Multimodal open d1 decision models for the edge
Summary
The paper presents multimodal open decision models designed for deployment on edge devices, addressing efficient inference and real-world decision-making under resource constraints.
Similar Articles
Open d1: Edge decision models for text, vision, and audio (6 minute read)
Liquid AI 发布了 d1 决策模型家族的两款开放权重模型 d1-3B 和 d1-omni-600M，支持文本、视觉和音频模态，通过单次前向传递直接输出答案，在 Decision Index 上超越同规模模型并可在 NVIDIA Jetson 边缘设备上实现实时推理。
Decision 3.0: open, multimodal decision models from 0.6B to 27B. Ranks #1 on both Jev Decision Index boards
The vLLM Semantic Router team released Decision 3.0 (d3), an open-source (Apache-2.0) multimodal decision model family from 0.6B to 27B that handles text, images, and video, ranking #1 on both Jev Decision Index boards with zero-shot video performance.
d3-edge (0.6B) fine-tuned outperformed d3 (27B) decision model
A 0.6B parameter d3-edge model, fine-tuned with SFT + LoRA on a few thousand examples, outperformed the 27B d3 decision model on typed decisions and nearly matched it on Banking77, highlighting the value of fine-tuning small specialized models over large general-purpose ones.
Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling
Intern-Decision introduces a family of compact (0.8B/2B/4B) multimodal decision models using an autoregressive masked language modeling objective to output structured choices with probabilities in a single causal forward pass, achieving 90.02% average accuracy across seven benchmarks with low latency for interactive agents.
@omarsar0: Decision models are going multimodal. Drex Max looks really strong. It can make fast decisions straight from screenshot…
Nace AI 发布多模态决策模型 Drex Max，可直接从截图、屏幕录像、扫描文档和图表中快速做出决策，适用于 computer-use 和 browser-use 智能体。该模型在 Mind2Web 上达到 88.3%，Decision Index 得分 67.6，推理速度为 34ms/决策。