#Model Efficiency

3 articles with this tag

Mobius-v0: Efficient AI Reasoning
AI Research

Mobius-v0: Efficient AI Reasoning

The Mobius-v0 architecture redefines LLM efficiency by separating knowledge and reasoning, leading to reduced training data needs and faster inference.

about 2 months ago
Rethinking VLM Token Reduction
AI Research

Rethinking VLM Token Reduction

Reroute transforms VLM token reduction from irreversible pruning to recoverable routing, improving grounding performance without sacrificing efficiency.

4 months ago
TaskGround: Bridging Scene Context and Action
AI Research

TaskGround: Bridging Scene Context and Action

TaskGround revolutionizes household AI by enabling compact models to interpret complex scenes, infer task structures, and act effectively, drastically improving performance and reducing costs.

5 months ago