Geração de Imagem

Blog Geração de Imagem

Compositional Motion Generation from Demonstration with Object-Centric Neural Fields

arXiv:2607.07129v1 Announce Type: new Abstract: Compositionality, by organizing complex behavior as combinations of simpler elements, enables robot learning that is scalable and data efficient. Leveraging this principle, we propose a generative learning-from-demonstration framework that enables compositional modeling of robotic behavior by connecting perception and motion through shared object-level representations. We render scenes from object-centric neural representations that integrate canon...

09.07.2026

Paper Geração de Imagem

LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models

LongE2V enables high-quality video recovery from sparse event streams by leveraging pre-trained video diffusion priors and addressing temporal stability and frame interpolation cha…

09.07.2026 ·▲ 31

Paper Geração de Imagem

OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators

OPSD-V enhances few-step autoregressive video diffusion models by using real long-video data for temporal context during training, providing dense trajectory-level supervision that…

09.07.2026 ·▲ 8

Paper Geração de Imagem

From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models

Pretrained diffusion transformers can be adapted for dense prediction tasks by mapping tokens to task-native outputs instead of generating RGB images, achieving state-of-the-art re…

09.07.2026 ·▲ 12

Paper LLMs & Texto

Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation

A benchmark for scientific lineage reasoning and idea generation is introduced, organizing scientific works as genetic-like Idea Genome objects and evaluating both reasoning and ge…

09.07.2026 ·▲ 32

Modelo Geração de Imagem

ostris/krea2_turbo_style_reference

Modelo de geração de imagem — 2.5 mil downloads e 77 curtidas no Hugging Face.

08.07.2026 ·↓ 2464

Blog LLMs & Texto

Prime Intellect raises $130M Series A to help enterprises build their own AI agents

Founded in 2024, Prime Intellect’s goal is to give organizations capabilities to train their own agentic systems without relying on frontier AI labs.

08.07.2026

Modelo Geração de Imagem

robbyant/lingbot-world-v2-14b-causal-fast

Modelo de geração de vídeo · 14 B de parâmetros — 0 downloads e 104 curtidas no Hugging Face.

08.07.2026

Modelo Geração de Imagem

mgwr/M87

Modelo de geração de imagem — 4.7 mil downloads e 163 curtidas no Hugging Face.

07.07.2026 ·↓ 4652

Modelo Geração de Imagem

Alissonerdx/LTX-Best-Face-ID

Modelo de geração de vídeo — 0 downloads e 202 curtidas no Hugging Face.

07.07.2026

Blog LLMs & Texto

Companies traded people for tokens. The returns haven’t shown up

Jensen Huang has a test for whether an engineer is worth keeping, and it comes with a token budget attached. On the All-In Podcast at the close of GTC 2026, the Nvidia chief executive said that if a US$500,000 engineer’s annual AI token consumption came in under US$250,000, half their salary, “I am going to be deeply alarmed.” Nvidia, […] The post Companies traded people for tokens. The returns haven’t shown up appeared first on AI News .

07.07.2026

Blog Dados & Embeddings

Inpainting U-Net for seamless pedestrian-level wind prediction across urban morphologies

arXiv:2607.02560v1 Announce Type: new Abstract: Pedestrian-level wind prediction is essential for urban design and wind-comfort assessment, but high-fidelity simulations such as LES remain computationally expensive for rapid evaluation. This study develops a two-stage U-Net framework for efficient prediction of time-averaged pedestrian-level wind speed over realistic urban morphologies. The model is trained and evaluated using the UrbanTALES dataset, which contains realistic city configurations ...

07.07.2026