filtered mixture-of-generators for synthetic survival data
fogs selects plausible synthetic samples from multiple tabular generators to improve downstream survival model training on small clinical datasets.
aisummaries filed under research
fogs selects plausible synthetic samples from multiple tabular generators to improve downstream survival model training on small clinical datasets.
ainew theory proves fourier neural operators can approximate and learn time-dependent solutions of dissipative partial differential equations with polynomial sample complexity.
aia new method uses deep neural networks and rank-based optimization to handle mixed outcome types in multitask learning with shared predictor selection.
aia new framework models moral cognition as a tradeoff between moral breadth and depth under limited resources, recasting ethical theories as efficient strategies.
aia study disentangles whether improvements in semi-supervised learning for security come from tuning the classifier alone or from joint optimization with the ssl pipeline.
aia new framework treats alignment as controlling how preferences evolve through interaction, not just satisfying fixed goals.
aithree popular language model training methods all adjust the same number: the standard deviation of correctness marks across sampled answers.
aigoogle announced gemini 3.5 live translate, android 17 features, and a new home speaker, plus tools for research and education.
aia controlled study finds that multi-turn improvement often comes from resampling or extra computation, not from feedback itself, with only strong external teachers providing real gains.
aia study shows learned stopping rules can improve reasoning model efficiency on math tasks but not on multiple-choice benchmarks.
aibayesbench evaluates how large language models update beliefs across multi-turn conversations, comparing their trajectories to rational bayesian inference.
aia new method uses competitive optimization to find governing partial differential equations from several datasets with different conditions.
aimetaflow trains language models to produce reusable task-level workflows instead of instance-specific solutions, improving reliability and interpretability.
aihierarchical global attention replaces dense causal attention in pretrained transformers, enabling 64k-token context on a single 32gb gpu without retraining.
aifew-step text generation fails because of sharp categorical readouts, not poor transport, as proven by a geometric analysis of continuous text decoders.
aiscarfbench evaluates ai agents on real-world enterprise java framework migrations, measuring build, deploy, and behavioral success.
aia new framework edits internal representations during reasoning to guide large language models toward truthful answers without disrupting correct thinking.
aievery eval ever and hugging face community evals are now intercompatible, enabling cross-posting and interpreting evaluation results with links to open models and leaderboards.
aigoogle research releases building-level rooftop reflectivity data for over 50 global cities to help planners target cool roof interventions and reduce urban heat.
aimiles is an open source framework that combines sglang, megatron-lm, ray, and pytorch for scalable reinforcement learning post-training of large language models.
ai