TAMO is a transformer policy pretrained with RL to perform amortized multi-objective optimization in-context, delivering 50-1000x faster proposals while matching Pareto quality on benchmarks.
Mean with 95% confidence intervals computed across 30 runs with random initial observations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
In-Context Multi-Objective Optimization
TAMO is a transformer policy pretrained with RL to perform amortized multi-objective optimization in-context, delivering 50-1000x faster proposals while matching Pareto quality on benchmarks.