8 papers
VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision
Zhehan Kan, Yubo Zhu, Xinghua Jiang +10
While Vision-Language Models (VLMs) demonstrate strong capabilities, they continue to suffer from a critical limitation: insufficient fine-grained visual perception, which fundamen…
UVU: Improving Multimodal Understanding via Vision-Language Unified Autoregressive Paradigm
Zhehan Kan, Xinghua Jiang, Yubo Zhu +10
Despite remarkable advancements in multimodal large language models (MLLMs), their fine-grained visual understanding is constrained by a primary reliance on sparse textual supervis…
Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
Zhixiang Wei, Yi Li, Zhehan Kan +38
Despite the significant advancements represented by Vision-Language Models (VLMs), current architectures often exhibit limitations in retaining fine-grained visual information, lea…
Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding
Haoyu Cao, Kun Yin, Yunfei Wu +16
This paper presents Youtu-Parsing, an efficient and versatile document parsing model designed for high-performance content extraction. The architecture employs a native Vision Tran…
DREAM: Document Reconstruction via End-to-end Autoregressive Model
Xin Li, Mingming Gong, Yunfei Wu +7
Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community.…
TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs
Zhehan Kan, Yanlin Liu, Kun Yin +8
DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs). While recent methods have attempted to replicate R1's reasoning capabilities in multimoda…
Break the Visual Perception: Adversarial Attacks Targeting Encoded Visual Tokens of Large Vision-Language Models
Yubo Wang, Chaohu Liu, Yanqiu Qu +3
Large vision-language models (LVLMs) integrate visual information into large language models, showcasing remarkable multi-modal conversational capabilities. However, the visual mod…
Talk With Human-like Agents: Empathetic Dialogue Through Perceptible Acoustic Reception and Reaction
Haoqiu Yan, Yongxin Zhu, Kai Zheng +4
Large Language Model (LLM)-enhanced agents become increasingly prevalent in Human-AI communication, offering vast potential from entertainment to professional domains. However, cur…