Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers developed Metric Match, a subset selection method that estimates LLM judge reliability from limited human annotations. The method achieved a win-rate of 0.838 against random selection across 15 datasets, redu…
Researchers introduced VigilFormer, a video anomaly detection framework combining deformable spatio-temporal attention with causal temporal modeling, achieving state-of-the-art AUC scores of 87.83% on UCF-Crime, 97.21% o…
Researchers introduced relational structural causal models (RSCMs) to enable AI to reason causally about environments with varying objects and relations. They defined relational causal graphs and derived symbolic identif…
Researchers propose QPILOTS, a method that steers flow-matching and diffusion policies at inference time by projecting noisy intermediate states to clean action estimates for critic gradient computation. QPILOTS achieves…
Researchers introduced MMLongEmbed, the first comprehensive benchmark for evaluating multimodal embedding models in long-context scenarios. The benchmark includes four retrieval tasks across text, document, and video mod…
Researchers formalized embedding model routing as an adversarial contextual linear bandit with low-rank experts, identifying a log-quadratic policy class for efficient online learning. They proposed the Hypentropy Policy…
Researchers introduced IRTS-ToolBench, a benchmark of 1,700 questions across 10 task types and 13 domains, to evaluate large language models and AI agents on irregular time series question answering. The benchmark addres…
A new study compares 19 graph neural network layer types for driving trajectory prediction, finding that ARMA, Chebyshev, and topology-aware layers outperform others. The research provides design principles such as sum-b…
Researchers propose SERAF, a semantics-enhanced retrieval-augmented time series forecasting framework that retrieves both historical time series segments and their self-generated textual descriptions to improve predictio…
Researchers propose sub-semantic image segmentation, a new category that partitions images into stable appearance patterns described by language rather than naming whole objects. They introduce DETECTURE, a system that o…
Researchers introduced DR-DCI, a retriever-steered Direct Corpus Interaction framework that dynamically expands a local workspace for agentic search over large corpora. On Browsecomp-Plus, DR-DCI achieved 71.2% accuracy,…
Researchers developed a high-throughput 3D behavioral phenotyping framework integrating deep learning object detection with binocular stereo vision for real-time monitoring of juvenile tilapia. The system automates body …
Researchers introduced a foundation model-driven framework for cross-modal representation alignment between CT imaging and longitudinal EHR data, improving time-to-event prediction across tasks and institutions. Fusion s…
Researchers introduced Physics-conforming Latent Twins, a framework for learning surrogate models that respect physical laws like conservation and dissipation. The method constrains latent dynamics to preserve structural…
A new paper from arXiv argues that world models for embodied decision-making should be evaluated based on their utility for counterfactual reasoning, planning, and policy optimization rather than visual realism. The auth…
Researchers introduced the Membership Inference Test (MINT) Demo 2, a framework to detect whether specific data were used in training machine learning models, achieving up to 90% accuracy in tests on face recognition mod…
Researchers from an undisclosed institution introduced Convolutional Nearest Neighbors (ConvNN), a unified framework that shows convolution and self-attention are special cases of k-nearest neighbor aggregation. ConvNN c…
A study from arXiv finds that linear regression outperforms the naive random walk in forecasting the monthly USD/CAD exchange rate, while machine learning ensemble models show only marginal differences. The research, usi…
Researchers propose replacing the inner product score in sparse autoencoders with a learned blend of cosine similarity and input magnitude, finding that cosine-scored SAEs learn more human-recognizable features and avoid…
Researchers introduced a temporal difference (TD) objective for diffusion models that enforces cross-time consistency along the denoising trajectory, improving sample quality especially with few sampling steps. The metho…