AI News Archive: April 30, 2026 — Part 22
Sourced from 500+ daily AI sources, scored by relevance.
- Dynamic Scaled Gradient Descent for Stable Fine-Tuning for Classifications
Fine-tuning pretrained models has become a standard approach to adapting pretrained knowledge to improve the accuracy on new sparse, imbalance datasets. However, issues arise when optimization falls into a collapsed state, where the model gets stuck, leading to degraded performance and unstable trai...
- Physical Foundation Models: Fixed hardware implementations of large-scale neural networks
Foundation models are deep neural networks (such as GPT-5, Gemini~3, and Opus~4) trained on large datasets that can perform diverse downstream tasks -- text and code generation, question answering, summarization, image classification, and so on. The philosophy of foundation models is to put effort i...
- Prediction-powered Inference by Mixture of Experts
The rapidly expanding artificial intelligence (AI) industry has produced diverse yet powerful prediction tools, each with its own network architecture, training strategy, data-processing pipeline, and domain-specific strengths. These tools create new opportunities for semi-supervised inference, in w...
- On the Expressive Power of GNNs to Solve Linear SDPs
Semidefinite programs (SDPs) are a powerful framework for convex optimization and for constructing strong relaxations of hard combinatorial problems. However, solving large SDPs can be computationally expensive, motivating the use of machine learning models as fast computational surrogates. Graph ne...
- Data-Efficient Indentation Size Effect Correction in Steels Using Machine Learning and Physics-Guided Augmentation
Shallow nanoindentation enables mechanical characterization of thin films, individual phases and other volume-constrained materials, but measured hardness is often inflated by the indentation size effect (ISE), contact-area errors and tip-geometry artifacts. Classical ISE corrections such as the Nix...
- Sampling two-dimensional spin systems with transformers
Autoregressive Neural Networks based on dense or convolutional layers have recently been shown to be a viable strategy for generating classical spin systems. Unlike these methods, sampling with transformers is commonly considered to be computationally inefficient. In this work, we propose a novel ap...
- Mind the Gap: Structure-Aware Consistency in Preference Learning
Preference learning has become the foundation of aligning Large Language Models (LLMs) with human intent. Popular methods, such as Direct Preference Optimization (DPO), minimize surrogate losses as proxies for the intractable pairwise ranking loss. However, we demonstrate that for the equicontinuous...
- Optimized Deferral for Imbalanced Settings
Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost. This approach, known as learning to defer, is essential in domains like natural language generation, medical diagnosis, and computer vision, wh...
- The TEA Nets framework combines AI and cognitive network science to model targets, events and actors in text
We introduce Target-Event-Agent Networks (TEA Nets) as a computational framework to extract subjects (``Agents"), verbs (``Events"), and objects (``Targets") from texts. Grounded in cognitive network science and artificial intelligence, TEA Nets are implemented as an open-source Python library. We t...
- ANCORA: Learning to Question via Manifold-Anchored Self-Play for Verifiable Reasoning
We propose a paradigm shift from learning to answer to learning to question: can a language model generate verifiable problems, solve them, and turn the resulting feedback into self-improvement without human supervision? We introduce ANCORA, an anchored-curriculum framework in which a unified policy...
- Green Physics-Informed Machine Learning Models For Structural Health Monitoring
Machine learning continues to emerge as an important tool to be utilised within structural engineering and structural health monitoring, due to its ability to accurately and quickly perform both regression and classification tasks. However, a purely data driven approach has its limitations, particul...
- Math Education Digital Shadows for facilitating learning with LLMs: Math performance, anxiety and confidence in simulated students and AIs
To enhance LLMs' impact on math education, we need data on their mathematical prowess and biases across prompts. To fill this gap, we introduce MEDS (Math Education Digital Shadows) as a dataset mapping how large language models reason about and report mathematics across human- and AI-like condition...
- One Pass, Any Order: Position-Invariant Listwise Reranking for LLM-Based Recommendation
Large language models (LLMs) are increasingly used for recommendation reranking, but their listwise predictions can depend on the order in which candidates are presented. This creates a mismatch between the set-based nature of recommendation and the sequence-based computation of decoder-only LLMs, w...
- Privacy-Preserving Federated Learning via Differential Privacy and Homomorphic Encryption for Cardiovascular Disease Risk Modeling
Protecting sensitive health data while enabling collaborative analysis is a central challenge in healthcare. Traditional machine learning (ML) requires institutions to pool anonymized patient records, centralizing analytical development and privacy risks at a single site. Privacy-enhancing technolog...
- FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning
Federated Multi-Label Learning is a distributed paradigm where multiple clients possess heterogeneous multi-label data and perform collaborative learning under privacy constraints without sharing raw data. However, modeling label correlations under heterogeneous distributions remains challenging. Du...
- Differentiable latent structure discovery for interpretable forecasting in clinical time series
Background: Timely, uncertainty-aware forecasting from irregular electronic health records (EHR) can support critical-care decisions, yet most approaches either impute to a grid or sacrifice interpretability. We introduce StructGP, a continuous-time multi-task Gaussian process that couples process c...
- Calibrating Attribution Proxies for Reward Allocation in Participatory Weather Sensing
Large-scale IoT weather sensing networks require incentive mechanisms to sustain participation, yet determining how much value individual data contributions bring to the network remains an open problem. Existing approaches address data quality but not data valuation; in operational meteorology, adjo...
- Beyond the Baseband: Adaptive Multi-Band Encoding for Full-Spectrum Bioacoustics Classification
Animals hear and vocalize across frequency ranges that differ substantially from humans, often extending into the ultrasonic domain. Yet most computational bioacoustics systems rely on audio models pre-trained at 16 kHz, restricting their usable bandwidth to the 0-8 kHz baseband and discarding highe...
- Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
In modern parametric model training, full-batch gradient descent (and its variants) suffers due to progressively stronger biasing towards the exact realization of training data; this drives the systematic ``generalization gap'', where the train error becomes an unreliable proxy for test error. Exist...
- Crin AI
Learn about AI & watch text become tokens in a node graph
- Probabilistic Circuits for Irregular Multivariate Time Series Forecasting
Joint probabilistic modeling is essential for forecasting irregular multivariate time series (IMTS) to accurately quantify uncertainty. Existing approaches often struggle to balance model expressivity with consistent marginalization, frequently leading to unreliable or contradictory forecasts. To ad...
- Hyper-Dimensional Fingerprints as Molecular Representations
Computational molecular representations underpin virtual screening, property prediction, and materials discovery. Conventional fingerprints are efficient and deterministic but lose structural information through hash-based compression, particularly at low dimensionalities. Learned representations fr...
- Runhuman
Human Testers for Your AI Code
- MiruAI: Nutrition Guide from Your Camera
Point. Scan. Know what you're eating.
- PorttoCV
Stunning portfolio & generate ATS-optimized CVs with AI
- Way Of Eat
AI-Powered Personalized Meal Plans & Nutrition Coaching
- ArchieGuru
Master system design with an AI-powered reviewer
- Synthoric
Every major AI model. One platform. From £7.99.
- Knowing You
AI Knowledge Companion — Read once, know forever
- AI search visibility for Main Street
AI search visibility scores for small businesses
- Pixelcut
Pixelcut AI | Free Background Remover & Image Upscaler
- AMT
Run creator marketing with AI, not manual work
- Calcis
Know what your LLM calls cost before you make them.
- GPT Image 2
The Ultimate AI Visual Hub powered by GPT Image 2 model.
- HolistCode
Your AI guide to Traditional Chinese Medicine.
- Serpio
Catch trending topics. Publish brand SEO content same day.
- RecipeAI
Cook Smarter with RecipeAI
- CloudWise
Free AWS cost optimizer with AI and 149 waste detectors
- HackFast
AI-powered hacking, from scan to exploit
- ReadMyContract
AI Contract Analyzer
- Cosmog
AI-powered team growth tool
- Astraly
Your AI astrologer who actually knows your chart
- Prism
Never ask for photos again.
- SocialConductorAI
Smart AI replies for all your social pages
- hostreply
Reply to Airbnb guests in seconds, not minutes.
- ContractGuard AI
ContractGuard AI — AI contract review in 30 seconds
- When Does Structure Matter in Continual Learning? Dimensionality Controls When Modularity Shapes Representational Geometry
To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stability-plasticity dilemma affects how representations can be reused across tasks: shared structure enables transfer when t...
- GSDrive: Reinforcing Driving Policies by Multi-mode Trajectory Probing with 3D Gaussian Splatting Environment
End-to-end (E2E) autonomous driving presents a promising approach for translating perceptual inputs directly into driving actions. However, prohibitive annotation costs and temporal data quality degradation hinder long-term real-world deployment. While combining imitation learning (IL) and reinforce...
- PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
Vision-Language-Action (VLA) models advance robotic control via strong visual-linguistic priors. However, existing VLAs predominantly frame pretraining as supervised behavior cloning, overlooking the fundamental nature of robot learning as a goal-reaching process that requires understanding temporal...
- OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction
Human-robot collaboration has been studied primarily in dyadic or sequential settings. However, real homes require multiadic collaboration, where multiple humans and robots share a workspace, acting concurrently on interleaved subtasks with tight spatial and temporal coupling. This regime remains un...