Explore GPD-1's transformative approach to motion planning and traffic simulation for smarter vehicles.

Researchers developed a scalable framework for data attribution in diffusion models, using influence functions to improve model transparency and accountability.

Researchers unveil MIMETIC2, a method to determine when text-to-image models cross the line from creativity to imitation, offering insights into ethical AI training.

UC Berkeley researchers introduce shortcut models, simplifying generative modeling to reduce computational costs while maintaining high-quality outputs.

Researchers introduce ViTok, a Vision Transformer-based auto-encoder that scales visual tokenization to enhance image and video generation while reducing computational costs.

AI struggles to match human creativity despite advancements, facing challenges in abstract thinking, coherence, and originality. Researchers call for a comprehensive process-based evaluation to enhanc...

OpenAI researchers propose TrigFlow, a novel framework that stabilizes and scales continuous-time consistency models using trigonometric parameterization, reducing complexity and improving efficiency.

How are you, hacker? 🪐 What’s happening in tech today, November 9, 2025? The HackerNoon Newsletter brings the HackerNoon homepage straight to your inbox. On this day, The chemical element Darmstadtium...

Researchers developed a groundbreaking dataset and detection models to identify and correct human artifacts in text-to-image outputs, significantly enhancing the quality of generative AI models.

Il Training-Free Guidance (TFG) semplifica la generazione condizionale eliminando il riaddestramento. Utilizzando predictor preaddestrati, come classificatori o funzioni di perdita, guida il processo senza sacrificare qualità. Unifica tecniche esistenti, ottimizza iperparametri ed è applicabile in contesti vari, dalle immagini alle molecole e all'audio. Mitiga bias nei dataset, riduce costi e tempi, e favorisce applicazioni scalabili, flessibili e inclusive.

Large language models struggle with coherence in tasks like navigation and logic puzzles, as new metrics expose gaps in their ability to recover underlying world models.