A survey proposes a novel 3D taxonomy classifying drifts into time stream, data stream, and model stream categories to unify research on non-stationary autonomous learning.
arXiv preprint arXiv:2502.07620 (2025)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 4polarities
background 4representative citing papers
XrayClaw deploys cooperative-competitive multi-agent alignment and Competitive Preference Optimization to raise diagnostic accuracy, reasoning fidelity, and generalization on chest X-ray benchmarks.
BVME uses variational Gaussian message encoding with KL regularization to maintain or improve multi-agent coordination performance while using 67-83% fewer message dimensions than naive compression on SMAC and MPE benchmarks.
APO framework aligns multi-source MLLM reasoning under concept drift by using inter-model divergences as negative constraints via supervised bootstrapping and multi-negative Plackett-Luce optimization, with a 7B model outperforming proprietary sources on chest X-ray tasks and a new CXR-MAX benchmark
HIBCG learns group-aware sparse coordination graphs in MARL using graph information bottleneck with a block-diagonal prior for edge selection and water-filling for capacity allocation.
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.
citing papers explorer
-
Autonomous Drift Learning in Data Streams: A Unified Perspective
A survey proposes a novel 3D taxonomy classifying drifts into time stream, data stream, and model stream categories to unify research on non-stationary autonomous learning.
-
XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis
XrayClaw deploys cooperative-competitive multi-agent alignment and Competitive Preference Optimization to raise diagnostic accuracy, reasoning fidelity, and generalization on chest X-ray benchmarks.
-
Bandwidth-constrained Variational Message Encoding for Cooperative Multi-agent Reinforcement Learning
BVME uses variational Gaussian message encoding with KL regularization to maintain or improve multi-agent coordination performance while using 67-83% fewer message dimensions than naive compression on SMAC and MPE benchmarks.
-
Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments
APO framework aligns multi-source MLLM reasoning under concept drift by using inter-model divergences as negative constraints via supervised bootstrapping and multi-negative Plackett-Luce optimization, with a 7B model outperforming proprietary sources on chest X-ray tasks and a new CXR-MAX benchmark
-
Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning
HIBCG learns group-aware sparse coordination graphs in MARL using graph information bottleneck with a block-diagonal prior for edge selection and water-filling for capacity allocation.
-
Towards Robust Endogenous Reasoning: Unifying Drift Adaptation in Non-Stationary Tuning
CPO++ adapts reinforcement fine-tuning of MLLMs to endogenous multi-modal concept drift through counterfactual reasoning and preference optimization, yielding better coherence and cross-domain robustness in safety-critical settings.