UniMaia demonstrates feasible prompt-conditioned control of a frozen Lc0 chess policy network via text encoder and conditioning, achieving SOTA expected accuracy on prompt benchmarks while remaining competitive on human move prediction.
Table 26 shows that all configurations perform similarly
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
UniMaia: Steering Chess Policies with Language for Human-like Play
UniMaia demonstrates feasible prompt-conditioned control of a frozen Lc0 chess policy network via text encoder and conditioning, achieving SOTA expected accuracy on prompt benchmarks while remaining competitive on human move prediction.