2025

Exploring MLLM-Diffusion Information Transfer with MetaCanvas

Han Lin, Xichen Pan, Ziqi Huang +10

Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation,…

cs.CV2025

Transfer between Modalities with MetaQueries

Xichen Pan, Satya Narayan Shukla, Aashu Singh +9

Unified multimodal models aim to integrate understanding (text output) and generation (pixel output), but aligning these different modalities within a single architecture often dem…

cs.CV2024

Kosmos-G: Generating Images in Context with Multimodal Large Language Models

Xichen Pan, Li Dong, Shaohan Huang +3

Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require te…

cs.SD2022

Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition

Xichen Pan, Peiyu Chen, Yichen Gong +3

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual s…

cs.CV2026

RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space

Xichen Pan, Aashu Singh, Satya Narayan Shukla +3

Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically limited to text encoding, while denoising is handled by newly trained generative…

cs.CV2025

BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Jiuhai Chen, Zhiyang Xu, Xichen Pan +10

Unifying image understanding and generation has gained growing attention in recent research on multimodal models. Although design choices for image understanding have been extensiv…

cs.CV2024

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Shengbang Tong, Ellis Brown, Penghao Wu +11

We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. While stronger language models can enhance multimodal capabilities, the design…

cs.CV2025

Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation

Zhiyang Xu, Jiuhai Chen, Zhaojiang Lin +10

Recent advances in large language models (LLMs) have enabled multimodal foundation models to tackle both image understanding and generation within a unified framework. Despite thes…