Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have developed RadarSim, a unified differentiable renderer that uses multimodal neural fields to generate high-resolution Doppler radar range images by leveraging camera data. The system addresses the low spa…
Researchers introduced MM-CreativityBench, a new benchmark designed to test whether large multimodal models can solve open-ended, physically grounded problems by repurposing objects in non-obvious ways. The study found t…
Researchers have demonstrated that retrieval-augmented generation (RAG) can be understood as an in-context optimization process, where a single linear self-attention layer performs a gradient-descent step on a unified RA…
Researchers have developed Geometry-Aware Representation Denoising (GARD), a framework that uses diffusion-based restoration within a feed-forward 3D reconstruction model's feature space to improve multi-view 3D reconstr…
Researchers have developed DuoGesture, a neuro-inspired dual-stream system that separately generates semantic and beat gestures for co-speech animation. The model uses a stochastic gate to coordinate when semantic gestur…
Researchers introduced SPEAR (Sandboxed Prompt Engineer with Active Roll-back), a code-augmented agentic optimizer that autonomously rewrites prompts using a Python sandbox for structural error analysis, outperforming ex…
Researchers have developed Token-to-Mask (T2M) remasking, a training-free replacement for Token-to-Token (T2T) editing in discrete masked diffusion language models like LLaDA. The method resets suspected erroneous tokens…
Researchers have introduced Neural Bayesian Sequential Routing (NBSR), a framework that models neural inference as active evidence accumulation over a hierarchical Directed Acyclic Graph using a Dirichlet-Categorical con…
Researchers introduced EnterpriseMem-Bench, a multi-turn Text-to-SQL benchmark of 300 sessions and 1,400 queries built from three enterprise domains, to evaluate how five frontier AI models handle memory across conversat…
Researchers have developed Self-Verified Distillation, a method allowing large language models to improve themselves using only unlabeled prompts without external feedback. The approach, tested on Qwen3 models across mat…
Researchers have proven a finite-sample bound on the approximate max-information of differentially private stochastic gradient descent (DP-SGD) that scales at most linearly with dataset size, matching classic results for…
Researchers developed HRVConformer, a deep learning architecture that classifies neonatal hypoxic-ischemic encephalopathy (HIE) by directly processing raw heart rate signals, achieving an AUC of 83.23% and accuracy of 74…
AirCast-SR, a new foundation model for atmospheric super-resolution, downscales global AI weather forecasts from 28-kilometer to 1-kilometer horizontal resolution at hourly intervals, producing 67-hour forecasts of eight…
A new study finds that vector representations exported from large language model summarization systems can leak sensitive information, even when source documents remain access-restricted. Researchers auditing clinical di…
Researchers introduced LongAV-Compass, a benchmark for evaluating minute-long audio-visual generation across text, image, and video conditioning modalities. The benchmark contains 284 test cases and assesses over 20 fine…
A new study reveals that large language models hallucinate on structured knowledge tasks due to systematic internal failures, not random errors. Researchers found that attention mechanisms disproportionately focus on sho…
Researchers have developed RICE-PO, a policy optimization framework that converts retrieval interactions into localized learning signals for training reasoning-based retrieval agents. The framework addresses the credit-a…
MiniMax released the M2 series of Mixture-of-Experts language models, featuring 229.9 billion total parameters with only 9.8 billion activated per token, designed for agentic deployment. The models use agent-driven data …
Researchers introduced AgingBench, a longitudinal benchmark designed to measure how AI agents degrade over time after deployment. The study found that agent reliability declines through four distinct aging mechanisms—com…
Researchers have introduced GEM (Geometric Entropy Mixing), a framework that reformulates LLM data curation as a variational problem on a hypersphere to overcome flaws in human taxonomies and Euclidean clustering. By dec…