From Single-Shot QA to Continuous Perception: Revisiting the Energy Composition and Optimization Boundary of Edge VLMs
cs.CV, cs.AI
Submitted: 2026-10-07
Updated: 2026-10-07
Comments: 5 pages, 3 figures. Accepted at IEEE International Conference on Data Mining 2026 Teen Research Track
Code: https://github.com/TensorAuto/OpenTau
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Inference
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
- LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics
- Rethinking Small VLM Quantization: From Component-Wise Analysis to Hardware-Aware Edge Deployment
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs