Geração de Imagem

Blog LLMs & Texto

L’Oréal brings Maybelline virtual try-on to ChatGPT

L’Oréal has announced a collaboration with OpenAI that will bring Maybelline New York’s virtual makeup try-on feature into ChatGPT. The announcement was made at VivaTech 2026. The partnership covers consumer-facing shopping tools, product discovery, advertising pilots, research, and internal content production. The collaboration also covers L’Oréal’s internal use of AI in research, formulation, content production, […] The post L’Oréal brings Maybelline virtual try-on to ChatGPT ap...

22.06.2026

Blog LLMs & Texto

Daybreak: Tools for securing every organization in the world

OpenAI introduces new Daybreak tools, including Codex Security and GPT-5.5-Cyber, to help organizations find, validate, and patch vulnerabilities at scale.

22.06.2026

Modelo Geração de Imagem

zai-org/SCAIL-2

Modelo de geração de vídeo em alta no Hugging Face — 0 downloads e 252 curtidas da comunidade.

22.06.2026

Paper LLMs & Texto

MeshFlow: Mesh Generation with Equivariant Flow Matching

MeshFlow generates triangle meshes directly using equivariant optimal-transport flow matching models with improved inference speed over autoregressive methods.

22.06.2026 ·▲ 1

Paper Geração de Imagem

Safe Few-Step Generation via Velocity Editing

VESFlow is a training-free safety method for flow matching-based text-to-image generation that edits velocity fields to ensure safe output while maintaining prompt integrity.

22.06.2026 ·▲ 4

Editorial Geração de Imagem

JanusMesh e a ilusão como teste de estresse da geração 3D

Um novo paper gera ilusões visuais tridimensionais de forma rápida e zero-shot. O resultado é menos um truque de festa do que um diagnóstico do estado da arte em síntese 3D.

21.06.2026

Dataset Geração de Imagem

HKUSTAudio/ISCSLP2026-CoT-TTS

Dataset em destaque no Hugging Face — 3.4 mil downloads. ISCSLP 2026 CoT-TTS Dataset Dataset Overview This dataset is prepared for the ISCSLP 2026 CoT-TTS Challenge and is designed to support research on con…

19.06.2026 ·↓ 3438

Paper Áudio & Voz

Improving Text-to-Music Generation with Human Preference Rewards

A text-to-music generation system uses reward conditioning, expert iteration, and preference tuning to improve audio quality while maintaining efficiency within a 120M-parameter mo…

19.06.2026

Blog LLMs & Texto

New usage analytics and updated spend controls for enterprises

OpenAI introduces new spend controls and usage analytics for ChatGPT Enterprise, helping organizations manage costs and scale AI with confidence.

18.06.2026

Blog LLMs & Texto

HSBC expands AI banking partnership with Google Cloud

HSBC has entered a multi-year partnership with Google Cloud to develop and deploy artificial intelligence tools across its global operations. Announced at Google Cloud Summit London 2026, the agreement covers work in wealth management, financial crime risk management, and internal decision support. HSBC will work with Google Cloud and Google DeepMind engineering teams on AI […] The post HSBC expands AI banking partnership with Google Cloud appeared first on AI News .

18.06.2026

Paper Geração de Imagem

JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising

A fast, training-free framework generates text-driven 3D visual illusions by decoupling generation into cross-space dual-branch denoising and view-conditioned texture synthesis for…

18.06.2026 ·▲ 19

Paper Robótica & RL

World Action Models: A Survey

World Action Models are predictive-action systems that generate future states for decision-making, with designs balancing representational richness against computational constraint…

18.06.2026 ·▲ 33