Structured per-agent randomness via ranked masking in attention allows symmetric agents to break ties and coordinate, achieving perfect success on symmetric tasks where deterministic policies fail and enabling zero-shot transfer across team sizes.
Artificial Intelligence , volume =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Di-COT is an unsupervised contrastive method that stochastically partitions time-series windows into overlapping sub-blocks to learn representations without augmentation, reporting SOTA results on classification and transfer tasks across multiple benchmarks while cutting training time.
The paper proposes persistent caching of component data and adapted branching heuristics to amortize computation in incremental #SAT, showing performance gains on argumentation and soft core problems.
citing papers explorer
-
Randomness is sometimes necessary for coordination
Structured per-agent randomness via ranked masking in attention allows symmetric agents to break ties and coordinate, achieving perfect success on symmetric tasks where deterministic policies fail and enabling zero-shot transfer across team sizes.
-
Divide and Contrast: Learning Robust Temporal Features without Augmentation
Di-COT is an unsupervised contrastive method that stochastically partitions time-series windows into overlapping sub-blocks to learn representations without augmentation, reporting SOTA results on classification and transfer tasks across multiple benchmarks while cutting training time.
-
Efficient Incremental #SAT via Cross-Instance Knowledge Reuse
The paper proposes persistent caching of component data and adapted branching heuristics to amortize computation in incremental #SAT, showing performance gains on argumentation and soft core problems.