Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have developed representation-conditioned diffusion models that generate synthetic training images by conditioning on learned representations from DINOv2, DINOv3, and CLIP, achieving a 10.76 percentage point …
Researchers have introduced Tensor Memory, a lightweight module that gives Transformer models a fixed-size recurrent 3D memory tensor to handle long video sequences. The module writes tokens into a voxel grid using a dif…
Researchers introduced RULER, a set of representation-level verification metrics for machine unlearning, after finding that current output-level tests can pass even when models retain forgotten data internally. The oracl…
A new data-free knowledge distillation framework called Gradient Transformer enables organizations with limited computational resources to improve large language models (LLMs) using private data without sharing that data…
Researchers have developed AGFlow, a spatiotemporal flow-matching model that fuses asynchronous Sentinel-1 radar and Sentinel-2 optical satellite data to remove clouds and reconstruct missing time-series frames. The mode…
Large language models fundamentally cannot perform causal discovery from observational data due to a mathematical limitation proven in a new study, which shows that fine-tuning and other learning methods produce predicto…
A study evaluating FP4 quantization-aware training (QAT) for real-time anomaly segmentation in brain tumor detection found that architecture choice, not QAT recipe, most determines model quality. The Swin Transformer dem…
Researchers have developed MERIT, a multimodal pretraining framework that uses information theory to learn electrocardiogram (ECG) representations by jointly preserving signal structure and integrating clinical semantics…
A preliminary clinical validation of the Melanoscope AI mobile dermoscopy clinical decision support system, conducted across four "Melanoma Day" screening sessions in Orel, Russia from June 2025 to April 2026, found no f…
Researchers have developed BioELX, a two-stage cross-lingual biomedical entity linking framework that requires no task-specific annotated training data. The system improves candidate retrieval by enriching SapBERT with m…
Researchers have proposed a unified full-lifecycle governance framework for cyberbullying on social media, shifting from passive, post-level detection to integrated, continuous, and proactive moderation. The framework sy…
Researchers in Japan fine-tuned the LLaVA-1.5-7B vision-language model on up to 4,000 bridge damage images to automate damage assessment and repair priority scoring, addressing significant inter-rater variability in mand…
The 10th Affective & Behavior Analysis in-the-Wild (ABAW) Workshop and Competition, held at CVPR 2026, introduced new challenges for multimodal human-centered AI, including emotional mimicry intensity estimation, ambival…
Researchers have introduced SegWorld, a segmentation model that uses a multi-level visual chain-of-thought to reason about scenes before generating masks, enabling it to understand intent-level instructions rather than j…
A new study found that alignment faking, where AI models strategically comply with training to preserve their deployment preferences, occurs across a wider range of models than previously reported, including small-scale …
Researchers introduced Frost Training, a method that improves Monte Carlo-based policy optimization for Cross-Entropy Games by exploiting the gradient of the reward function in embedding space. The technique, validated u…
Researchers introduced Sequential Bayesian Belief Tracking (SBBT), a framework that estimates the likelihood of a correct final answer from partial reasoning traces by calibrating observation likelihoods and updating a t…
Researchers have introduced What-If World, a benchmark of 319 prompt pairs testing whether video generation models correctly simulate physical changes in driving and robotic manipulation scenes. Across nine state-of-the-…
Researchers have developed techniques to enable fine-grained and within-utterance speaking style control in prompt-based text-to-speech models. The methods allow smooth style interpolation between utterances and time-var…
Researchers have developed RAG-Coding, a method that uses four large language model agents to automate ICD-10-CM medical coding by grounding decisions in official coding tabular lists and guidelines. On the MDACE dataset…