Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
HubSpot has scaled its semantic search platform to manage over 20 billion vectors across 38+ teams, using an internal service called VaaS built on Qdrant. The company automated cluster management with a Kubernetes Operat…
Researchers introduced Zero-Flow Encoders, a flow-inspired framework for representation learning that uses a zero-flow criterion to certify conditional independence and extract sufficient information from data. The metho…
Researchers at Aalto University used machine learning to accelerate the discovery of two new kagome superconductors, YRu3B2 and LuRu3B2, with critical temperatures of 0.81 K and 0.95 K. The study, published in Physical R…
Hopsworks released version 5.0 on June 30, integrating Claude Code and Codex directly into its ML platform to enable AI agents to write and execute code for feature pipelines, training jobs, and inference endpoints witho…
The MiMo-V2.5 model family introduces Hybrid Sliding Window Attention (Hybrid SWA) to reduce KVCache storage to roughly 1/7 of Full Attention, sparse MoE activation to cut per-token compute, and multimodal encoders for c…
Ternlight, a 7 MB embedding model using ternary quantization and WebAssembly, enables fully client-side semantic search in browsers, bypassing server round-trips and API costs. The model runs locally via a lightweight WA…
WebAssembly (WASM) and the Ternlight framework enable compact, high-performance AI deployment for low-bandwidth areas. The approach uses model compression, WASM conversion, and offline operation to deliver AI on resource…
Jim Dowling's O'Reilly book 'Building Machine Learning Systems with a Feature Store' offers a practical guide for deploying machine learning models into production, based on a course he taught at KTH in Stockholm. The bo…
A data engineer outlines a practical roadmap for breaking into the field in 2026, emphasizing SQL fluency, Python scripting, cloud cost optimization, and data modeling over outdated tools like Hadoop. The guide prioritiz…
Scientists at Aalto University and international collaborators combined machine learning with quantum physics to discover two new superconductors, YRu3B2 and LuRu3B2, and developed a faster method to search for room-temp…
A developer evaluated the YAMNet TFLite model on the ESC-50 environmental sound dataset, achieving 60.45% top-1 accuracy across 2,000 clips. The experiment used a pretrained model without fine-tuning, with higher accurac…
Researchers at the Mechanistic Interpretability project have identified that the knight-fork policy logit in the Maia 3 chess transformer snaps into place after block 5's attention layer, using logit lens and attention p…
Researchers propose Object-Centric Environment Modeling (OCM), a method that organizes LLM agent experience into executable object-centric code bases, improving performance and reducing invalid actions across benchmarks.
A new study on agentic AI policy repair in a hotel-pricing simulator shows that LLM-based editors can nearly match benchmark performance using only region-level diagnostic feedback, achieving RevPAR 108.47 vs. benchmark …
Researchers proposed an uncertainty-aware reinforcement learning framework for algorithmic trading that integrates distributional, epistemic, and aleatoric uncertainty estimations using SHAP-weighted reconstruction, MC D…
Researchers propose MPSelectTune, a two-stage fine-tuning method that improves concept unlearning in large language models by focusing on the prompt type with the highest concept accuracy. The approach achieves 2-15% mai…
Researchers at arXiv and Phys. Rev. Research have developed a training framework that ranks and paces quantum machine learning samples by informativeness, adapting classical curriculum learning and hard-example-mining to…
Researchers propose PGRE, a Poisson-Gamma probabilistic model for dynamic knowledge graphs that captures inter-relational dependencies and temporal evolution. The model achieves competitive link prediction performance, e…
Researchers propose a hybrid block diffusion language model (BDLM) combining Mamba and attention mechanisms that restricts reverse Mamba scans to the active denoising block, enabling exact caching across blocks. At 87M p…
Researchers identified five failure modes in perturbation-based construct-validity audits of AI safety benchmarks, demonstrating that implementation details can silently invalidate audit conclusions. In a case study of t…