Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced B-Spline Embedded Structure Learning, a framework that improves 3D tooth segmentation by embedding dental arch structure into the model. On the 3DTeethSeg22 benchmark, the method achieves state-of-…
Researchers propose Data-DPO, a target model-oriented data selection method for supervised fine-tuning that uses one-step probing to capture target-model-aware data preferences and combines them with external quality sco…
A new study using connected vehicle telemetry data from Greater Sydney, Australia, found that ARIMA, a classical time-series model, achieves the lowest mean absolute error (MAE: 162.21) in forecasting near-miss risky dri…
A new arXiv paper introduces Strategic 16K, a leakage-controlled corpus of 16,000 diplomatic cables from the WikiLeaks Public Library of US Diplomacy (PlusD), and benchmarks six model architectures for automatic document…
Researchers propose RoBell-RVFL, a robust generalized bell random vector functional link network that uses a dual-strategy, sample-level weighting mechanism to handle class imbalance and label noise, preserving minority …
Researchers propose MASS, a hierarchical data selection method that uses manifold coverage and sparse feature coverage to improve LLM post-training efficiency. In experiments on Vision Flan and LLaVA-CoT, MASS outperform…
Researchers propose Mr.Dec, a multimodal Transformer Decoder that models hospital admissions as daily sequences of EHR updates and chest X-ray findings, achieving state-of-the-art performance on MIMIC-IV and MIMIC-CXR da…
A new study from arXiv (2608.16931v1) introduces SW-ProxyCE, a query-free attack framework that exploits public EEG foundation encoders to generate adversarial examples that transfer to private downstream models, achievi…
Researchers propose MultiSigBERT, a multimodal sequential survival model for oncology that integrates free-text medical reports, numerical measurements, and structured variables using path signature representations. On a…
A new arXiv paper (2608.17087v1) introduces telos, a PyTorch library providing an algebra-generic, differentiable evaluation engine for linear temporal logic, enabling gradient-based training of softly-valued systems suc…
A new arXiv study (2608.17091v1) evaluates six deep learning models for day-ahead electricity price forecasting across multiple markets, using the Germany-Luxembourg (DE-LU) bidding zone 2024 as the test set. The authors…
Researchers propose a logic-based framework for node classification in Simple Graph Convolution (SGC) networks that extracts global logical rules from minimal abductive explanations, achieving compact rules with high fid…
KernelArc, a multi-agent framework for autonomous GPU kernel optimization, achieved first-place rankings on representative L1, L2, Quantization, and FlashInfer tasks at the public SOL-ExecBench leaderboard snapshot recor…
Researchers at arXiv (2608.17170v1) introduced an automated approach using Large Language Models (LLMs) in an agentic check-fix-verify loop to synthesize executable Python feature extractors for constraint satisfaction p…
Researchers propose PlanPO, a group planning-aware policy optimization method that improves multi-turn agentic large language models by distinguishing advantages among successful trajectories based on interaction efficie…
Researchers propose TraceSQL, a lightweight verification model that uses 67 explicit diagnostic features to estimate whether generated SQL correctly answers a user question without ground-truth references. On BIRD develo…
Researchers propose CoAL-RAG, a complexity-aware legal retrieval-augmented generation method that adaptively routes retrieval strategies based on question complexity, improving answer quality and efficiency. On Chinese l…
A new framework called WER (Write, Execute, and Refine) trains a Skill Optimizer to improve tool-using agents' performance by learning from execution feedback, achieving a 7.80-point average Pass@1 improvement over the n…
A developer created a multilayer perceptron (MLP) from scratch, manually computing all forward and backward passes with a calculator to deepen understanding of neural networks. The project, detailed in a technical blog p…
A developer built a transformer from scratch and computed a full forward pass by hand to understand the architecture introduced in the 2017 paper 'Attention is All You Need' by Vaswani et al. The transformer, similar to …