Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have identified a failure mode in multimodal AI systems called "Modal Isolation," where generated images and text reasoning fail to inform each other during complex tasks. The team proposes MoTiF, a two-stage…
Researchers have developed Z-Image Turbo++, a two-step image generation model distilled from an eight-step teacher model, achieving high-fidelity results through three targeted design choices. The method uses teacher-gen…
Researchers have introduced Rotary Value Embeddings (RoVE), a parameter-free modification to Rotary Position Embeddings (RoPE) that makes value pathways position-sensitive by rotating values simultaneously with keys. Thi…
Researchers from a study on arXiv introduce HieraRAG, a hierarchical framework for determining optimal granularity in RAG benchmark construction, using 5,872 synthetic QA pairs from FineWeb-10BT across three dimensions. …
A new perspective argues that generative AI models for semiconductor manufacturing must enforce hard physical constraints by design, not through post-hoc filtering, because physically invalid outputs are unusable in fabr…
Researchers at an academic medical center developed a pre-response classifier that predicts the risk of a user rejecting an LLM-generated clinical response, achieving an AUROC of 0.719 over 4.5 months of user feedback. T…
Researchers introduced PERIA, a tool-augmented visual agent designed to improve spatial reasoning in vision-language models by actively acquiring evidence and performing multi-step visual interactions. The agent uses two…
Researchers have developed ProHiFlo, a hierarchical flow matching framework for de novo protein generation that models backbone geometry before refining to all-atom coordinates, reducing computational cost while maintain…
Researchers have demonstrated that parameter quantization and electrode reduction techniques can significantly reduce the computational complexity of deep neural networks for EEG analysis on wearable devices with minimal…
Researchers have developed a framework for strategic decision support in AI agent systems, where agents act on behalf of users and require human or tool assistance to prevent consequential errors. The framework minimizes…
Apple debuted the third generation of Apple Foundation Models (AFM) on June 8, 2026, unveiling a family of five models spanning on-device and server deployments, including the 20-billion-parameter, natively multimodal AF…
A developer has completed PuskesmasAI, an offline-first Progressive Web App that uses AI-powered medical triage to assist community health workers in rural Indonesia. The app runs entirely on-device with no internet conn…
RAG (Retrieval-Augmented Generation) enables AI applications to retrieve relevant information from external data sources and use that context to generate accurate responses, overcoming the limitation of large language mo…
A new PDF analysis tool detects parser and representation differences in documents, using 47 forensic passes with MITRE ATT&CK mapping and LightGBM machine learning to identify exploits, tampering, and semantic nondeterm…
Researchers have developed Doc-to-Atom (Doc2Atom), a compositional parametric memory framework that decomposes documents into typed knowledge atoms compiled into independent micro-LoRA adapters. The system uses a query r…
Semgrep's benchmark for AI-powered vulnerability detection shows its Semgrep Multimodal tool finds 3.5x more true positives than a tuned guided prompt at similar precision and lower cost per finding. The system uses stat…
The Tessera team released v1.1 of their geospatial embedding model, improving temporal stability and reducing noise in regions with sparse satellite observations. The update eliminates grid-like seams and stabilizes embe…
New research shows that larger AI models no longer reliably outperform smaller ones on analogical reasoning tasks, undermining the scaling laws that have guided AI development for years. The findings suggest that increas…
Large language models can complete simple analogies like "surgeon is to scalpel as painter is to brush," but they struggle with higher-order structural reasoning that requires transferring relational insights between dif…
Google released Diffusion Gemma in early 2025 as its first open-weight diffusion language model, using a masked diffusion approach that generates text by starting with noise and iteratively refining it into coherent outp…