AI News Archive: April 29, 2026 — Part 26
Sourced from 500+ daily AI sources, scored by relevance.
- Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models
Diffusion models have achieved remarkable success in synthesizing complex static and temporal visuals, a breakthrough largely driven by Classifier-Free Guidance (CFG). However, despite its pivotal role in aligning generated content with textual prompts, standard CFG relies on a globally uniform scal...
- Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners
One of the most exciting applications of vision models involve pixel-level reasoning. Despite the abundance of vision foundation models, we still lack representations that effectively embed spatio-temporal properties of visual scenes at the pixel level. Existing frameworks either train on image-base...
- noirdoc
PII guard for Claude Code to keep client data out of context
- Cross-Domain Transfer of Hyperspectral Foundation Models
Hyperspectral imaging (HSI) semantic segmentation typically relies on in-domain training, but limited data availability often restricts model performance in real-world applications. Current approaches to leverage foundation models in proximal sensing use cross-modality techniques, bridging RGB and H...
- $\text{PKS}^4$:Parallel Kinematic Selective State Space Scanners for Efficient Video Understanding
Temporal modeling remains a fundamental challenge in video understanding, particularly as sequence lengths scale. Traditional video models relying on dense spatiotemporal attention suffer from quadratic computational costs for long videos. To circumvent these costs, recent approaches adapt image mod...
- Last-Layer-Centric Feature Recombination: Unleashing 3D Geometric Knowledge in DINOv3 for Monocular Depth Estimation
Monocular depth estimation (MDE) is a fundamental yet inherently ill-posed task. Recent vision foundation models (VFMs), particularly DINO-based transformers, have significantly improved accuracy and generalization for dense prediction. Prior works generally follow a unified paradigm: sampling a fix...
- Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
We introduce Hyper Input Convex Neural Networks (HyCNNs), a novel neural network architecture designed for learning convex functions. HyCNNs combine the principles of Maxout networks with input convex neural networks (ICNNs) to create a neural network that is always convex in the input, theoreticall...
- Multiple Additive Neural Networks for Structured and Unstructured Data
This paper extends and explains the Multiple Additive Neural Networks (MANN) methodology, an enhancement to the traditional Gradient Boosting framework, utilizing nearly shallow neural networks instead of decision trees as base learners. This innovative approach leverages neural network architecture...
- Unifying Sparse Attention with Hierarchical Memory for Scalable Long-Context LLM Serving
Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing only a small, query-dependent subset of the KV state per decoding step and extending the KV storage to CPU memory. In practice, however, these algorith...
- Uncertainty-Aware Predictive Safety Filters for Probabilistic Neural Network Dynamics
Predictive safety filters (PSFs) leverage model predictive control to enforce constraint satisfaction during deep reinforcement learning (RL) exploration, yet their reliance on first-principles models or Gaussian processes limits scalability and broader applicability. Meanwhile, model-based RL (MBRL...
- Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging
Federated Unlearning (FU) is an emerging paradigm in Federated Learning (FL) that enables participating clients to fully remove their contributions from a trained global model, driven by data protection regulations that mandate the right to be forgotten. However, existing FU methods mostly rely on s...
- A Multi-Dataset Benchmark of Multiple Instance Learning for 3D Neuroimage Classification
Despite being resource-intensive to train, 3D convolutional neural networks (CNNs) have been the standard approach to classify CT and MRI scans. Recent work suggests that deep multiple instance learning (MIL) may be a more efficient alternative for 3D brain scans, especially when the pre-trained ima...