Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Cloudflare has introduced spend limits for its AI Gateway, allowing users to set cost-based budgets that block further requests with a 429 response when cumulative spending reaches a defined threshold within a time windo…
TorchRec's KeyedJaggedTensor, designed to efficiently combine sparse features in recommendation systems without padding, introduces GPU-CPU synchronization that degrades system performance. The data type's output shape c…
Sapient Inc. open-sourced HRM-Text in May 2026, a 1.15 billion parameter text generation model based on the HRM architecture. Trained on roughly 40 billion tokens—up to 1,000 times less data than comparable models—it ach…
A tech writer fine-tuned a local LLM to replicate the style of 1980s and 1990s software documentation, using a 37-million-word corpus of scanned Microsoft manuals from the Bitsavers archive. The experiment, conducted on …
A new raw-waveform diffusion model called WavFlow has achieved audio fidelity matching or exceeding that of autoencoder-based pipelines, eliminating the need for latent compression. On the VGGSound benchmark, WavFlow's F…
Megan Lawther is developing Guardian AI, a forensic diagnostic decision-support system designed to improve clarity in complex clinical pathology. The system uses Google's MedGemma, TensorFlow, and Edge AI to cross-refere…
Google released Magenta RealTime 2, an open-weights AI model and real-time inference engine that enables live, low-latency music generation on a MacBook. The model responds instantly to MIDI, audio, and text inputs, achi…
Researchers developed a variance-aware reward framework using Group Relative Policy Optimization (GRPO) to improve heart-focused medical question answering in large language models. The approach, which replaces tradition…
Researchers introduced generic triple-latent sequence models that maintain a running token state and compressed pair-memory pathway to capture higher-order token interactions without benchmark-specific parsing. The tripl…
Researchers have developed TTT-RTL, the first per-design test-time training framework that uses reinforcement learning to optimize hardware designs generated by large language models. The system closes the loop between a…
Researchers introduced VideoKR, a large-scale training corpus of 315,000 video reasoning examples over 145,000 expert-domain videos designed to strengthen knowledge- and reasoning-intensive video understanding. The team …
Researchers have developed CVT-RL, a reinforcement learning algorithm that uses policy-conditioned counterfactual credit assignment to reduce unsupported evidence chains and shortcut actions in long-horizon language agen…
Researchers have developed ReGeN, a reference-guided generative pipeline that creates synthetic multivariate time series data by decomposing observed sequences into periodic backbones, stochastic residuals, and cross-var…
Researchers developed and evaluated deep learning models for automated age-related macular degeneration (AMD) staging using OCT and OCT angiography data from 271 participants. A biomarker-based model achieved the highest…
Researchers developed a sensor-guided adaptive contrastive learning framework that uses privileged LiDAR data during training to teach visual encoders to focus on navigation-relevant geometry rather than scene-specific a…
Researchers have developed ReasoningFlow, a framework that maps the non-linear discourse structures of large reasoning model (LRM) traces into directed acyclic graphs (DAGs) to improve evaluation and monitoring. Through …
Researchers have developed LANTERN, a lightweight memory layer that recovers facts lost when large language models compress long conversations, achieving 78.3% recovery of verifiable facts without requiring any LLM calls…
Researchers introduced a two-stage early failure alerting system for dialogs and LLM-agent trajectories that learns from sparse turn-level evidence rather than assigning terminal labels to every prefix. The attention-bas…
Researchers have developed BUMP, a self-supervised framework that trains large language models to generate personalized user profiles without requiring labeled data from downstream tasks. The system uses a bidirectional …
Researchers at arXiv propose a hybrid pre-training objective for language models that combines a Joint Embedding Predictive Architecture (JEPA) latent-space prediction loss with masked language modelling (MLM). Pre-train…