3 citations · 3 across the 17 of their papers we have counts for
11 papers · 1 filter
Prior Directions: Separating Geometric Identification from Behavioral Efficacy in Visual Revision
Weile Gong, Zijian Lu, Mingcai Chen +3
Vision-language models can remain anchored to stale verbal priors even when current visual evidence supports a different answer. We use this controlled revision failure to ask whet…
Geometric Risk Control for Vision-Language Model OCR
Weile Gong, Zijian Lu, Mingcai Chen +3
Vision-language models (VLMs) enable flexible generative optical character recognition (OCR), while their open-ended decoders can expose wrong but fluent text with weak visual supp…
The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation
Chenyu Mu, Xin He, Qu Yang +13
Recent advances in video generation have produced models capable of synthesizing stunning visual content from simple text prompts. However, these models struggle to generate long-f…
EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture
Xin He, Longhui Wei, Jianbo Ouyang +3
We propose EMMA, an efficient and unified architecture for multimodal understanding, generation and editing. Specifically, EMMA primarily consists of 1) An efficient autoencoder wi…
PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
Shulei Wang, Longhui Wei, Xin He +4
Personalized generation models for a single subject have demonstrated remarkable effectiveness, highlighting their significant potential. However, when extended to multiple subject…
A Comprehensive Survey on World Models for Embodied AI
Xinqing Li, Xin He, Le Zhang +3
Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators that capture environment dynamics,…
Mixpert: Mitigating Multimodal Learning Conflicts with Efficient Mixture-of-Vision-Experts
Xin He, Xumeng Han, Longhui Wei +2
Multimodal large language models (MLLMs) require a nuanced interpretation of complex image information, typically leveraging a vision encoder to perceive various visual scenarios.…
ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts
Xumeng Han, Longhui Wei, Zhiyang Dou +6
Mixture-of-Experts (MoE) models embody the divide-and-conquer concept and are a promising approach for increasing model capacity, demonstrating excellent scalability across multipl…
Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models
Xin He, Longhui Wei, Lingxi Xie +1
Multimodal Large Language Models (MLLMs) are experiencing rapid growth, yielding a plethora of noteworthy contributions in recent months. The prevailing trend involves adopting dat…
Boosting Segment Anything Model Towards Open-Vocabulary Learning
Xumeng Han, Longhui Wei, Xuehui Yu +6
The recent Segment Anything Model (SAM) has emerged as a new paradigmatic vision foundation model, showcasing potent zero-shot generalization and flexible prompting. Despite SAM fi…
SemanticBoost: Elevating Motion Generation with Augmented Textual Cues
Xin He, Shaoli Huang, Xiaohang Zhan +2
Current techniques face difficulties in generating motions from intricate semantic descriptions, primarily due to insufficient semantic annotations in datasets and weak contextual…