Tahoe-100M is an atlas of 100 million single-cell transcriptomes, capturing how 50 cancer cell lines respond to ∼1,100 drug-dose treatments. By pairing single-cell and molecular phenotypes at scale, the resource links drug mechanisms to cellular responses and provides an openly available substrate for training predictive models of cell behavior.

Nature Medicine, Published online: 17 September 2026; doi:10.1038/s41591-026-04646-6

Results of this study show in experimental models and data from patient cohorts that the antiseizure medication levetiracetam is associated with longer survival and reduced tumor growth in diffuse midline glioma, but not hemispheric high-grade glioma, by selectively dampening GABAergic synaptic signaling, independently of its canonical SV2A-mediated primary antiseizure mechanism.

Nature Medicine, Published online: 16 September 2026; doi:10.1038/s41591-026-04625-x

In a prospective study involving 1,785 individuals from four countries, the PANXEON exosome-based biomarker, combined with carbohydrate antigen 19-9 levels, achieves high sensitivity for the detection of early-stage pancreatic cancer.

Nature Medicine, Published online: 15 September 2026; doi:10.1038/s41591-026-04610-4

Two early clinical studies of selective KRASG12D inhibitors show encouraging activity in advanced cancers with G12D mutations, signaling a transformative change in the treatment landscape for RAS-driven cancers with potential applications across tumor types and stages of disease.

Nature Medicine, Published online: 15 September 2026; doi:10.1038/s41591-026-04644-8

In the phase 2 RIO trial, there was delayed viral rebound and resistance to broadly neutralizing antibodies 3BNC117-LS and 10-1074-LS in adult males living with HIV undergoing analytical treatment interruption, and initial reservoir sensitivity to autologous antibodies was associated with a longer time to rebound.

Recombining domains across an entire protein family, rather than relying on natural sequences shaped by evolution, generates synthetic “DESynR” transcription factors with enhanced function. DESynR AP-1 TFs reprogram CAR T cells into non-natural, therapeutically optimized states and outperform natural AP-1 factors in antitumor immunity.

Spatial multi-omics reveals macrophage states that constrain adaptive immunity in immunosuppressed non-melanoma skin cancer.

Arginine availability regulates arginyl tRNA levels and codon-dependent translation of MHC class I, tuning antigen presentation and shaping anti-viral and anti-tumor immunity.

Liu et al. develop Oncoformer, a multimodal transformer that reads routine laboratory tests and chest X-rays already collected in everyday care. Across more than 3.6 million individuals, it detects cancer, infers tumor stage, and stratifies treatment response and recurrence risk, pointing toward risk-adapted cancer care built on data already in hand.

Two genetically distinct neuronal subtypes in the intrinsic cardiac nervous system are differentially required for baseline cardiac function and stress resilience to maintain cardiac stability and survival.

arXiv:2609.12105v1 Announce Type: new Abstract: The prevailing assumption in applied machine learning is that progress on consequential quantitative decisions such as pricing risk, allocating capital, triaging patients, or containing a network intrusion will follow from progress in large language models (LLMs). A language model is trained on a representation of the world that was produced by human description; description is a lossy encoding of the quantitative record, and the loss is irreversible: no downstream model, at any scale, can recover from a description what the description did not encode. We formalize this as a property of the representation on which a model is trained rather than of the model capacity, and we identify three further properties that consequential settings demand of a model and that a language substrate cannot supply by construction: reproducibility, lineage from every output back to the source records that produced. it, and calibrated uncertainty. We argue that these properties define a distinct model class, which we call the Large Quantitative Model (LQM).

arXiv:2609.12139v1 Announce Type: new Abstract: Atomic layer deposition (ALD) and atomic layer etching (ALE) are reported heterogeneously across experimental and simulation literature in materials science, hindering comparison and machine-actionable reuse. We present four domain-expert-reviewed JSON Schemas for ALD and ALE experimental and simulation processes. Curated with schema-miner and grounded in QUDT using schema-miner pro, the schemas structure materials, process conditions, configurations , and measured or predicted results. We compare their scope, structure, and semantic grounding, and demonstrate their use for schema-guided literature extraction and publication of structured records through ORKG templates.

arXiv:2609.12718v1 Announce Type: new Abstract: Hallucinations can undermine clinician trust in LLMs, making it important that evaluation methods capture clinically relevant errors. Rubric-based evaluation has become the leading approach for assessing LLMs in medicine, but it is unclear whether rubric scores reflect such errors. We first study this in a controlled setting using MedHallu, finding that more specific rubrics better distinguish correct from hallucinated responses. To test this systematically, we develop a taxonomy of medical hallucination types and a clinician-validated error-injection pipeline that creates matched correct and error-injected responses. Across HealthBench, HealthBench Professional, and LiveMedBench, our clinically relevant hallucinations are missed by rubrics, often leaving scores unchanged. We find that rubrics are most effective when explicitly checking facts, and are less effective for additional or unexpected errors they do not anticipate. A preliminary retrieval-based factuality check recovers some of the rubric-blind errors, suggesting a complementary approach. These findings reveal systematic blind spots in current medical evaluation of LLMs and suggest that rubric scores alone are insufficient to establish clinical reliability, potentially undermining clinician trust and confidence in clinical deployment.

arXiv:2609.12747v1 Announce Type: new Abstract: Multimodal AI, powered by Large Language Models (LLMs) and Vision-Language Models (VLMs), is transforming assistive technologies by enabling simultaneous processing of visual and textual data. This advancement holds significant promise for over 43 million visually impaired and neuro-divergent individuals worldwide who face persistent challenges in navigating indoor and outdoor environments due to limited spatial awareness and insufficient environmental cues. Existing navigation aids often lack comprehensive 3D scene understanding, relying on constrained route-based strategies that hinder user autonomy. In this paper, we introduce a novel end-to-end framework that integrates LLMs, VLMs and digital twin technologies to deliver a spatially cognitive navigation support for visually impaired and neuro-divergent users. Our system captures video input via standard mobile phone cameras, and employs SLAM3R to generate dense 3D point clouds from monocular RGB sequences in real-time. Our custom post-processing algorithm ensures accurate point cloud alignment across multiple viewpoints without requiring predefined reference points. This enhances the capabilities of SpatialLM to produce structured 3D representations, including architectural elements and oriented object bounding boxes. The enriched spatial data is then processed by a locally deployed LLM, which interprets 3D contexts to generate detailed scene descriptions and precise distance measurements between users and surrounding objects. We evaluated our approach across diverse video scenarios featuring various perspectives, looped walking views and captured in multiple environments. The evaluation results demonstrate consistent accuracy in 3D scene interpretation and object localisation, underscoring the potential of our system as a transformative assistive navigation solution that combines advanced visual perception with spatial reasoning

arXiv:2609.12822v1 Announce Type: new Abstract: Blinded physician evaluation has been considered by many to be the gold standard for assessing clinical reasoning in large language models (LLMs). This is difficult to scale; thus, prior studies typically rely on small physician panels, often from a single institution or specialty, which both limits the scientific questions investigated and makes it unclear whether findings would be reproduced with a different set of evaluators. To more rigorously and scalably study clinical reasoning in AI models, here we introduce PrecepTron, an LLM fine-tuned for physician-level evaluation of open-ended responses. PrecepTron was trained using low-rank adaptation (LoRA) of a 32-billion-parameter model on a small number of physician examples. We also release GRAND-ROUNDS, a new large-scale physician-annotated benchmark of 9,217 scores by 11 physicians across seven studies. We show that frontier LLMs in typical "LLM-as-a-judge" approaches often disagree with physicians and with each other, but fine-tuning PrecepTron on a small number of cases enables physician-level consistent scoring across tasks. We use PrecepTron to reproduce headline findings from five influential studies assessing LLMs for clinical care in JAMA, Science, and Nature Medicine without new human grading. Using PrecepTron, we then pose new questions about how LLMs reason in medicine that would have been infeasible with human grading alone, including measuring the diagnostic accuracy of frontier LLMs when clinical cases are provided piecemeal, even token by token. Together, PrecepTron and GRAND-ROUNDS provide a foundation for reproducible, large-scale study of how LLMs reason in medicine. All code, data, and labels are made freely available for researchers.

arXiv:2609.13047v1 Announce Type: new Abstract: Humans organize knowledge into a taxonomy of concepts with nested levels of abstraction and a \emph{basic level} at which people recognize and name objects with the least cognitive effort. Cobweb is a classic cognitive account of this ability, an incremental learner that builds a probabilistic concept hierarchy by maximizing category utility. We argue that diffusion models, although designed for image synthesis, implicitly perform the same computation. The noisy marginals of a diffusion model are Gaussian smoothings of the data distribution, and the modes of these marginals form a hierarchy that corresponds to a Cobweb tree of probabilistic prototypes in four respects. Both are hierarchical density models, both are hierarchical-Bayesian models with Gaussian prototypes, both treat categorization as score-following that reduces uncertainty, and in both a basic level emerges. We locate this basic level for a diffusion model at an intermediate noise level, where recent analyses show that the reverse process commits to the class identity of a sample. The two models differ mainly in how they represent and learn the taxonomy. Cobweb learns a discrete tree incrementally, whereas a diffusion model encodes a continuous, interpolable hierarchy in a single learned score field fit to the data distribution. We test the correspondence on MNIST and Fashion-MNIST by recovering the diffusion hierarchy through mode-finding and comparing the basic levels of the two models. This reframes diffusion as a cognitive model of concept formation and offers Cobweb a continuous, scalable instantiation.

npj Digital Medicine, Published online: 14 September 2026; doi:10.1038/s41746-026-03225-w

Data-driven identification of repurposable drugs for ALS

Nature Nanotechnology, Published online: 14 September 2026; doi:10.1038/s41565-026-02281-3

This study demonstrates on-chip all-optical switching by integrating magnetic memory elements with photonic circuits, establishing a route towards fully integrated magneto-photonic systems for ultrafast and energy-efficient information technologies.

Cell Death Discovery, Published online: 09 September 2026; doi:10.1038/s41420-026-03332-3

Multi-omic profiling reveals metabolic vulnerabilities in enzalutamide resistant prostate cancer

Science, Ahead of Print.