Search AI Products and News

PolyU & OPPO developed DLoRAL, a video super-resolution framework using dual LoRA: CLoRA for temporal consistency and DLoRA for spatial details. Its two-stage training balances quality and speed (10× faster inference), with open-source code/models available. Limited in tiny text recovery but promising for real-time applications.....

Hong Kong Polytechnic University and OPPO Research Institute jointly released the open-source video super-resolution framework DLoRAL, which generates high-definition videos in one step using diffusion models. The framework adopts a dual LoRA architecture: C-LoRA maintains temporal consistency between frames, while D-LoRA enhances spatial details. Through a two-stage training strategy, it optimizes temporal coherence and high-frequency information. Compared to traditional methods, DLoRAL improves inference speed by 10 times while maintaining smoothness, significantly enhancing image details, and providing an efficient open-source solution for video HD enhancement.

Aliyun open-sources the network agent WebSailor. Its 32B and 72B versions performed well in the BrowseComp evaluation, surpassing multiple closed-source models, ranking just behind OpenAI DeepResearch. The project has been released on GitHub with construction plans and datasets, promoting open innovation in the AI field and providing developers with a smarter web interaction tool.

Glass, an open-source AI assistant by Pickle, gained popularity for its invisible design and real-time processing. It captures screen/audio to organize notes without disrupting workflow, prioritizing privacy. Available for macOS (Windows/Linux planned), it's Apache2.0 licensed with 1.8k GitHub stars. Future plans include 'digital clone' expansion.....

Glass, an open-source AI desktop assistant for macOS, rapidly captures screen/audio data to boost productivity with real-time meeting notes and contextual understanding. Its stealth design ensures privacy.....

Open-source multimodal model EarthMind, designed for Earth observation data, uses spatial attention for precise localization and cross-modal fusion to integrate optical and radar data, supporting multi-granular analysis for disaster monitoring and urban planning.....

Recently, the French AI laboratory Kyutai announced the official open source of its new text-to-speech model, Kyutai TTS, providing global developers and researchers with a high-performance, low-latency speech synthesis solution. This breakthrough release not only promotes the development of open-source AI technology but also opens up new possibilities for multilingual voice interaction applications. AIbase provides an exclusive analysis of this technological highlight and its potential impact. Ultra-low latency, a new experience in real-time interaction. Kyutai TTS has become an industry standout with its exceptional performance.

At the recent Zhipu Open Platform Industrial Ecosystem Conference held in Shanghai, a major development emerged in the field of artificial intelligence: Pudong Venture Capital Group and Zhangjiang Group jointly announced a strategic investment of up to 1 billion yuan in Zhipu, with the first installment already completed. This significant investment will provide strong support for Zhipu in building a trusted artificial intelligence infrastructure and accelerate its layout in the field of General Artificial Intelligence (AGI). In his keynote speech at the conference, Zhipu CEO Zhang Peng elaborated on two latest achievements in the company's efforts to move toward AGI in collaboration with ecosystem partners.

The TEN Agent team recently announced that its core models **TEN Voice Activity Detection (VAD)** and **TEN Turn Detection** are now open source, providing powerful technical support for building real-time, multimodal speech AI agents. This move marks a significant advancement in the TEN framework's efforts to promote the democratization and open-source collaboration of speech interaction technology. The following is the latest information compiled by AIbase, offering an in-depth analysis of these two core models.