Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have developed PiD, a pixel diffusion decoder that directly transforms latent representations into high-resolution images, bypassing the traditional decode-then-super-resolve pipeline. The system decodes 512×…
Apple blocked $11.2 billion in potentially fraudulent App Store transactions over the past six years, including $2.2 billion in 2025 alone, while also rejecting over 2 million app submissions and removing nearly 200 mill…
Mimesis, an open-source data generation library, can be used to create balanced, counterfactual datasets for auditing bias in machine learning models. A hands-on guide demonstrates training a loan approval classifier on …
Python developers can now use type hinting and MyPy static analysis to catch type errors before runtime, reducing production crashes. The typing module allows developers to annotate variable types and create structured s…
MathWorks hosted a webinar demonstrating an end-to-end workflow for designing, training, and deploying AI-based virtual sensor models to embedded processors within a single environment. The session highlighted techniques…
Google's Gemma 4 large language model can now be paired with multi-token prediction (MTP) drafters to generate multiple tokens in parallel, achieving up to three times faster inference without quality loss. The lightweig…
Alibaba’s Qwen3.7-Max autonomously optimized a kernel on unfamiliar hardware for 35 hours, making 1,158 tool calls and achieving a 10x speedup over the reference implementation. The model outperformed competitors GLM 5.1…
Researchers have developed CoReVAD, a training-free video anomaly detection framework that uses a single frozen Vision-Language Model to generate both anomaly scores and temporal descriptions without additional training …
Researchers introduced PathCal, a training-free decoding controller that calibrates reasoning paths in large language models by distinguishing distinct types of reflection markers such as "wait" and "but." The system int…
Researchers have developed Latent Cache Flow (LCF), a method enabling direct model-to-model communication by translating and compressing key-value cache data instead of using text. The approach uses an adapter only 4% th…
A new method for measuring uncertainty in language model outputs, developed by researchers and detailed in a preprint on arXiv, extracts geometric features from the model's internal layer-by-layer processing to outperfor…
Researchers introduced Tensor Cache, a two-level memory system for Transformer models that stores evicted key-value pairs from a sliding-window cache into a compressed outer-product fast-weight memory. The approach uses …
Researchers have developed Multi-Agent Residual In-Context Learning (MARICL), a framework that uses large language model agents to analyze where a base statistical model fails and generate explicit correction terms from …
Researchers have introduced Transcoders, a function-centric framework that decomposes vision-language models into interpretable computational pathways linking image patches to token generation. Applied to Gemma 3-4B-IT, …
New research shows that exact certification of neural networks—determining the smallest set of labeled examples needed to guarantee a learned hypothesis matches the target—becomes exponentially hard under minimal overpar…
Researchers introduced Learned Relay Representations (Relay), a method that enables Masked Diffusion Models to propagate latent information between denoising steps rather than discarding internal computations. The approa…
Researchers have introduced BOHM, a zero-cost attribution method for compound AI systems that extracts hierarchical attribution trees directly from existing routing weights. The method provides multi-resolution attributi…
Researchers introduced NeuroNL2LTL, a neurosymbolic framework that translates natural language into Linear Temporal Logic (LTL) with formal correctness guarantees. The system uses a structure-preserving intermediate repr…
Researchers have developed A-LEMS, a measurement framework that redefines AI energy accounting from energy per inference to Energy per Successful Goal (EpG), aggregating total workflow energy across all execution attempt…
Researchers have introduced EVE-Agent, a self-evolving search agent that requires each training example to include a source-grounded evidence span verifying its answer. The system uses a proposer-solver framework where a…