Subject
Machine learning, neural networks, language models, and computer vision.
A replay-free method for continual learning scored higher across the reported benchmarks and showed no measured retention loss on TRACE, though its routing has not been tested under severe distribution shifts.
Scientific publication4 min read
A training-free approach that ranks visual tokens by both current relevance and changing importance performed strongly across several multimodal language-model benchmarks, including tests with 88.9% pruning.
Scientific publication4 min read
A preprint reports valid-and-unique molecular yields and more distinct elite architectures, while a digit-image control favored Soft on distribution matching.
Scientific publication4 min read
A new preprint describes LipDA, a detector that uses mismatches between lip motion and head movement to identify LipSync forgeries and estimate which generator family produced them.
Scientific publication4 min read
A preprint reports favorable shifts on several gender-bias measures across three language models, while general-capability averages remained close to the corresponding base models.
Scientific publication5 min read
An arXiv preprint reports higher within-model caption scores for full fine-tuning, while Video-LLaVA prompts remained below the strongest fine-tuned model and its full fine-tuning and LoRA tests were not completed.
Scientific publication3 min read
A method called MOSAIC reported higher macro-client top-1 accuracy than FedDDA across domain-shift and joint-shift benchmark settings. The study points to a better average across clients rather than a universal win, with only three seeds and no confidence intervals reported.
Scientific publication5 min read
A preprint describes TACD, a distillation method that limits terminal supervision and reports stronger benchmark results, faster generation and lower peak GPU memory across text-to-motion tests.
Scientific publication4 min read
The uncertainty-guided system recorded higher segmentation metrics on an independent cohort, with its largest reported change in tumor core, while a structural tripwire routed 36 of 362 cases to full manual review.
Scientific publication4 min read
A preprint testing FlyVision across computer-vision and biomedical datasets found that it nearly matched ResNet18 on MNIST with far fewer parameters, while larger tasks produced mixed results.
Scientific publication4 min read
A study of 139 Beijing adults found strong internal performance when machine-learning models separated phlegm-dampness and balanced constitutions, but larger validation is still needed.
Frontiers in endocrinology4 min read
A machine-learning model identified concurrent fear of movement in older patients after coronary procedures, with strong results in a time-separated test group but important limits on wider use.
Frontiers in medicine4 min read
A model built from six clinical measures performed better than three comparison methods in an internal test of 518 children with allergic rhinitis. The study found associations involving IgE, Vitamin D, BMI, sleep and screen time, but it did not show that any of these factors causes ADHD or that changing them would alter symptoms.
Frontiers in public health5 min read
In a retrospective study, LightGBM ranked in-hospital mortality risk in a held-out ICU cohort and an external database, but only 30.3% of external high-risk predictions were followed by death.
Frontiers in neurology5 min read
Among 768 young and middle-aged adults receiving maintenance hemodialysis, 40.23% were in paid work at survey time, and a random-forest model performed well in an independent group of 203 patients.
Frontiers in public health4 min read
Researchers compared machine-learning and Cox models for predicting recorded fasting-glucose-defined prediabetes in adults whose baseline glucose was normal. The selected model performed moderately in internal and hospital-based external testing, but the study did not test whether using it improves care.
Frontiers in endocrinology4 min read
Camera-based AI scoring closely matched consensus video review for total BESS scores and produced smaller discrepancies than real-time on-site manual scoring in 80 participants.
Sports Medicine - Open4 min read
The model was strongest on rhythm abnormalities and weaker on conduction and morphological conditions, with results varying across diagnoses and datasets.
Health information science and systems4 min read
Researchers found immune and tissue-related gene signals in separate datasets on disc degeneration and osteoporosis, but say the findings need larger, clinically matched human studies.
Frontiers in immunology5 min read
Researchers built a mobile system that reminds people to take medicines, collects short intake videos and uses artificial intelligence to classify what is happening. The model performed well on held-out test data, but the clinical pilot was small, short and uncontrolled.
Revista da Associacao Medica Brasileira (1992)5 min read
A reinforcement-learning retriever called MO-IKE reported higher combined scores than DR-IKE on Llama and Mistral tests, and recorded an overall score of 24.5 on UniEdit.
Scientific publication4 min read
Thirteen frontier models were tested on 20 computational-biology tasks, and none scored above 0.48 overall; performance was lower on very large inputs and deep analysis chains.
Scientific publication4 min read
A methods study found higher reproducibility for claim-locked language-model reports in fMRI tests, while separate audits showed why stability is not the same as correctness.
Scientific publication4 min read
A modeling study found that one speech-act-based forecasting design led on three dialogue datasets and in low-data tests, while transfers between datasets remained uneven.
Scientific publication4 min read
A methods preprint describes LiDAR-SAM2, which uses video foundation-model masks to create 4D point labels and train LiDAR-only models without human LiDAR annotation. On SemanticKITTI, the labels produced higher reported scores than SAM2 labels but did not match full ground truth.
Scientific publication4 min read
A preprint reports a video-generation system that combines a unified 3D control interface with streaming output, but its tests also show a modest quality gap and occasional failures in object consistency.
Scientific publication4 min read
An agent trained for video deep research scored higher than its base model on two benchmarks, while an ablation reported fewer interaction turns when tool necessity was weighted.
Scientific publication4 min read
A theoretical preprint proposes a way to compress weighted graphs and trained neural networks with an explicit error budget, but its demonstration covers only three post-training cases.
Scientific publication4 min read
A preprint benchmark reports that an episode-based AI memory system scored higher than tested full-context and retrieval methods while using much less retrieved text.
Scientific publication4 min read
A constructed example cuts constrained risk in half, but the classical ordering returns when the model class is unrestricted.
Scientific publication5 min read
A paper-derived training pipeline produced a 60 billion-token corpus and was linked to higher writing scores, while reasoning results stayed close to direct fine-tuning.
Scientific publication4 min read
A preprint study of graph-based question answering found that carefully controlled rewrites damaged performance mainly during subgraph construction, not entity linking or final decoding.
Scientific publication4 min read
DCGC reported the best average score in a six-benchmark comparison, while tests of shuffled drafts suggested that the original draft still mattered.
Scientific publication4 min read
A new model-auditing method called ICON was designed to show which supplied concepts a deep network relies on, even when those concepts overlap. Tests on synthetic, dermoscopic and neuroimaging models found lower simulation error and clearer signals about image artifacts and demographic correlations.
Scientific publication5 min read
A literature-based review proposes an iterative workflow for AI systems that carry out multi-step data science, while stressing that the framework has not been experimentally validated.
Scientific publication4 min read
A preprint study found that the top-ranked token changed a model’s reported credal width more than random eligible tokens, while numerical checks exposed limits in the attribution values.
Scientific publication4 min read
A constrained-reinforcement-learning approach for distilling reasoning into smaller language models recorded the highest reported reasoning success rate across the tested settings, with mixed but often competitive final-answer results.
Scientific publication3 min read
A transformer model for sparse-view computed tomography reported leading image-quality scores in fixed and variable-view tests and was also tested on one real nanoscale mouse-brain pillar.
Scientific publication4 min read
In synthetic AI teams, changing inputs was linked to a sharp rise in feedback, while training on the resulting records was associated with higher success in several benchmark comparisons.
Scientific publication3 min read
LEGO-OPD combines language-prior and visual-grounding signals and reports higher reasoning averages than evaluated baselines in Qwen3 experiments, with perception gains limited to benchmark scores.
Scientific publication3 min read