Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A developer built a 5-layer, 512-wide TinyStories language model that runs natively on Apple's M4 CPU by treating ARM Neon instructions—including XOR, popcount, and SDOT—as trainable architectural primitives rather than …
A historical survey traces the first physical and computational reinforcement learning machines built between 1948 and 1954, beginning with Norbert Wiener's 1948 Cybernetics and its negative-feedback principle, which the…
A developer identified and fixed a bug in TensorFlow's lookup table kernels where LookupTableExportOp bypassed signature verification, causing a hard CHECK_EQ assertion failure and process-level SIGABRT instead of a catc…
Edge0-AI has open-sourced Edge0, an Apache 2.0 streaming inference engine that memory-maps sparse mixture-of-experts weights from SSD so a 35B model runs in roughly 2.9 GiB of peak active memory. The project ships two 4-…
A developer explains that generative models are not designed to memorize datasets but to approximate the unknown probability structure behind observed samples. The writeup outlines how a parameterized Model Distribution …
A multi-stage rule-chaining framework solved 230 of 240 ARC-AGI-2 test tasks and exceeded 95 percent overall accuracy, according to an arXiv paper (2609.10654v1) presenting the system. The framework combines a determinis…
A study posted to arXiv (2609.10657v1) mapped the memorization-to-generalization boundary across 384 configurations of two-hidden-layer MLPs on modular arithmetic, fitting a power-law scaling relation for grokking onset …
A new arXiv paper (2609.11061v1) proposes belief-shift branching, a fork-placement method for tree-structured reinforcement learning with verifiable rewards that forks a chain just before the step where the model's conse…
A study of 70,500 X messages tied to securities class actions from 2002 to 2025 found that benchmark agreement between financial sentiment tools and human labels establishes semantic validity but does not by itself deter…
A study posted to arXiv (2609.11452v1) introduces RouteRepair, an instance-level failure diagnosis and targeted repair method for LLM-based automated heuristic design in routing optimization. On the traveling salesman pr…
Researchers proposed CoMA-DiT, a bidirectional cross-modal Diffusion Transformer for latent augmentation that treats paired modalities as mutual generative supervision, according to an arXiv paper (2609.11341v1). In expe…
Researchers introduced ActMap, a white-box representation that compresses a large language model's generation-time hidden-state trajectory into a fixed 12 × 32 × 128 tensor occupying 96 KiB, enabling single-pass uncertai…
A new arXiv paper (2609.11199v1) presents an AI-driven, culturally sensitive stress detection and wellness support system for Pakistani university students, built on a Random Forest model trained on 1,100 validated stude…
COBRA-Skills, a framework introduced in arXiv paper 2609.11682v1, formulates LLM agent skill optimization as budgeted sequential optimization over a dynamically evolving candidate space, coupling contextual-bandit-guided…
Researchers introduced RAMamba-Net, a reliability-aware Mamba-based multimodal fusion network for auditory attention decoding (AAD) that combines electroencephalography (EEG) and electrooculography (EOG) signals, accordi…
A new arXiv paper (2609.11709v1) proposes Bayesian backward reasoning as a label-free anchor for multi-agent collective decision-making, using Jensen-Shannon divergence to rank LLM agents by cross-path consistency. Evalu…
A controlled study submitted to arXiv on 9 Sep 2026 found that moderate LoRA ranks are the most efficient setting for diffusion model fine-tuning, with rank 4 achieving the best DDPM FID of 124.1380 on CIFAR-10 and rank …
Researchers submitted CascadeLUT, an information-ordered streaming inference framework for bandwidth-constrained FPGAs, to arXiv on 1 Aug 2026. CascadeLUT partitions input features into ordered subsets and progressively …
OpenAI posted an on-site San Francisco job listing for a Researcher, Safety Training, National Security role paying $380,000 to $500,000 per year, a range the listing says sits 87% above the $236,000 median for Core ML r…
A developer's experiment testing a full hierarchical Pitman-Yor language model with Gibbs sampling and inferred hyperparameters found it fails to match the data-scaling slope of a small transformer, gaining only +0.008 t…