# Foundation Models

A team at Seoul National University Hospital released CARMEN, a single encoder pretrained without labels on ten cardiorespiratory waveforms totaling about 2.27 million modality-hours, which accepts any combination of co-recorded signals and inputs from 10 s to 5 min. With the encoder frozen and only a linear layer trained, it was significantly better than end-to-end supervised models on 12 of the 15 tasks that had supervised comparators, and better than three pretrained foundation models on 14 to 17 of 19 tasks, with none exceeding it.

A team at Seoul National University Hospital released CARMEN, a single encoder pretrained without labels on ten cardiorespiratory waveforms totaling about 2.27 million modality-hours, which accepts any combination of co-recorded signals and inputs from 10 s to 5 min. With the encoder frozen and only a linear layer trained, it was significantly better than end-to-end supervised models on 12 of the 15 tasks that had supervised comparators, and better than three pretrained foundation models on 14 to 17 of 19 tasks, with none exceeding it.

Glyph decomposes clinical foundation-model embeddings into sparse, nameable concepts so that features previously entangled in high-dimensional vectors can be tested like clinical variables. Across abdominal CT, radiology reports and laboratory data from 41,628 patients, the study tested 604,185 concept–outcome pairs and retained 397 high-risk concepts with 4,463 Bonferroni-significant associations. Most associations reproduced in three held-out cohorts without recalibration, and the top ten concepts reproduced more often than markers recovered from the literature.

Glyph decomposes clinical foundation-model embeddings into sparse, nameable concepts so that features previously entangled in high-dimensional vectors can be tested like clinical variables. Across abdominal CT, radiology reports and laboratory data from 41,628 patients, the study tested 604,185 concept–outcome pairs and retained 397 high-risk concepts with 4,463 Bonferroni-significant associations. Most associations reproduced in three held-out cohorts without recalibration, and the top ten concepts reproduced more often than markers recovered from the literature.

Most ICU sepsis warning models answer only whether sepsis will occur, leaving clinicians unsure of the onset context and early course once an alarm sounds. SepsisFlow places hourly pre-onset risk, the patient state at onset and the 72-hour organ-support trajectory on one clock advancing hourly from ICU admission: before onset it uses only bedside-visible records without antimicrobial or culture orders, reaching a 24-hour AUROC of 0.822 on the MIMIC-IV internal test set, and its onset states form three contexts with 28-day in-hospital mortality of 17.1%, 15.1% and 2.2%.

Most ICU sepsis warning models answer only whether sepsis will occur, leaving clinicians unsure of the onset context and early course once an alarm sounds. SepsisFlow places hourly pre-onset risk, the patient state at onset and the 72-hour organ-support trajectory on one clock advancing hourly from ICU admission: before onset it uses only bedside-visible records without antimicrobial or culture orders, reaching a 24-hour AUROC of 0.822 on the MIMIC-IV internal test set, and its onset states form three contexts with 28-day in-hospital mortality of 17.1%, 15.1% and 2.2%.

Mouse behavior analysis has relied on self-supervised pose models that encode each animal independently, yet aggression, courtship, mounting and allogrooming are inherently multi-animal. MICE aligns six mouse-pose datasets to a universal 12-keypoint vocabulary and pretrains jointly, pairing a hierarchical individual encoder for per-mouse kinematics with a Perceiver-style social encoder whose learned latent codebook handles any group size, so one checkpoint serves different animal counts without retraining. Across six datasets and four evaluation protocols, MICE matches or exceeds prior keypoint-based baselines, and layer-wise probing shows the social stage improves discriminability beyond the individual encoder.

Mouse behavior analysis has relied on self-supervised pose models that encode each animal independently, yet aggression, courtship, mounting and allogrooming are inherently multi-animal. MICE aligns six mouse-pose datasets to a universal 12-keypoint vocabulary and pretrains jointly, pairing a hierarchical individual encoder for per-mouse kinematics with a Perceiver-style social encoder whose learned latent codebook handles any group size, so one checkpoint serves different animal counts without retraining. Across six datasets and four evaluation protocols, MICE matches or exceeds prior keypoint-based baselines, and layer-wise probing shows the social stage improves discriminability beyond the individual encoder.

Human annotation on the target dataset is replaced by an automatic pipeline: SAM produces segmentation proposals, CLIP pre-filters and matches labels, and a large vision-language model labels only cluster medoid images, after which an open-set detector is trained on those pseudo-labels and refined iteratively. Under zero-shot settings on COCO val2017 and LVIS minival, the YOLO-backbone variant reaches 60.8 AP and 47.4 AP, while the Swin-T variant reaches 57.2 AP and 46.2 AP, indicating the gain is not only from the detector backbone.

Human annotation on the target dataset is replaced by an automatic pipeline: SAM produces segmentation proposals, CLIP pre-filters and matches labels, and a large vision-language model labels only cluster medoid images, after which an open-set detector is trained on those pseudo-labels and refined iteratively. Under zero-shot settings on COCO val2017 and LVIS minival, the YOLO-backbone variant reaches 60.8 AP and 47.4 AP, while the Swin-T variant reaches 57.2 AP and 46.2 AP, indicating the gain is not only from the detector backbone.

Collider analyses have trained a separate model per task; EVENET instead represents each collision as an unordered particle cloud and pretrains one backbone on 500 million simulated events with self-supervised plus physics-informed objectives, then adapts it through interchangeable task heads. In an anti-isolated ϒ→μ+μ− search on CMS Open Data, the fully pretrained variant reaches a median local significance of 7.6σ after calibration, above the published 6.4σ, and across a heavy-resonance mass grid its maximum SIC averages about 50% above training from scratch.

Collider analyses have trained a separate model per task; EVENET instead represents each collision as an unordered particle cloud and pretrains one backbone on 500 million simulated events with self-supervised plus physics-informed objectives, then adapts it through interchangeable task heads. In an anti-isolated ϒ→μ+μ− search on CMS Open Data, the fully pretrained variant reaches a median local significance of 7.6σ after calibration, above the published 6.4σ, and across a heavy-resonance mass grid its maximum SIC averages about 50% above training from scratch.

AnyLanguageModel 1.0 turns Apple's Foundation Models interface into a replaceable layer: an app changes its import from FoundationModels to AnyLanguageModel, and the same session code can call the system model, open-weight models run through llama.cpp, MLX and Core ML, and several hosted providers. Before this, developers curious about local models were unsure how to start and wanted to avoid the added complexity of supporting multiple inference providers. Over the year the library aligned tool calling and guided generation across providers and added image input and Linux support.

AnyLanguageModel 1.0 turns Apple's Foundation Models interface into a replaceable layer: an app changes its import from FoundationModels to AnyLanguageModel, and the same session code can call the system model, open-weight models run through llama.cpp, MLX and Core ML, and several hosted providers. Before this, developers curious about local models were unsure how to start and wanted to avoid the added complexity of supporting multiple inference providers. Over the year the library aligned tool calling and guided generation across providers and added image input and Linux support.