12 papers
RISE-Video: Can Video Generators Decode Implicit World Rules?
Mingxin Liu, Shuran Ma, Shibei Meng +9
While generative video models have achieved remarkable visual fidelity, their capacity to internalize and reason over implicit world rules remains a critical yet under-explored fro…
ReMiT: RL-Guided Mid-Training for Iterative LLM Evolution
Junjie Huang, Jiarui Qin, Di Yin +4
Standard training pipelines for large language models (LLMs) are typically unidirectional, progressing from pre-training to post-training. However, the potential for a bidirectiona…
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-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Junru Lu, Jiarui Qin, Lingfeng Qiao +35
We introduce Youtu-LLM, a lightweight yet powerful language model that harmonizes high computational efficiency with native agentic intelligence. Unlike typical small models that r…
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…
Streaming Video Instruction Tuning
Jiaer Xia, Peixian Chen, Mengdan Zhang +2
We present Streamo, a real-time streaming video LLM that serves as a general-purpose interactive assistant. Unlike existing online video models that focus narrowly on question answ…
ActiveVLN: Towards Active Exploration via Multi-Turn RL in Vision-and-Language Navigation
Zekai Zhang, Weiye Zhu, Hewei Pan +4
The Vision-and-Language Navigation (VLN) task requires an agent to follow natural language instructions and navigate through complex environments. Existing MLLM-based VLN methods p…
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…
Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving
Yao Cheng, Yibo Zhao, Jiapeng Zhu +3
Large Language Models (LLMs) have demonstrated significant potential across various domains. However, they often struggle with integrating external knowledge and performing complex…
HRVDA: High-Resolution Visual Document Assistant
Chaohu Liu, Kun Yin, Haoyu Cao +6
Leveraging vast training data, multimodal large language models (MLLMs) have demonstrated formidable general visual comprehension capabilities and achieved remarkable performance a…
Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models
Xin Li, Yunfei Wu, Xinghua Jiang +6
Recently, the advent of Large Visual-Language Models (LVLMs) has received increasing attention across various domains, particularly in the field of visual document understanding (V…