Topics › Multimodal & Video Generation
Multimodal & Video Generation
Image, video, and speech generation plus production practice: Sora, Veo, Kling, Suno, and the open-source multimodal stack.
· Sep 15, 2026
#Multimodal AI#video generation#Multimodal#image generation#speech generation#voice cloning#Sora#Veo#Kling#Suno
· 8 / 638 articles
News
· 2025-06-26
Qwen has unveiled the Qwen VLo model, a significant upgrade in the multimodal AI domain that not only understands image content but also generates high-quality recreations based on that understanding. This unified multimodal model bridges the gap between perception and creation, showcasing advancements in AI's ability to process and create visual content. The release highlights Qwen's commitment to pushing the boundaries of multimodal AI technology.
News
· 2025-06-04
This article critically examines the prevailing misconceptions about Artificial General Intelligence (AGI) in the AI community. The author argues that while multimodal AI models excel in specific tasks, they fall short of truly emulating human intelligence due to their lack of foundational understanding of the physical world. The author proposes that AGI should prioritize embodiment and interaction with the environment rather than merely stitching together different modalities. By critiquing the
News
· 2025-06-04
In a thought-provoking article on The Gradient, Brown University PhD candidate Benjamin A. Spiegel argues that the current multimodal approach to AGI is doomed. He contends that LLMs learn syntactic heuristics rather than true world models, and that multimodal models sever deep connections between modalities while lacking embodied data. He advocates for embodied interaction as primary, allowing modality-specific processing to emerge naturally. The piece challenges scale-maximalist interpretation
News
· 2025-05-28
DeepSeek has released the latest version R1-0528, featuring significant improvements in benchmark performance, frontend capabilities, hallucination reduction, and support for JSON output and function calling. The update also offers enhanced interaction modes and open-source weights for developers. This release underscores DeepSeek's commitment to enhancing model utility and developer-friendliness, providing a more powerful tool for AI applications.
News
· 2025-04-28
Qwen has officially launched the Qwen3 series of large language models, including the flagship Qwen3-235B-A22B, the smaller MoE model Qwen3-30B-A3B, and the lightweight Qwen3-4B. Qwen3 demonstrates competitive performance in coding, mathematics, and general capabilities benchmark tests, outperforming top-tier models like DeepSeek-R1 and Grok-3. The introduction of the MoE architecture allows Qwen3-30B-A3B to achieve significant performance improvements with only a fraction of the parameters of Q
News
· 2024-12-09
xAI has announced the integration of Aurora, a new autoregressive image generation model, into the Groknet platform. This release signifies xAI's continued advancements in AI image generation, providing developers with enhanced tools for creating high-quality images.
News
· 2024-03-19
Google Research has introduced ScreenAI, a vision-language model designed to understand and interact with user interfaces (UIs) and infographics such as charts, diagrams, and tables. Built upon the PaLI architecture and incorporating the flexible patching strategy from pix2struct, ScreenAI achieves state-of-the-art performance in UI navigation, question answering, and summarization tasks. With 5 billion parameters, it excels in benchmarks like WebSRC, MoTIF, ChartQA, and InfographicVQA. The rele
News
· 2020-11-19
Hugging Face has released the Kornia Differentiable Data Augmentation (DDA) module, leveraging Kornia's differentiable computer vision solutions to integrate data augmentation pipelines with existing PyTorch components such as autograd and optimizers. The module supports both spatial (2D) and volumetric (3D) tensor data augmentation and includes a benchmark comparing its performance with other data augmentation frameworks, highlighting its potential in multimodal data processing.