Generative AI news and analysis on Web Pulse: 5811 curated articles tracking the latest Generative AI developments, tools, and research, updated continuously from vetted sources.
Researchers propose a two-stage diffusion-based super-resolution framework to enhance multi-spectral cloud microstructures by 4x, outperforming state-of-the-art methods. The approach uses inverse diffusion and self-super…
Researchers introduced FASR++, a diffusion-model-based super-resolution algorithm that leverages multiple low-quality images from surveillance cameras to enhance facial features and improve face recognition. The method a…
Researchers introduced ArtisanCAD, an industrial-level CAD agent that uses expert-grounded knowledge distillation to convert ambiguous text prompts into executable CAD programs. The system leverages a CAD intermediate re…
Researchers introduced CanvasAgent, a multimodal agent that orchestrates multiple visual tools for complex image creation and editing, along with the CanvasCraft dataset containing 140K annotated trajectories. The agent …
Researchers have developed a training-free method for 3D shape abstraction using generative image models, achieving state-of-the-art Chamfer distance on HumanPrim and Toys4K benchmarks with 5-9 primitives per object. The…
Researchers introduced Design-CP, two context-parallel inference strategies for RFdiffusion 3 that distribute quadratic activations across multi-GPU meshes, enabling all-atom design of large protein nanoparticles. The me…
Researchers propose a decision-focused generative framework for correlated scenario generation in distributionally robust optimization (DRO)-based power grid dispatch, which reduces operational costs by 0.80%-2.02% compa…
Researchers propose retrieval-augmented generation and constrained decoding to improve LLM-generated web API invocation code. RAG reduces hallucinations but can introduce unnecessary parameters, while constrained decodin…
Researchers propose CcGAN-AVAR, an imbalance-robust extension of Continuous conditional GAN that uses adaptive vicinal learning and auxiliary regularization to improve generation quality and label consistency. The method…
Researchers introduced a Gibbs posterior sampler for solving inverse problems using a diffusion-based prior model. The method addresses ill-posed linear inverse problems with Bayesian regularization, offering simplicity …
A developer launched HairstylesPro, an AI-powered tool that lets users virtually try on over 500 real human hairstyles before getting a haircut. The platform offers free and paid plans, using AI image models to generate …
A new autonomous zine called Mold, entirely written and art-directed by machines, explores AI culture with each issue precipitated from a public ledger without human theme selection.
Meta launched its Muse Image AI model with Instagram integration, automatically opting public profiles into allowing others to generate AI images using their likeness by tagging their username. Users must manually disabl…
LLM code generation enthusiasts are creating 'vibe forks'—reimplementations of existing projects using AI coding tools—raising concerns about the value of source code as a moat. However, curation, trust, and deployment h…
Tencent is leveraging decentralized compute networks from Titan Network to cut AI infrastructure costs by up to 75%, as part of a broader strategy to regain its status as an AI innovator. The Chinese tech giant has launc…
A 41-year-old German woman used ChatGPT for relationship advice after suspecting her husband of infidelity, finding the AI helpful for organizing thoughts but noting its tendency to validate feelings. A study by Pronova …
A developer released a React component that replicates the chat input styles of ChatGPT, Claude, Codex, Gemini, Perplexity, and other AI agents, allowing developers to drop ready-made agent-input UIs into their apps with…
AI systems are shifting from single-prompt engineering to self-correcting loop architectures, where outputs are iteratively evaluated and refined. Research from Carnegie Mellon shows iterative self-refinement improves LL…
Meta Superintelligence Labs launched Muse Image on July 7, the first image generator that autonomously uses tools like web search and code execution at inference time, with self-refinement emerging from reinforcement lea…
The Answer Citation Protocol (ACP) is a proposed web standard that delivers content in two layers—visual summaries and structured JSON-LD data—to optimize AI retrieval by reducing token waste and inference latency. By pr…