200 articles tagged with #ai-models. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers have developed SAFE, a new framework for ensembling Large Language Models that selectively combines models at specific token positions rather than every token. The method improves both accuracy and efficiency in long-form text generation by considering tokenization mismatches and consensus in probability distributions.
Researchers introduced D-Negation, a new dataset and learning framework that improves vision-language AI models' ability to understand negative semantics and complex expressions. The approach achieved up to 5.7 mAP improvement on negative semantic evaluations while fine-tuning less than 10% of model parameters.
Google's NotebookLM now generates fully animated 'cinematic' video overviews from user research and notes, upgrading from basic narrated slideshows. The feature uses multiple AI models including Gemini 3, Nano Banana Pro, and Veo 3 to create animated visuals and determine narrative style automatically.
A Bitcoin Policy Institute study reveals that major AI systems including Claude, GPT, Grok, and Gemini show preference for Bitcoin over traditional fiat currencies and stablecoins. This finding suggests AI models may inherently recognize Bitcoin's value proposition when making currency-related decisions.
Researchers introduce StaTS, a new diffusion model for time series forecasting that learns adaptive noise schedules and uses frequency-guided denoising. The model addresses limitations of fixed noise schedules in existing diffusion models by incorporating spectral regularization and data-adaptive scheduling for improved structural preservation.
Researchers introduce Whisper-MLA, a modified version of OpenAI's Whisper speech recognition model that uses Multi-Head Latent Attention to reduce GPU memory consumption by up to 87.5% while maintaining accuracy. The innovation addresses a key scalability issue with transformer-based ASR models when processing long-form audio.
Researchers introduce General Proximal Flow Networks (GPFNs), a generalization of Bayesian Flow Networks that allows for arbitrary divergence functions instead of fixed Kullback-Leibler divergence. The framework enables iterative generative modeling with improved generation quality when divergence functions are adapted to underlying data geometry.
The article provides a hands-on comparison between Google and ByteDance's latest image AI models, evaluating their differences in pricing, processing speed, and creative control capabilities. This analysis helps understand the competitive landscape in the rapidly evolving image generation AI market.
Venice AI's VVV token surged 35% today, pushing the company's valuation above $600 million. The rally was triggered by Venice becoming the recommended private model provider for OpenClaw.
Anthropic is challenging the US Pentagon's decision to label it a 'supply chain risk' after negotiations over military use of its AI models failed. The AI company argues that blacklisting its technology would be legally unsound.
Perplexity has launched Perplexity Computer, a new system that the company claims unifies all current AI capabilities into a single platform. This represents another strategic bet that users prefer accessing multiple AI models through one integrated system rather than switching between different AI services.
Google has released Nano Banana 2, an AI image generation model that combines professional-level world knowledge with high-speed performance and improved text handling. The launch faces immediate competition from ByteDance's newly announced Seedream 5 model in the AI image generation space.
Google has launched Nano Banana 2, a new AI image generation model that replaces previous versions and is now available in Gemini. The model represents Google's latest advancement in AI image generation technology.
Google has released Nano Banana 2 (Gemini 3.1 Flash Image), a new AI image generation and editing model that promises professional-level intelligence and fidelity. The model is positioned as their best offering for image applications and is now available for developers to build with.
Last Week in AI #335 covers major AI model releases including Opus 4.6, Codex 5.3, Gemini 3 Deep Think, GLM 5, and Seedance 2.0. The edition is described as particularly packed with AI developments and includes additional minor updates.
Google integrates Gemini AI-powered 'auto browse' functionality into Chrome browser while users increasingly adopt open source Moltbot for continuous AI assistance. Qwen3-Max-Thinking model has also launched, highlighting continued advancement in AI capabilities across multiple platforms.
China's Moonshot AI released an open-source model Kimi K2.5 along with a coding agent, while Google launched Genie 3's interactive world-building prototype for AI Ultra subscribers. These developments represent significant advances in AI model capabilities and accessibility across both open-source and commercial platforms.
OpenAI will retire multiple ChatGPT models including GPT-4o, GPT-4.1, GPT-4.1 mini, and OpenAI o4-mini on February 13, 2026, alongside the previously announced GPT-5 retirement. The API services will remain unchanged at this time.
ATLAS presents new scaling laws for multilingual generative AI models, providing practical frameworks for understanding how model performance scales across different languages and model sizes. This research offers valuable insights for optimizing multilingual AI system development and deployment strategies.
The article discusses a methodology for improving intent extraction in AI systems by using smaller, specialized models through decomposition techniques. This approach aims to achieve better performance than larger, monolithic models by breaking down complex intent recognition tasks into smaller, more manageable components.
OpenAI is enhancing cybersecurity safeguards and defensive capabilities as AI models become more powerful. The company is focusing on risk assessment, preventing misuse, and collaborating with the security community to improve overall cyber resilience.
DeepSeek releases version 3.2 AI model claiming improved speed, cost-efficiency and performance. NVIDIA partners are reportedly shifting toward Google's TPU ecosystem, while new research explores nested learning in deep learning architectures.
DeepSeek released new reasoning models version 3.2, while Mistral launched version 3 with both frontier and small model variants. These releases represent significant advances in AI model capabilities, with open-weight models continuing to challenge proprietary alternatives.
A new Swift client library called swift-huggingface has been released, providing complete integration with Hugging Face's AI model ecosystem. This development enables iOS and macOS developers to directly access and implement Hugging Face's machine learning models in their Swift applications.
Google launches two new AI models - Gemini 3 and Nano Banana Pro - while Anthropic releases Claude Opus 4.5. These developments represent continued advancement in the competitive AI model landscape among major tech companies.
