ATLAS is a fully local, open-source coding agent that wraps a frozen 14B model in a multi-phase pipeline to hit 74.6% on LiveCodeBench — no API keys, no cloud, no fine-tuning required.
A curriculum over network depth improves fine-grained anatomical classification on limited medical data, with transformer models gaining more than 16 accuracy points.
A new subset selection method forces equal weights on chosen prototypes, boosting minority class accuracy and LLM training on imbalanced data mixtures.
Berkeley researchers introduce RAPO, a dual formulation robust RL method that steers rollouts toward worst-case dynamics without collapsing into over-conservatism.
A feedforward network from University of Bonn renders novel views at 40 FPS from just three cameras, using Delaunay triangulation and depth-guided fusion.
A new paper shows SHAP, Breiman importance, and Knockoffs all extrapolate on correlated data, and proposes Gaussian-copula fixes with theoretical guarantees.
New method translates a decade-old piece of pure mathematics into a fast, quadratic-loss training loop for learning discrete diffusion dynamics on graphs.
A new framework called LASE-AD keeps control systems running when attackers spoof their sensors, using Bayesian inference and active probing to isolate compromised inputs.
A new certification framework proves neural networks stay correct under label poisoning, delivering tighter guarantees with 100x fewer ensemble partitions.
A Cambridge study models Country+1, Friendshoring and Reshoring on the global EV supply network and finds these localizing policies mostly increase interdependence.