Skip to content
Agientry
ZH
← Back to Videos

Decision 3.0: Open Multimodal Foundation Decision Models

Loading video
Loading video

vLLM-SR releases Decision 3.0, an open multimodal foundation decision-model family spanning 0.6B-27B that tops both Jev Decision Index boards on a new Pareto frontier, with weights open on Hugging Face.

MultimodalFoundation ModelsDecision ModelOpen SourceLLM
Category: research
Author: @XunzhuoLiu
Date: 2026-10-11T00:00:00
Duration: 60.483s
Source: https://x.com/XunzhuoLiu/status/2109207207284027737
Reference: https://huggingface.co/collections/vllm-sr/decision-30

Related Videos

PixelUMM: Pixel-Space Image and Video Model
0:29

PixelUMM: Pixel-Space Image and Video Model

@CongWei1230 · 99 views · 2026-10-01
NVIDIAPixelUMM
Mistral Large 4: a 1T-parameter natively multimodal model
0:17

Mistral Large 4: a 1T-parameter natively multimodal model

@MistralAI · 544 views · 2026-10-06
MistralLMM
Jev v1.13: A Non-LLM Model Dodging Rockets by Probability
0:39

Jev v1.13: A Non-LLM Model Dodging Rockets by Probability

@atomic_chat_hq · 570 views · 2026-09-17
Decision ModelNon-LLM
ACE-Data-0 synchronized multimodal embodied dataset
2:15

ACE-Data-0 synchronized multimodal embodied dataset

@yukangcao · 1.7k views · 2026-07-31
ACEACE-Data-0
Idol Generates One Million Splats in Three Seconds
0:45

Idol Generates One Million Splats in Three Seconds

@speridlabs · 152 views · 2026-10-29
Image-to-3D3D Diffusion
A Multi-Character Audio-Video Generation Pipeline
6:43

A Multi-Character Audio-Video Generation Pipeline

@nakazakifam · 140 views · 2026-10-31
Video GenerationMultimodal

As an Amazon Associate, we earn from qualifying purchases.