Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced MR-DiffuSR, a 3D latent diffusion framework that uses high-resolution T1w structural priors to guide super-resolution of thick-slice FLAIR MRI scans, preventing anatomical hallucinations. The model…
Researchers introduced LDM-v0, a large decision model trained offline on trajectories from thousands of heterogeneous reinforcement learning environments, including robotics, autonomous driving, and video games. The sing…
Researchers introduced Local Branch Routing (LBR), a token-level test-time scaling framework that expands a small local lookahead tree and uses a lightweight router to select the best branch, enabling efficient and train…
Researchers propose Dustin, a sparse verification framework for long-context speculative decoding in LLMs, achieving a 27.85x speedup in self-attention and 9.17x end-to-end decoding speedup at 32k sequence length with ne…
Researchers propose a test-time adaptation method using semi-supervised learning to improve AI text detection under continual distribution shifts, such as adversarial humanization and new LLMs. The approach leverages inf…
Researchers used the AI-mathematician system AIM to co-discover sign-embedding quantum algorithms for matrix equations and matrix functions, advancing quantum linear algebra. The human-AI collaboration transformed a vagu…
Researchers propose a new approach to near-sensor computing that performs lightweight Neural Architecture Search (NAS) directly on deployment devices to adapt tiny neural networks to real-time sensor data. Validated on t…
Researchers at arXiv propose a method to certify conservation laws in learned latent world models by decoding physical invariants from latent states. They derive shell-horizon certificates that decompose into representat…
Researchers propose DCQ-GNN, a spectral graph neural network using convex-concave quadratic filters to improve spectral selectivity without high-order polynomials. The model achieves top average rank on heterophilic grap…
Researchers released MacroLens, a multi-task benchmark for contextual financial reasoning under macroeconomic scenarios, covering 4,416 U.S. small- and micro-cap equities from 2021-2026. The benchmark integrates prices, …
A new study on holographic memory for zero-shot compositional reasoning in knowledge graphs found that while Holographic Reduced Representations (HRR) and Fourier HRR (FHRR) perform competitively on single-hop queries, t…
Researchers present a low-resource machine translation system for the Tangkhul-English language pair, achieving a BLEU score of 39.97 using a ByT5-large model fine-tuned on 38,336 parallel sentences. The study highlights…
Researchers argue that neural network learning opacity stems from dynamical complexity, identifying sensitivity to weight initialization, feedback in gradient optimization, and sensitivity to training data as irreducible…
Researchers propose G-SPIN, a graph-based framework that corrects phonetic errors in ASR outputs by combining a graph neural network for candidate generation with a masked language model and LLM for contextual re-ranking…
Astromech, a startup founded in 2025 by Ben Lamm and George Church, develops a Large Life Model and autonomous biological intelligence system that fuses evolutionary logic with deep learning to decode regulatory patterns…
Sai, a software and data engineer based in Florida, introduces himself to the DEV community. He recently completed an MS in Computer Science at Florida Atlantic University and focuses on backend services, data pipelines,…
A developer built two AI tools—TeachSim and GitHub Digest—and realized the second tool revealed how they should be learning AI. The developer found that hands-on projects with real stakes led to deeper understanding than…
A developer built an AI-powered transaction intelligence system for enterprise reconciliation, handling nearly two trillion in annual incoming transfers. The system uses a pipeline including business taxonomy, financial …
A developer argues that most AI projects fail to reach production not because of model quality but due to a lack of robust software engineering. Production systems require reliability, data validation, observability, and…
Pangram Labs researchers explored the internal representations of their AI detection model Pangram 3.3.2 using document-level analysis of activations across layers, aiming to understand what the model sees when distingui…