Related papers: Xuanwu: Evolving General Multimodal Models into an…

We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing…

Reinforcement Learning has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), yet the resulting policies remain brittle against real-world visual degradations such as blur, compression artifacts,…

Language models (LMs) and their extension, vision-language models (VLMs), have achieved remarkable performance across various tasks. However, they still struggle with complex reasoning tasks that require multimodal or multilingual…

Effective content moderation is essential for video platforms to safeguard user experience and uphold community standards. While traditional video classification models effectively handle well-defined moderation tasks, they struggle with…

Recent progress in Multimodal Large Language Models (MLLMs) have significantly enhanced the ability of artificial intelligence systems to understand and generate multimodal content. However, these models often exhibit limited effectiveness…

Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fragmented architectures, cascaded pipelines, and misaligned…

Vision-Language Models (VLMs) have achieved remarkable breakthroughs in recent years, enabling a diverse array of applications in everyday life. However, the substantial computational and storage demands of VLMs pose significant challenges…

Recent multimodal large language models have achieved strong performance in unified text and image understanding and generation, yet extending such native capability to 3D remains challenging due to limited data. Compared to abundant 2D…

Real-world clinical decision-making requires integrating heterogeneous data, including medical text, 2D images, 3D volumes, and videos, while existing AI systems fail to unify all these signals, limiting their utility. In this paper, we…

Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…

Traditional multimodal learning approaches require expensive alignment pre-training to bridge vision and language modalities, typically projecting visual features into discrete text token spaces. We challenge both fundamental assumptions…

Recent advancements in video generation have significantly impacted daily life for both individuals and industries. However, the leading video generation models remain closed-source, resulting in a notable performance gap between industry…

Video Multimodal Large Language Models (V-MLLMs) have shown impressive capabilities in temporal reasoning and cross-modal understanding, yet their vulnerability to adversarial attacks remains underexplored due to unique challenges: complex…

Multimodal Large Language Models (MLLMs) have significantly progressed in offline video understanding. However, applying these models to real-world scenarios, such as autonomous driving and human-computer interaction, presents unique…

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, they encounter challenges in terms of reasoning efficiency, large model size and overthinking. However, existing lightweight…

Large Vision-Language Models (LVLMs) encode visual inputs as dense sequences of patch-level tokens to capture fine-grained semantics. These visual tokens often outnumber their textual counterparts by a large margin, leading to substantial…

Multimodal retrieval is becoming a crucial component of modern AI applications, yet its evaluation lags behind the demands of more realistic and challenging scenarios. Existing benchmarks primarily probe surface-level semantic…

While autoregressive Large Vision-Language Models (LVLMs) demonstrate remarkable proficiency in multimodal tasks, they face a "Visual Signal Dilution" phenomenon, where the accumulation of textual history expands the attention partition…

In this work, we introduce the Qwen3 Embedding series, a significant advancement over its predecessor, the GTE-Qwen series, in text embedding and reranking capabilities, built upon the Qwen3 foundation models. Leveraging the Qwen3 LLMs'…

This paper presents HunyuanOCR, a commercial-grade, open-source, and lightweight (1B parameters) Vision-Language Model (VLM) dedicated to OCR tasks. The architecture comprises a Native Vision Transformer (ViT) and a lightweight LLM…