How Should a Camera-First AI Agent Work?

cs.AI, cs.HC, cs.LO

Submitted: 2026-10-10

Updated: 2026-10-14

Comments: 8 pages, 4 figures, 3 tables. Position/contract paper on time-critical camera-first agents (systems/timing).Primary cs.AI;

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• AutoMix: Automatically Mixing Language Models
• Token Merging: Your ViT But Faster
• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• Moshi: a speech-text foundation model for real-time dialogue
• Adaptive Computation Time for Recurrent Neural Networks
• The Platonic Representation Hypothesis
• VisionClaw: Always-On AI Agents through Smart Glasses
• Recurrent Models of Visual Attention
• RouteLLM: Learning to Route LLMs with Preference Data
• DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
• Mixture-of-Depths: Dynamically allocating compute in transformer-based language models
• Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
• BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks
• Qwen2.5-Omni Technical Report

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
• Agents' Last Exam
• 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