Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers at Poolside released two new Mixture-of-Experts AI models, Laguna M.1 and Laguna XS.2, designed for long-horizon software engineering tasks. The 225.8-billion-parameter M.1 and 33.4-billion-parameter XS.2, tr…
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…
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…
Researchers have developed Architecture-driven Shift (ADS), a lightweight metric that captures logit shift trends in continual learning models using few data samples, addressing the high computational cost of traditional…
Researchers developed a translation model that converts soft prompts—parameter-efficient but uninterpretable LLM adaptations—into natural language text. The translated prompts outperformed existing interpretability metho…
Metric-Aware PCA (MAPCA) parameterizes principal component analysis by a positive-definite metric matrix, with a canonical subfamily interpolating between standard PCA and output whitening. The paper positions MAPCA with…
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 have developed ICG, a framework that uses multimodal large language models and personalized preference alignment to generate cover images tailored to individual users. The system extracts semantic features fr…
Researchers introduced DynaSchedBench, a diagnostic framework for the Dynamic Flexible Job Shop Scheduling Problem that uses a Sequential Event-Space Calibrator to control instance difficulty through a novel Schedule Str…
Researchers introduced MTM-Bench, a controlled benchmark that isolates three distinct language roles—instruction, content, and response—across English, Spanish, and Chinese to evaluate multilingual LLM task execution. Te…
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…
Researchers at Simorgh have developed a region-aware hybrid retrieval method combining BM25 lexical matching and dense semantic similarity with regional weighting heuristics to improve culturally grounded question answer…
A new jailbreak framework called PAST2HARM has achieved up to 100% attack success rates against state-of-the-art multimodal AI systems, including Gemini Nano, GPT Image 2, and SD XL, by exploiting past tense reformulatio…
Researchers have released GenSBI, an open-source library for simulation-based inference built entirely in JAX, implementing flow matching, score matching, and denoising diffusion methods. The library offers three transfo…
Researchers at arXiv have identified that Batch Normalization causes gradient skew in dynamic sparse training (DST) methods, leading to slower convergence compared to dense neural network training. The team proposed Spar…
Researchers have developed a new interpretation method for Transformer models that use heterogenous attention structures, which process information from different sources. The approach addresses challenges in understandi…
Researchers developed a personalized observation normalization (PON) method to address heterogeneity in federated reinforcement learning, where differing state-transition dynamics cause non-identical input distributions …
Researchers introduced E²-LoRA, a method that concentrates knowledge into leading ranks of parameter updates to prevent energy diffusion and free capacity for new tasks in continual learning. The approach, which includes…
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 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…