跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-15AI 評分37

Intern-Decision:以自回歸掩碼語言建模實現高效多模態決策

Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling

AI 導讀

Intern-Decision 提出 0.8B、2B 和 4B 多模態決策模型,可根據文字及可選圖片輸出結構化選擇和候選項目概率。4B 模型在七個評測套件的未加權平均準確率為 90.02%,高於 Jev v1.13.0 的 88.74%;固定 289-token、含三個欄位的請求在單張 RTX 4090 上平均延遲為 44.16 ms。

正文

Published on Oct 15

Authors:

,

,

,

,

,

,

,

,

Abstract

Intern-Decision introduces compact multimodal models that output structured choices with probabilities via masked language modeling, achieving high accuracy and low latency for interactive agents.

Interactive agents repeatedly choose among a finite set of actions, labels, or ordinal outcomes. Generating a free-form response for each choice adds latency and complicates the interface between a model and its environment. We present Intern-Decision, a family of 0.8B, 2B, and 4B multimodal decision models that return structured choices and candidate probabilities from text and optional images. Our autoregressive masked language modeling objective places one decision placeholder per field in a complete assistant JSON skeleton. Ground-truth symbols appear only in supervision, while all fields are evaluated in a single causal forward pass using the backbone's native language-model head. The 4B model achieves a 90.02% unweighted average accuracy across seven evaluation suites, compared with 88.74% for Jev v1.13.0. For a fixed 289-token request with three fields on one RTX 4090, mean latency is 44.16 ms for the 4B model and approximately 33--34 ms for the smaller models. On a separate 96-case known-distribution pilot, temperature scaling reduces expected multiclass Brier from 0.628 to 0.550 and expected calibration error from 0.213 to 0.089. A confidence-based handoff study on 111 public Jevbench-Hard items improves accuracy from 82/111 (73.87%) to 97/111 (87.39%) by routing 42 items to Atria-Dawn-Preview. We also describe qualitative game, visual interface, and browser demonstrations. These results support compact decision models as a practical component of larger agent systems.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.22131

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.22131 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.22131 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.22131 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co