Arena, an AI evaluation platform born at UC Berkeley, reached a $100M annual revenue run rate eight months after launching its product, as demand surges for benchmarks that measure real-world AI utili…
Researchers introduced GAT, a purely transformer-based Generative Adversarial Network trained in a compact Variational Autoencoder latent space, achieving state-of-the-art single-step class-conditiona…
Researchers propose ViPSy, a framework for constructing preference data that reduces hallucinations in Vision-Language Models (VLMs) by leveraging visual cues from semantically aligned image variants.…
A developer built an artist attribution system using PyTorch and a pretrained ResNet-50 model. The system classifies paintings by artist with top-3 predictions, leveraging transfer learning for effici…
Unconventional AI released Un-0, an image generation model powered by coupled Kuramoto oscillators instead of conventional neural network architectures, publishing code and weights to demonstrate its …
Unconventional AI released Un-0, an image generator that uses simulated coupled oscillators instead of neural network layers, achieving an FID of 6.74 on ImageNet 64x64. The model validates that physi…
Unconventional AI released Un-0, an image generator powered by a simulated system of coupled oscillators, achieving an FID of 6.74 on class-conditional ImageNet 64×64. The model demonstrates that phys…
Researchers released DiffusionBench, a unified codebase for holistic evaluation of generative diffusion transformers across tasks like ImageNet and text-to-image generation. The benchmark supports tra…
A developer traces the 70-year history of AI from symbolic systems to modern transformer-based models, highlighting key milestones like the 1956 Dartmouth Workshop, expert systems, the first AI winter…
Researchers propose a method to learn asynchronous denoising schedules for multi-representation diffusion models, improving visual synthesis. On ImageNet 256x256, their approach achieves FID 1.05 with…
Researchers Tian et al. introduced Visual Autoregressive Modeling (VAR), a new image generation method that predicts the next resolution instead of the next token, achieving state-of-the-art results o…
A developer argues that the current AI revolution is fundamentally different from past waves of enthusiasm, citing the convergence of large-scale labeled data, GPU computing, and deep network architec…
Researchers at arXiv have identified that Batch Normalization causes gradient skew in dynamic sparse training (DST) methods, leading to slower convergence compared to dense neural network training. Th…
Researchers have developed Concept-Aware Fault Detection (CAFD), a learning-based method that improves fault detection in deep neural networks by integrating model-based, distance-based, and a novel c…
The next frontier for medical AI is building "world models" that can predict how a biological state changes in response to an intervention, moving beyond current systems focused on classification or q…
"weight banding," a structural phenomenon in neural networks where the weights in the final convolutional layer of vision models using global average pooling display a uniform spatial pattern, particu…
Deep neural networks can be understood as pipelines of simple functions, and that the intermediate values (or "activations") within these networks can be viewed as high-dimensional vectors. To analyze…