ConventionPlay extends cognitive hierarchies with diverse adaptive followers and capability-limited training to achieve superior coordination efficiency in ad-hoc tasks with differentiated payoffs.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
ClickSeg3D uses a point Transformer encoder and hierarchical mask decoder with semantic embeddings to enable single-pass multi-object 3D interactive segmentation from sparse points, reporting over 20% mIoU gains versus baselines and 8-10% cross-dataset improvements with one click per instance.
AIM applies modality-specific masks to balance stability and plasticity in asymmetric VLMs, achieving SOTA average performance and reduced forgetting on continual VQA v2 and GQA while preserving generalization to novel compositions.
Positive-rate probabilistic cellular automata admitting stationary Bernoulli measures are exponentially ergodic with logarithmic mixing times for finite regions.
citing papers explorer
-
ConventionPlay: Capability-Limited Training for Robust Ad-Hoc Collaboration
ConventionPlay extends cognitive hierarchies with diverse adaptive followers and capability-limited training to achieve superior coordination efficiency in ad-hoc tasks with differentiated payoffs.
-
ClickSeg3D: Few-Click Interactive Segmentation via Semantic Embeddings
ClickSeg3D uses a point Transformer encoder and hierarchical mask decoder with semantic embeddings to enable single-pass multi-object 3D interactive segmentation from sparse points, reporting over 20% mIoU gains versus baselines and 8-10% cross-dataset improvements with one click per instance.
-
AIM: Asymmetric Information Masking for Visual Question Answering Continual Learning
AIM applies modality-specific masks to balance stability and plasticity in asymmetric VLMs, achieving SOTA average performance and reduced forgetting on continual VQA v2 and GQA while preserving generalization to novel compositions.
-
Positive-rate PCA and IPS with stationary Bernoulli measures are rapidly forgetful
Positive-rate probabilistic cellular automata admitting stationary Bernoulli measures are exponentially ergodic with logarithmic mixing times for finite regions.