Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
YouTube's 2026 AI-powered video summarization feature signals a broader shift toward machine understanding, now mirrored in enterprises where AI agents analyze documents, contracts, and records with similar intelligence.…
An AI agent evaluation harness is a repeatable test system that runs realistic tasks, captures every step, scores outcomes, and turns failures into regression tests. It helps teams move beyond demo success to production …
Lore, an open source version control system designed for scalability, has been released to help developers manage large-scale projects efficiently. The system aims to provide a more efficient and scalable alternative to …
Multiple independent researchers are seeking endorsements on arXiv to submit papers on machine learning topics, including a discrete choice model for LLM alignment, a control-theoretic approach for long-form generation, …
A developer built an interactive 2026 World Cup predictor dashboard using LightGBM and Streamlit, deployed for free on Streamlit Community Cloud. The app features a bracket visualization with custom CSS and a GitHub Acti…
Meta's Advantage+ Shopping Campaigns (ASC) report a single blended ROAS that often overstates true value by mixing new and returning customers and relying on Meta's own attribution. To measure ASC causally on Shopify sto…
Profile v2.1.4, a physics-aware optimizer for vLLM inference servers, achieved a 15x throughput increase from 31 to 470 tok/s and a 93% cost reduction on an NVIDIA A100 GPU. The tool uses roofline math to compute theoret…
Docker solves the 'it works on my machine' problem for AI engineers by packaging all dependencies—OS, Python, packages, code, and config—into a single portable image. A typical AI project has multiple dependency layers (…
Researchers at arXiv propose a framework for selecting the most informative comparison pairs in preference-based post-training of large language models, showing that strategic pair selection can improve sample efficiency…
Researchers derived a three-force decomposition of AdamW training dynamics explaining Weibull weight-scale parameter evolution in transformers, finding alignment force dominates growth. A spline displacement method recov…
Researchers propose a method to learn asynchronous denoising schedules for multi-representation diffusion models, improving visual synthesis. On ImageNet 256x256, their approach achieves FID 1.05 with 4x less training th…
FocusOnFun team's Vortex system achieved 90.5% in the Preliminary Round and 'Excellent' overall performance with 'Outstanding' QA results at the Ho Chi Minh City AI Challenge 2025. The multimodal video retrieval system i…
Researchers introduced Emyx, a 140M-parameter conditional flow matching model for all-atom protein generation, which outperforms larger models like RFdiffusion3 on enzyme design benchmarks while requiring only 682 GPU-ho…
Researchers introduced VERITAS, a zero-shot framework for formal theorem proving that leverages rich verifier signals through a two-phase protocol combining Best-of-N sampling and critic-guided Monte Carlo tree search. V…
Researchers introduced a continuous relaxation of the determinantal point process (DPP) maximum a posteriori (MAP) problem for diversity-aware data selection, reformulating it as a nonlinear eigenvalue problem (NEPv) on …
Researchers introduced the Integral Transform Network (ITNet), a unified architecture that subsumes convolution, attention, and recurrence as special cases of a learnable integral transform. ITNet matches or exceeds spec…
Researchers introduced LooseControlVideo, a framework that uses sparse, oriented 3D boxes as a proxy for spatial blocking in text-to-video generation, enabling intuitive control over layout and trajectory. Fine-tuned on …
Researchers introduced SLARouter, an online routing algorithm for large language model (LLM) applications that learns cost-optimal policies from sparse user feedback while guaranteeing Service Level Agreement (SLA) compl…
Researchers propose Conditional-Composition Domain Match (CCDM), a training-free metric family that predicts the utility of synthetic data for object detection, achieving a Spearman correlation of 1.0 with YOLOv8 perform…
Researchers propose a one-shot novel view and pose human image synthesis method using a conditional denoising diffusion model guided by 3D human priors. The approach outperforms existing techniques on public datasets and…