Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced SpeechDx, a large-scale benchmark for clinical speech AI spanning 12 datasets and 27 tasks across diverse health conditions, designed to evaluate generalization by structuring tasks according to di…
Researchers tested whether language models can independently discover the concept of zero through arithmetic generalization. GPT-2-sized models failed at test time regardless of language pretraining, but improved after t…
Researchers at arXiv have identified a conflict signature in language models that distinguishes deceptive outputs from honest errors, achieving 100% accuracy in detecting lies across multiple models including GPT-2, Qwen…
Researchers propose negative token filtering, a method enabling stable single-rollout training for critic-free reinforcement learning in large language models, outperforming group-based techniques on agentic tasks.
Researchers introduced Finslerian graph neural networks, a new architecture that estimates the Finsler Laplacian on point clouds and converges to the true operator on manifolds. This approach extends graph neural network…
Researchers developed a diffusion-based model that generates irregular clinical time series by jointly modeling laboratory values and their observation patterns, using the MIMIC-III-derived DACMI benchmark. The approach …
Researchers introduced a geosteering framework that combines particle filtering with reinforcement learning to optimize well trajectory decisions under geological uncertainty. The framework evaluates three decision-makin…
Researchers have theoretically analyzed how deep transformers represent hierarchical structures in language, constructing models whose depth grows linearly with grammar depth and whose neuron count scales with derivation…
McKinsey's June 2026 analysis finds that 75% of advertisers expect AI to increase total media spend, with one-third forecasting at least a 10% ROAS increase. Over 50% say AI has reshaped discovery and consideration, whil…
A developer demonstrated that gzip, a standard file compressor, can perform rudimentary language modeling by exploiting the compression-prediction equivalence. Using beam search over byte sequences, gzip generates text t…
Oxlo.ai demonstrates how few-shot learning with large language models enables domain-specific classification without weight updates, using in-context learning to infer patterns from exemplars. The company highlights its …
Ax, a new open-source tool, monitors coding agent sessions to identify repeated mistakes and generate repo-specific fixes. Built by Necmttn, it runs locally with SurrealDB and aims to improve agent performance by turning…
LessWrong published an essay on April 21, 2024, proposing that humans may be more over-parameterized than AI systems, framing this as a key difference between deep learning and human intelligence.
Google launched the TPU Developer Hub, a centralized educational resource for guidance on Google Cloud TPU infrastructure and software stack. The hub covers the full developer lifecycle from pre-training to inference, fe…
A researcher proposes that human brains minimize bias through extreme overparameterization and high-learning-rate training on small diverse datasets, while LLMs minimize variance. This 'catapulting' hypothesis could expl…
Imprint's engineering leader revises leadership rules for the AI era, emphasizing that migrations can be done by individuals in 10% of the time, processes should be optimized for AI agents, and durable teams with domain …
A developer debugging a JAX/Flax NNX training loop discovered that the loss was stuck at 10.82, indicating the model was performing no better than random guessing. The issue was traced to the training loop's plumbing rat…
A developer explains that by 2026, data pipelines must be redesigned for AI agents as primary consumers, requiring context-rich metadata, lineage tracking, and embedding outputs. The post introduces 'agentic data enginee…
MarkTechPost published a tutorial on building memory-efficient Transformers using xFormers, covering packed sequences, grouped-query attention, ALiBi, SwiGLU, and causal attention. The guide demonstrates how to achieve f…
Email teams frequently argue about campaign performance not because of bad data but because they evaluate results through different, unspoken lenses: marketing focuses on engagement, growth on conversion, and founders on…