{"data":{"event":{"id":"2afe50a7-8062-4482-8b51-3d3bca873ac5","slug":"reading-the-whole-heart-latent-attention-masked-autoencoders-for-multimo-3e1872b1ea","title":"Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning","short_summary":"arXiv:2609.12035v1 Announce Type: new \nAbstract: Cardiovascular diagnosis rests on integrating complementary modalities, like ECG, echocardiography, chest radiographs, and clinical variables, each capturing distinct but correlated aspects of cardiac physiology. Yet most medical foundation models remain modality-specific, combining modalities only for finetuning or post-training. This discards the cross-modal evidence clinicians naturally integrate and ignores the structure within each modality. We introduce Latent-Attention Masked Autoencoders (LAMAE), a multimodal, structure-aware masked auto","full_description":"arXiv:2609.12035v1 Announce Type: new \nAbstract: Cardiovascular diagnosis rests on integrating complementary modalities, like ECG, echocardiography, chest radiographs, and clinical variables, each capturing distinct but correlated aspects of cardiac physiology. Yet most medical foundation models remain modality-specific, combining modalities only for finetuning or post-training. This discards the cross-modal evidence clinicians naturally integrate and ignores the structure within each modality. We introduce Latent-Attention Masked Autoencoders (LAMAE), a multimodal, structure-aware masked autoencoder that jointly learns patient-level representations during self-supervised pretraining. Rather than fusing modalities post hoc, LAMAE exchanges information directly in the latent space through a shared latent-attention module operating over a study-view-entity hierarchy, enabling aggregation of variable observations and graceful handling of missing modalities. Pretrained on over 1.2 million MIMIC-IV hospital stays, LAMAE outperforms modality-specific pretraining and strong contrastive and vision-language baselines across multimodal hospital-stay tasks, such as in-hospital mortality, ICD-10 and DRG coding, and length of stay, while remaining competitive on unimodal tasks. These gains persist even when only a single modality is available at test time, showing that modeling both intra- and inter-modal structure yields more robust, transferable representations.\n\nUpdate (2026-09-21): Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving. arXiv:2609.21486v1 Announce Type: new \nAbstract: Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene representations. Incomplete evidence leads to low-quality candidate generation and unreliable ranking among geometrically similar trajectories. On a register-based baseline, bad and poor candidates constitute 19.74% of the candidate set, while the oracle-best candidate ranks only 33.9th on average. We propose RRDrive, which introduces risk-aware occupancy as a dense, temporally aligned, and trajectory-queryable representation. Its global structure guides high-quality multimodal generation, while candidate-conditioned risk queries support fine-grained selection. We further construct RiskOcc4D-NAVSIM with automatic risk annotations. RRDrive achieves a selected-trajectory PDMS of 0.951, representing a 1.5% relative improvement over the baseline (0.937), and improves the average candidate PDMS by 7.7%. In challenging scenes, it improves candidate PDMS by 30.2%","ledger_type":"benefit","primary_domain_id":"c09546b6-10f8-48df-8347-0c1979416464","event_status":"provisional","event_date":"2026-09-14T00:00:00.000Z","discovery_date":"2026-09-14T00:00:00.000Z","first_published_date":"2026-09-14T00:00:00.000Z","last_reviewed_date":"2026-09-21T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.2000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.002000","confidence_level":"low","score_explanation":"Ingest update: independent source raised evidence; added a follow-up source. Score remains provisional until review.","methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","original_methodology_version_id":"d7881163-fb23-4e71-8625-bac1a8662c0f","published_at":"2026-09-14T04:00:50.322Z","created_at":"2026-09-14T04:00:50.322Z","updated_at":"2026-09-21T04:01:06.582Z","flags":[],"domain_name":"Medicine & Health","domain_slug":"medicine-health","methodology_version":"0.1"},"contributions":[{"id":"b9861d56-50db-413c-8859-4e41286a179a","event_id":"2afe50a7-8062-4482-8b51-3d3bca873ac5","model_id":"535014f7-c941-4d39-aa9b-8f9c1d3d07b7","role_description":"Unspecified system mentioned or implied by a news item. Remap to a named release when identified.","attribution_multiplier":"0.1000","credit_share":"1.0000","contribution_score":"0.002000","attribution_rationale":"News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.","attribution_confidence":"medium","first_used_date":"2026-09-14T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-14T04:00:50.333Z","model_slug":"unspecified-ai-system","model_name":"Unspecified AI system","identity_class":"unknown","is_internal":false,"family_name":"Unspecified","family_slug":"unknown-unspecified","organization_name":"Unknown","organization_slug":"unknown"}],"sources":[{"id":"6f570289-cd70-4e2f-b84b-50e05d71bdc2","event_id":"2afe50a7-8062-4482-8b51-3d3bca873ac5","url":"https://arxiv.org/abs/2609.12035","canonical_url":"https://arxiv.org/abs/2609.12035","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-14T00:00:00.000Z","retrieved_at":"2026-09-14T04:00:50.339Z","title":"Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning","excerpt":"arXiv:2609.12035v1 Announce Type: new \nAbstract: Cardiovascular diagnosis rests on integrating complementary modalities, like ECG, echocardiography, chest radiographs, and clinical variables, each capturing distinct but correlated aspects of cardiac physiology. Yet most medical foundation models remain modality-specific, combining modalities only for finetuning or post-training. This discards the cross-modal evidence clinicians naturally integrate and ignores the structure within each modality. ","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-14T04:00:50.339Z"},{"id":"e6a5c6bc-4192-4b62-a1d3-5adae0e5a47e","event_id":"2afe50a7-8062-4482-8b51-3d3bca873ac5","url":"https://arxiv.org/abs/2609.21486","canonical_url":"https://arxiv.org/abs/2609.21486","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-21T00:00:00.000Z","retrieved_at":"2026-09-21T04:01:06.568Z","title":"Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving","excerpt":"arXiv:2609.21486v1 Announce Type: new \nAbstract: Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene representations. Incomplete evidence leads to low-quality candidate generation and unreliable ranking among geometrically similar trajectories. On a register-based baseline, bad and poor candidates constitute 19.74% of the candidate set, while the oracle-best candidate ranks only 33.9th on average. We ","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-21T04:01:06.568Z"}],"claims":[{"id":"bb49a65c-015b-4c8c-a71d-0f246b52b1fa","event_id":"2afe50a7-8062-4482-8b51-3d3bca873ac5","claim_text":"Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-14T04:00:50.346Z","updated_at":"2026-09-14T04:00:50.346Z"}],"revisions":[{"id":"d85efccc-d42e-4d07-aa9b-e3f67d66d692","event_id":"2afe50a7-8062-4482-8b51-3d3bca873ac5","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-14T04:00:50.353Z"},{"id":"c4681de0-3fef-4975-8991-39699adcc9eb","event_id":"2afe50a7-8062-4482-8b51-3d3bca873ac5","model_id":null,"previous_score":"0.001000","new_score":"0.002000","previous_factors":{"tier":1,"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"new_factors":{"tier":1,"models":["535014f7-c941-4d39-aa9b-8f9c1d3d07b7"],"evidence":0.2,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Ingest update: independent source raised evidence; added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["e6a5c6bc-4192-4b62-a1d3-5adae0e5a47e"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-21T04:01:06.590Z"}],"secondary":[]},"methodology_version":"0.1"}