Machine Learning News

Researchers introduced FinSMART, the first market-aligned reinforcement learning framework for financial sentiment analysis, which directly optimizes sentiment signals using realized market outcomes and improves cumulati…

Researchers introduced Reflective Retrieval Memory (RRM), a framework that improves long-horizon multimodal reasoning by adding reflective experience memory to an entity-centric multimodal memory graph, distilling reusab…

Researchers propose a novel framework using inverted causal self-attention within a transformer architecture for causal discovery in multivariate time series, outperforming existing methods on linear and nonlinear datase…

Researchers at the University of Arizona tested a convolutional neural network for low-order wavefront sensing on the Tiny Observatory for Telescope Optimization (TOTO) optical testbed, as detailed in a paper submitted t…

Researchers from an unnamed institution proposed a structured information extraction framework using LLaMA-3.1-70B to extract six semantic dimensions from financial news, finding that combining these with FinBERT sentime…

Researchers introduced CG-World, a large-scale world-state dataset and protocol derived from industrial computer graphics production pipelines, containing approximately 850,000 temporally aligned segments of 1-5 seconds …

Researchers introduced CaM-Wolf, the first social deduction game agent that integrates multimodal perception and generation, processing video inputs from players and using a causal-aware Reasoner trained via reinforcemen…

Researchers present B1ade, an efficient retrieval-augmented generation (RAG) architecture with a 335M parameter embedding model and a 1B parameter small language model (SLM). B1ade-embed achieves top MTEB scores among su…

A new arXiv study (2607.27564v1) finds that a simple order-vote policy outperforms more complex agentic strategies for multi-image medical visual question answering, achieving 57.89% ± 0.65% final-test accuracy on MedFra…

Researchers propose DualAnchor, a gloss-free sign language translation framework that preserves language priors and improves lexical fidelity, achieving strong performance on PHOENIX-2014T and CSL-Daily. The framework us…

A Baseten inference engineer known as @waterloo_intern published a technical blog post titled '22,580: From GPT-2 to Kimi K3, Explained,' which has garnered 2.4 million views. The post provides runnable PyTorch code trac…

A developer released a shell script that lets users test custom prompts against an already-trained ESP32-S3 model without retraining or rewriting the 15MB model partition. The script tokenizes the prompt, patches the fir…

Researchers at UC Berkeley Sky Lab extended the K-Search evolutionary kernel optimization framework with a CUDA-to-MLX translation layer, enabling automatic transfer of GPU kernel expertise from NVIDIA's CUDA ecosystem t…

A developer has released a one-shot build script that automates the entire pipeline for running a 28M parameter AI model on an ESP32-S3 microcontroller, from cloning the repository to training, exporting, compiling, and …

LangChain 0.3, PyTorch 3.0, TensorFlow.js 5.0, AWS CDK v3, and GitHub Copilot Chat Enterprise are highlighted as top developer tools and tutorials for July 2026. These releases bring significant improvements in LLM agent…

Giles Thomas, in a blog post, reports that deliberately overtraining GPT-2-style models did not improve their performance on instruction fine-tuning evaluations, contrary to his hypothesis that OpenAI's models were overt…

A developer introduced PIVOT, an algorithm that reduces the indexer cost of dynamic sparse attention from O(L²) to O(L²/g) by grouping queries and using a proxy query for a single scan per group. The algorithm exploits t…

Researchers Ivan Martinez-Murillo, Robiert Sepúlveda-Torres, and Juan Pablo Consuegra-Ayala found that transformer-based fraud detection models trained only on English achieve near-perfect in-language performance (F1 ≈ 0…

Researchers at the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security reported that fine-tuning small language models on synthetic cybersecurity data yields mixe…

A developer implemented batch normalization, layer normalization, and group normalization from scratch and compared their performance on a simple multi-layer perceptron (MLP) classifying the MNIST dataset, finding that e…