Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers introduced a visual analytics framework for exploring attention dynamics in diffusion models, enabling structured analysis of token-level cross-attention maps across generation steps. The framework integrates…
Researchers propose a fuzzy-logic extension of Answer Set Programming (ASP) to bridge numerical data and qualitative reasoning, using learning-based membership functions and semantically enriched predicates. The framewor…
A new study on agentic AI policy repair in a hotel-pricing simulator shows that LLM-based editors can nearly match benchmark performance using only region-level diagnostic feedback, achieving RevPAR 108.47 vs. benchmark …
Researchers developed a semi-automatic pipeline that converts CT-based cardiac segmentations into simulation-ready meshes in minutes, preserving anatomical and topological consistency. Validated on 58 healthy cardiac CT …
Researchers introduced Sparse-Reslim, a plug-in routing module that reduces computational cost in ViT-based weather forecasting by processing only 25% of spatial tokens through expensive transformer blocks while maintain…
Researchers revised the GestaltMML paper on arXiv, describing a Transformer-based multimodal model that combines frontal facial images, demographics, and clinical text to improve rare genetic disease diagnosis accuracy. …
Researchers at a university found that selectively applying monocular depth priors from Depth Anything V2 improves sparse-view neural reconstruction in driving scenes, with Splatfacto gaining 1.029 PSNR and reducing RMSE…
Researchers used interpretable machine learning to predict Parkinson's disease motor severity from QSM and fMRI features, achieving 45.4% variance explained and 75% of predictions within 5 points of clinical scores. The …
Researchers introduced VulcanVoxel, a spatial affordance model that learns 3D blade insertion feasibility in cluttered stowing environments using a masked autoencoder over occupancy fields. Trained on 10,000 real warehou…
Researchers propose a hybrid block diffusion language model (BDLM) combining Mamba and attention mechanisms that restricts reverse Mamba scans to the active denoising block, enabling exact caching across blocks. At 87M p…
Researchers developed a two-stage U-Net framework for efficient pedestrian-level wind prediction across urban morphologies, using the UrbanTALES dataset. The first stage predicts wind fields patch-by-patch, while the sec…
Researchers proposed DMKGC, a conditional diffusion-guided knowledge transfer framework for multi-domain knowledge graph completion, achieving a 4.3% average MRR improvement over state-of-the-art methods. The framework t…
Researchers propose TR-RAG, a teacher-regularized reinforcement learning method for cross-lingual retrieval-augmented generation that addresses language drift and unreliable evidence use. The method combines reward optim…
Researchers at arXiv propose a formal model of internal pluralism showing that local pairwise comparisons fail to capture global priorities like proportionality and egalitarianism, and can cause behavioral distortions wh…
Researchers propose Trajectory-Aware Commit Gating (TACG), a training-free decoder for diffusion language models that uses trajectory-aware signals to decide when to commit tokens, improving accuracy and efficiency on co…
Researchers propose ALORE, a scalable and domain-robust estimator for the size of the largest overlap between tables, addressing limitations of the state-of-the-art Armadillo. ALORE reduces mean absolute error by up to 5…
Researchers studied online adaptation of discrete diffusion models for molecular optimization, finding that combining acquisition, reward shaping, debiasing, replay, and validity control outperforms offline fine-tuning a…
Swipe Cleaner, an iOS app built on the OpenNomos ecosystem, processes all photo cleaning tasks on-device using Apple's Core ML and Vision frameworks, ensuring no user data leaves the device. The app employs a Tinder-styl…
SGLang development is being augmented with agent-assisted workflows that encode procedural engineering knowledge into executable skills, covering LLM serving, GPU kernels, diffusion pipelines, and production incident han…
Researchers introduced Decomposer, a post-training framework that decompiles symbolic music (MIDI) into editable Strudel programs. Using synthetic data and reinforcement learning, the system outperforms closed-source LLM…