Emergent Specialization in Populations of Self-Supervised Collaborative Vision Experts Without a Shared Gate or Cross-Agent Gradients
cs.AI, cs.CV, cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Terminology
Sources
- Cosmos World Foundation Model Platform for Physical AI
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Emergent Tool Use From Multi-Agent Autocurricula
- eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
- RT-1: Robotics Transformer for Real-World Control at Scale
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- DiPaCo: Distributed Path Composition
- HDEE: Heterogeneous Domain Expert Ensemble
- Scaling Diffusion Transformers to 16 Billion Parameters
- Scaling Expert Language Models with Unsupervised Domain Discovery
- Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models
- Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts
- Decoupled Weight Decay Regularization
- DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
- DINOv3
- Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
- GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection