A new arXiv paper (2609.36348v1) reports that adding cross-view class-token alignment to diffusion transformer training improves ImageNet linear-probing accuracy by 9.4% with the class token and 10.1%…
Researchers introduced Persistence Forcing (PerF), a pixel-space diffusion Transformer method that assigns different feature groups distinct refinement budgets across depth, producing what the authors…
A new arXiv paper (2609.28561v1) introduces CARE (Condition-Aware REpresentation regularization), a lightweight plug-and-play framework that dynamically modulates feature distribution based on conditi…
A practical guide demonstrates transfer learning with MobileNetV2 in Keras, using a frozen pretrained base plus a new Dense(5) output layer to classify 3,670 flower photos across five categories (rose…
Researchers introduced curvature-adaptive tubular correction (CAT), a training-free plugin that regulates gradient-guided diffusion sampling by decomposing the guidance gradient into normal and tangen…
A soft-voting ensemble of Swin-Tiny and TinyViT-5M halved the area under the risk-coverage curve (AURC) to 0.0022 from 0.0045 — a 51.8% reduction, lower in all five folds — and raised the coverage at …
A September 11, 2026 arXiv paper shows that permutation-based model confidentiality in hybrid fully homomorphic encryption (FHE) inference fails, with d+1 admissible queries per linear layer enabling …
A condensed timeline traces AI's 80-year arc from artificial neurons and the Turing Test in the 1940s–50s through the first AI winter, the backpropagation breakthrough, statistical machine learning, a…
Learning in imagination, a model-based reinforcement learning approach that trains policies solely on data generated by an action-conditioned world model, addresses sample efficiency by generating dat…
Fei-Fei Li, co-founder of World Labs, has built a company that reached a $1 billion valuation within roughly twelve weeks of emerging from stealth in September 2024, after raising $230 million initial…
Marvin Minsky's 1986 observation that humanity lacks experience with complex machines remains relevant as AI evolves from Frank Rosenblatt's 1957 perceptron to modern deep learning, with AlexNet's 201…
Researchers propose MeanFlow-Transfer (MF-T) and Continuous Adversarial MeanFlow (CAMF) to adapt pretrained diffusion or flow models to new domains with limited data while accelerating sampling. MF-T …
Fei-Fei Li, Stanford professor and co-director of the Stanford Institute for Human-Centered AI, urged policymakers at the AI Action Summit in Paris to base AI regulation on scientific evidence rather …
World Labs co-founder Fei-Fei Li said in a Bloomberg Technology interview published Wednesday that her company aims to teach AI to understand and act in three-dimensional space, moving beyond chatbots…
A researcher replaced the standard scaled dot-product attention in vision transformers with SSOG (Separable Sum of Gaussians), a content-blind geometric attention mechanism that uses a few Gaussian at…
Artist Trevor Paglen's new book argues that the rise of computer vision and generative media has transformed visual culture more profoundly than the discovery of perspective or photography, turning di…
Unconventional AI reported that sparsity in coupled oscillator networks cuts up to 98.4% of connections in its Un-0 image generation model while improving performance by 1.9 FID on ImageNet 64x64. The…
Fei-Fei Li, known as the 'Godmother of AI' and inventor of ImageNet, said on the Huberman Lab podcast that the biggest AI risk in schools is students losing the motivation and agency to learn, not che…
Stanford University professor and Human-Centered AI Institute director Dr. Fei-Fei Li told Andrew Huberman on the Huberman Lab podcast that AI can enhance human intelligence but cannot replicate the d…
A new dissertation from an unnamed researcher introduces bio-inspired active vision systems that use foveal-peripheral sampling and learned saccades to improve efficiency and robustness in deep neural…