in-context-learning
Tabular foundation models: teaching one model to understand many spreadsheets Lesson
A tabular foundation model is pretrained across many synthetic or real table problems so it can make useful predictions on a new spreadsheet with little or no per-dataset training.
FlowEvo turns finished workflows into callable skills News
A training-free framework accepted at COLM 2026 compiles an agent's successful workflows into reusable executable functions, stores them in a growing bank, and suppresses the ones that hurt later tasks, reaching 85.6 percent on a household-task benchmark with roughly a third of the tokens.
A robot that learns a new task from a twelve-second demo News
Generalist AI's GEN-1.5 robot foundation model can attempt an unfamiliar physical task after watching a single 3-to-12-second demonstration, with no fine-tuning at all, succeeding 59 percent of the time across ten tasks.
A robot AI that adapts to a moved camera by wiggling, not retraining News
A new method lets robot policies figure out a changed setup from a few seconds of self-directed fiddling, so they keep working when the camera or robot body changes - with no retraining.