Week of November 9, 2026
20 curated disruptive papers. How Deep is the Signal? Time-Context up to 30 Years for Colorectal Cancer Prediction in a Primary-Care EHR Model; Machine learning quantum data to accelerate quantum Monte Carlo; PharmAgents2; Social Humanoid. Free explainers publish after editorial write-up. Prior week 2026-W45 remains in the archive.
Start with #1 → How Deep is the Signal? Time-Context up to 30 Years for Colorectal Cancer Prediction in a Primary-Care EHR Model
How Deep is the Signal? Time-Context up to 30 Years for Colorectal Cancer Prediction in a Primary-Care EHR Model
EHR foundation models read medical events within a fixed context window, and long context has so far been measured only in tokens. How far back in time a model…
Machine learning quantum data to accelerate quantum Monte Carlo
Simulating strongly correlated electrons in molecules and materials remains a central goal for quantum computing. A promising strategy uses quantum processors…
PharmAgents2: Towards Autonomous End-to-End Drug Discovery
Drug discovery requires continuous scientific decision-making across a vast research space. We introduce PharmAgents2, an autonomous system for end-to-end drug…
Social Humanoid: Socially Responsive Human-Humanoid Interaction
Humanoid robots are typically trained as solitary agents, leaving them unable to coordinate physically with human partners who naturally anticipate and adjust…
Quantum Knowledge Distillation: State-of-the-art, Applications and Open Problems
Knowledge distillation transfers predictions, representations, or other supervisory information between learning models and is increasingly investigated in qua…
SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
LLM-guided evolutionary search uses AI agents to improve programs for mathematical and computational problems by iteratively refining solutions and combining h…
Latent RL Priors for Data-Efficient Dexterous Manipulation
Learning dexterous manipulation from limited visual demonstrations is challenging because policies must acquire both perceptual grounding and precise control,…
MOMASPLAT: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation
Visuomotor policies trained through imitation learning are highly sensitive to changes in camera viewpoint. This is particularly problematic for mobile manipul…
Geometric Relevance Is Not Sufficient: Evaluating Focused Post-Training Supervision in Diffusion Docking
Diffusion-based molecular docking requires learning a corrective score field across a broad corruption distribution, yet individual pose errors can differ subs…
Anisotropy lifts topological protection of transport in pumped spin chains
We investigate the prospect of topological spin pumping and transport in a dimerized spin-$\frac{1}{2}$ anisotropic XY chain with tunable in-plane anisotropy.…
Where and Why is Grounded Reasoning Useful?
Grounded reasoning, where a model outputs text coordinates of relevant locations in chain-of-thought reasoning, is a common strategy for solving complex visual…
Accelerating reaction network identification via frequency-domain analysis
The identification of intracellular reaction networks from single-cell data lies at the heart of many biological studies, as it can unravel key mechanisms in l…
Tensor Networks for Block Adaptive Thermal Radiation Transport
Thermal radiation transport (TRT) is computationally challenging because the photon specific intensity depends simultaneously on space, angle, and frequency, p…
Direct transition from a fractional Chern insulator to a topological superconductor
We find numerical evidence for a direct continuous transition from a Laughlin fractional Chern insulator (FCI) to a $c_-=3/2$ topological superconductor (TSC),…
Modeling Gene Expression Noise: From Transcriptional Dynamics to Cell Growth and Division
Gene expression is inherently noisy, leading to substantial cell-to-cell variation in mRNA and protein levels. The telegraph model and the simpler bursty model…
The cold substellar frontier in JWST Extragalactic surveys: a robust parallax measurement yields the most distant known ultra-cold Y dwarf
We present an analysis of JADES-GS-BD-5, an extremely cold Y dwarf identified in the JADES/GOODS-South field. Using multi-epoch JWST/NIRCam imaging spanning a…
Winding-Pack Quench Simulation of Stellarator Coils: Hydraulic Field-Network Coupling and Transverse Heat Conduction in OPENSC$^2$
Quench propagation in cable-in-conduit conductors is thermo-hydraulically driven, yet existing 1D models treat a conductor as one straight adiabatic cable with…
FA-Agent: An extensible multimodal agent framework for first-arrival picking in mountainous seismic data
First-arrival traveltimes underpin near-surface velocity modeling and static corrections, but in low signal-to-noise mountainous land data the first arrival is…
Estimating Vertical Ocean Velocity from Horizontal Currents: Linear and Depth-Conditional Neural-Network Approaches on a High-Resolution Regional Ocean Model
The vertical component of the ocean velocity, w, is several orders of magnitude smaller than the horizontal components u and v, yet it controls vertical tracer…
Trapping and Fracture of Particles in Three-Sphere Ball-Milling Collisions
We numerically investigate the collision and fracture processes of ball milling based on a minimal model of a three-sphere geometry using discrete element meth…