Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have developed MedExpMem, an experience memory framework that enables medical vision-language models to accumulate differential diagnosis expertise from their own diagnostic failures. The system, which mirror…
A new study of small language models reveals that chain-of-thought prompting for arithmetic relies on a positional shortcut: the model copies whichever number appears last before the answer delimiter, regardless of the l…
Researchers have developed FederatedRSF, a Python package enabling multi-center survival prediction using federated random survival forests without sharing patient-level data. The method aggregates locally trained surviv…
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 …
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 developed a graph neural network that models alignment topology between reference documents and LLM outputs to detect hallucinations, achieving state-of-the-art results on four datasets. The method outperform…
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…
New research formalizes fundamental computational limits as design specifications for trustworthy AI systems, proving that transformer architectures have a fixed accuracy ceiling—the Deterministic Horizon—determined sole…
Researchers introduced Reflection-Augmented Scaling (RAS), a method that uses execution error messages from databases to improve Cypher query generation through in-context learning. Testing across three Neo4j datasets an…
A study of fMRI data from 112 English, Chinese, and French speakers found that brain-LLM alignment is driven by training-language dominance, not an inherent property of English. A Chinese-dominant model reversed the alig…
Researchers have developed the GazeBehavior Annotation Toolkit (GBAT), a deep-learning-based system that automates the synchronization and annotation of egocentric eye-tracking and video data from child-caregiver interac…
Researchers have developed LQ-rPPG, a label-quantized coarse-to-fine learning framework that improves remote photoplethysmography (rPPG) estimation from facial videos by reducing noise in training labels. The framework u…
Researchers tested seven large language models on their ability to infer employee expertise from 27,188 Slack messages, finding that Gemini 2.5 Flash achieved the lowest estimation error at 21.13% mean absolute error. Th…
Researchers at the German Cancer Research Center (DKFZ) developed a new "Verified Tracking" paradigm for tumor lesion tracking across serial CT scans, achieving first place in the MICCAI autoPET IV challenge. The method …
Researchers have developed CoMoGen, a controllable video generation framework that creates realistic motion dynamics and interactions from a single binary mask sequence and an input image. The system uses a lightweight M…
A new computational study provides causal evidence that large language models acquire knowledge of unacceptable grammatical constructions through statistical preemption, a mechanism previously theorized in Construction G…
Researchers have developed SciAtlas, a large-scale knowledge graph integrating over 43 million papers across 26 disciplines, 157 million entities, and 3 billion triplets to serve as a structured cognitive map for automat…
Researchers decomposed GPT-2 XL and Llama-3.1-8B into 16,000 to 32,000 interpretable features per layer using sparse autoencoders, finding that semantic features alone recovered 94% of peak brain-response encoding perfor…
A developer has published a conceptual blueprint for AURORA, a low-energy cognitive organism architecture that operates without transformers or token prediction. The system uses sparse predictive microfields, episodic me…
A new glossary from Hugging Face aims to clarify the terms "harness" and "scaffold" in AI agent development, following confusion among researchers at the ICLR 2026 conference. The glossary defines a "harness" as the exec…