Thousands of papers come flying out every day like confetti from a citation cannon, and most of them do not make me stop my scroll. This one did, because it asks a very practical question with very expensive consequences: can you make a biology foundation model bigger, better, and less of a...
That is the bet in a 2026 paper on GDF15, a stress-signal protein that shoots up in cancer cachexia - the brutal wasting syndrome where patients lose weight, muscle, appetite, and a whole lot of margin for error. GDF15 is one of the load-bearing troublemakers here. When levels rise, it talks to a...
Your phone already does a tiny version of this trick every day. It decides which photos look alike, which calls smell like spam, and which notifications deserve your eyeballs first. Now imagine taking that same pattern-finding instinct, aiming it at cancer data, and asking: can a model sort...
If you've ever tried to figure out how much liver a surgeon can safely remove, you know how frustrating hand-drawing eight squishy liver segments on CT scans is. This paper fixes that.
The annoying truth up front: this method still does not let scientists glance at a single cell and predict its future with magical, scary accuracy. The signal is noisy. The accuracy is moderate. Some cell types were easier than others. And yet - this paper still pulls off something pretty wild. It...
A shiny blob on a virtual object turned out to need less brain-like machinery than expected.
A couple of years from now, the overnight radiology shift at a small hospital might feel less like a bottleneck and more like a well-run garage: one human expert at the lift, an AI standing beside them with a flashlight, already pointing at the loose belt, the oil leak, and the weird rattle before...
Maybe the usual question in cancer pathology is a little too tidy. What if the important thing is not how many immune cells show up in a prostate tumor, but whether they actually gather like a coordinated neighborhood watch instead of three lost tourists in a parking lot?
I’ll admit it: the part that threw me at first was almost embarrassingly simple. This paper asks whether an AI reading 3D mammograms gets better if you also hand it the patient’s earlier exams, and my first reaction was, well, obviously yes, that’s like giving the quarterback last season’s footage....
For the past few years, cell-atlas people and platelet people have been in a quiet little research race: who gets to redefine the megakaryocyte first - the folks with giant single-cell datasets, or the folks who actually know what these cells do for a living? This new Developmental Cell paper by...
SWAP-Score judges a neural network by the sample-wise activation patterns it produces, which means it tries to spot a promising model before training has even had time to set the GPU fan screaming.[1]
41 models, 30 datasets, 5 tasks, and zero all-purpose champion. That is the headline from Deep Time Series Models: A Comprehensive Survey and Benchmark, where Wang and colleagues put a huge chunk of the modern time-series zoo into one fair-ish arena and found something refreshingly unglamorous: the...
Before this paper, urban heat was often treated like one giant citywide fever. After it, we get a sharper read: some cities are running hot mostly because of climate, some because of urban form, and plenty because both are doing a nasty superset together [1].
R2R, the Room-to-Room benchmark, matters because it is the classic test of whether a navigation agent can actually follow directions in an unfamiliar indoor space instead of free-styling its way into a broom closet like a very confident Roomba with a philosophy degree.
At 7:12 a.m., a radiologist opens the worklist and gets hit by a squall of scans - chest CTs, stroke alerts, follow-up MRIs, all piling up before the coffee has even found the bloodstream. Off to one side sits the promise of AI, polished like a new brass compass. It can flag bleeds, triage urgent...
When Apollo 11 touched down, NASA was not asking whether the Moon was beautiful. They were asking the much more practical question your contractor asks before stepping on a suspicious attic beam: will this thing actually hold? Ladies and gentlemen of the research jury, that is basically what Blake...
Plot twist: the camera app you use every day to see whether your face is awake yet may someday lean on a memory device that behaves like both a coin flip and a calculator. Out here in the silicon underbrush, researchers have found a tidy little creature called a ferroelectric tunnel junction, or...
Before this contraption arrived, suspicious lung clots waited in the radiology queue like uninvited guests at a manor dinner. After it arrived, the machine began tapping the butler on the shoulder and whispering, "Pardon me, but this one looks alarming."
Most people treat chromosome mix-ups in pregnancy like a one-variable math problem: older eggs, higher risk, end of story. This review politely walks into the room, clears its throat, and says not so fast - maternal age matters, but a mother's own genetic variants may help explain why some younger...
You probably didn't know that the camera app, photo editor, and health gadgets you use all day are quietly making judgment calls about which pixels matter, which ones get smoothed over, and which ones become the story - and in medicine, that same pixel-level guesswork can end up outlining a tumor,...