Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A new arXiv study (2608.14114v1) finds that an AlphaZero-inspired reinforcement learning approach using Monte Carlo Tree Search achieves 98.43% peak survivability in power grid topological control, significantly outperfo…
Researchers developed the Smart Routes platform to compare exact, heuristic, and deep learning algorithms for the Capacitated Vehicle Routing Problem with Time Windows (CVRPTW). For problems of size 50, deep learning and…
Researchers propose the Structure-Guided Spatiotemporal Attention Graph Neural Network (SGSAN) for traffic flow prediction, achieving state-of-the-art accuracy while providing built-in interpretability. The model learns …
Researchers at an unnamed institution applied a modified JAMPR deep reinforcement learning model to solve pickup and delivery problems with capacity and time window constraints (CPDPTW), achieving fast optimal solutions …
A study from arXiv (2608.14186) finds that a two-hidden-layer Deep Boltzmann Machine (DBM) matches the Autoencoder baseline on UCI Bank Marketing and statistically beats it on NSL-KDD, while outperforming seven other bas…
Researchers introduced Attention-Aware Transform Coding (AATC), a KV cache compression method that reduces memory use by approximately 5.8x while maintaining near-lossless accuracy on models like Llama-3.1-8B-Instruct an…
Researchers released CytoBERT, an open-source foundation model for single-cell cytometry data, pretrained on 15 human datasets with over 50 million cells to learn transferable inter-marker relationships. Fine-tuning for …
Researchers proposed new convex losses for Support Vector Machines (SVM) and shallow neural networks, applied to binary classification, and solved the primal SVM problem using Particle Swarm Optimization. Experiments on …
A new training-free method for multi-modal trajectory prediction achieves accuracy comparable to a 57M-parameter transformer while requiring no GPU and zero learned parameters, according to a paper posted on arXiv (2608.…
Researchers propose a two-stage framework for cross-tabular data generation that converts heterogeneous tables into standardized statistical tables and uses a diffusion transformer to generate synthetic data, achieving h…
Researchers propose sMuon, a method that adapts the Muon optimizer for low-rank fine-tuning by approximating the orthogonalization step via linearization and least-squares, using only matmul operations. In experiments ac…
Researchers introduced Rollplex, a runtime that enables cross-phase GPU spatial sharing for vision-language model post-training, achieving 1.23x–1.30x speedup over serial colocation and 1.57x–2.24x over disaggregation on…
Researchers propose RecipeNet, a hierarchical Transformer architecture for recipe data that encodes field-level interactions within steps and sequential dependencies across steps, outperforming existing tabular models on…
Researchers introduced a visual-interactive system that explains deep learning predictions for computer network traffic classification using aggregated class activation maps, addressing the challenge of diverging pattern…
Researchers introduced BCIJelly, a unified Python ecosystem integrating 18 curated brain-computer interface (BCI) datasets, 15 benchmark decoders, and 80 reusable modules, plus an automated architecture search (AAS) and …
A Hacker News user proposed an RL environment to improve frontier AI models' math explanations, where a large model teaches a small 0.5-1B parameter model to solve hard problems, with rewards based on the small model's s…
A developer demonstrates how to use MCP's Resource primitive to synchronize knowledge graphs across concurrent LangGraph agent conversations, preventing context loss in support bots. The approach defines a shared Knowled…
Artificial intelligence is helping patients solve medical mysteries, according to a Wall Street Journal report. The technology analyzes complex symptoms and medical histories to suggest rare diagnoses that doctors may ha…
LabLLM, a free native macOS app built with SwiftUI and Apple MLX, lets users train small GPT-style Transformer and LLM models from scratch on Apple Silicon (M1 or newer, macOS 14+). The beta supports pretraining, SFT, Lo…
Linux 7.2, released by Linus Torvalds on August 16, introduces cache-aware load balancing for chiplet-based servers like AMD EPYC and Intel Xeon 6, but the feature is opt-in via CONFIG_SCHED_CACHE. The kernel also improv…