Heterogeneous visual agents form shared symbols via decentralized Metropolis-Hastings captioning, where encoder similarity shapes the content and symmetry of the resulting language.
Generative emergent communication: Large language model is a collective world model,
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
A decentralized collective world model integrates predictive coding with bidirectional communication to achieve simultaneous symbol emergence and coordination, outperforming non-communicative baselines in a two-agent trajectory task under divergent perceptions.
Post-training reweights a pretrained model's behavior distribution either within its existing accessible support (elicitation) or by expanding that support (creation), with both SFT and RL acting as free-energy minimization under different signals.
SANEmerg enables emergent communication among bounded-intelligence AI agents for semantic-aware task fulfillment in AgentNet systems via a bandwidth-adaptable importance filter and MDL-based complexity regularizer.
LLMs approximate human patterns in beauty-emotion links and image feature priorities but diverge in emotional response distributions and especially in beauty-bodily sensation relationships.
citing papers explorer
-
Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning
Heterogeneous visual agents form shared symbols via decentralized Metropolis-Hastings captioning, where encoder similarity shapes the content and symmetry of the resulting language.
-
Decentralized Collective World Model for Emergent Communication and Coordination
A decentralized collective world model integrates predictive coding with bidirectional communication to achieve simultaneous symbol emergence and coordination, outperforming non-communicative baselines in a two-agent trajectory task under divergent perceptions.
-
On Distinguishing Capability Elicitation from Capability Creation in Post-Training: A Free-Energy Perspective
Post-training reweights a pretrained model's behavior distribution either within its existing accessible support (elicitation) or by expanding that support (creation), with both SFT and RL acting as free-energy minimization under different signals.
-
SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking
SANEmerg enables emergent communication among bounded-intelligence AI agents for semantic-aware task fulfillment in AgentNet systems via a bandwidth-adaptable importance filter and MDL-based complexity regularizer.
-
Interoceptive Divergence in Aesthetic Evaluation and Implications for Human-AI Alignment
LLMs approximate human patterns in beauty-emotion links and image feature priorities but diverge in emotional response distributions and especially in beauty-bodily sensation relationships.