Skip to content
#small language model Book Open access

MBench: Rebuilding Human-Aligned Zero-Shot Evaluation for Motion-Language Models

Nov 2026 · Proceedings of the 34th ACM International Conference on Multimedia · 0 citations · 13 references

TL;DR

This work introduces MBench, a comprehensive benchmark for zero-shot compositional motion understanding, and introduces a systematic scaling strategy—synchronously expanding training data diversity and model capacity across architectures like TMR and MoPa—to confirm that synergistically scaling data and capacity is indispensable for robust, human-aligned open-world generalization.

Abstract

Despite rapid progress in text-driven motion retrieval and generation, effective evaluation remains a critical bottleneck. Existing benchmarks rely on small-scale, in-domain test sets and legacy metrics that fail to assess zero-shot performance or the emergent generalization capabilities unlocked by scaling. To resolve this, we introduce MBench, a comprehensive benchmark for zero-shot compositional motion understanding. Supported by a low-cost markerless capture pipeline, MBench provides 20K diverse motions and a curated human-preference set of 373 motion samples. Using this dataset, we expose the limitations of legacy metrics in zero-shot generalization and develop a human-aligned evaluation protocol. To overcome the vulnerabilities diagnosed by MBench, we introduce a systematic scaling strategy—synchronously expanding training data diversity (up to 200 hours) and model capacity across architectures like TMR and MoPa. Consequently, our 300M-parameter ScaTMR establishes a new state-of-the-art for zero-shot generalization—dominating both MBench R-Precision and human preference hit rates—while our scaled MoPa variant sets new in-domain records on HumanML3D. Ultimately, these results confirm that synergistically scaling data and capacity is indispensable for robust, human-aligned open-world generalization.

Read PDF

Similar papers

#small language model Dataset Open access Oct 2026

Socratic guiding questions in synthetic arithmetic data: matched LoRA runs (revision v2)

Supporting data, adapters, predictions and code for the article *Low-Cost LoRA Fine-Tuning of Small Language Models for Multi-Step Arithmetic Reasoning* by Jake O'Grady, Asena Isik Gürhan, Chee Fong Ting and Effirul Ramlan (University of Galway). We generated 20,000 GSM8K-derived arithmetic problems with step-by-step s...

O'Grady, Jake, Gürhan, Asena Isik, Chee, Fong Ting et al. · 465 citations
#computer vision Open access Jun 2016

Software Development in Startup Companies: The Greenfield Startup Model

The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.

Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al. · 178 citations · ⚡14
#computer vision Open access Oct 2016

Software Startups - A Research Agenda

Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.

M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al. · 157 citations · ⚡17
#machine learning Review Open access Oct 2016

“Failures” to be celebrated: an analysis of major pivots of software startups

This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.

Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al. · 127 citations · ⚡15
#computer vision Review Open access May 2015

A survey study on major technical barriers affecting the decision to adopt cloud services

The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.

Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al. · 111 citations · ⚡8
#large language models Review Open access Nov 2020

Status of the WHO recommended timing and frequency of antenatal care visits in Northern Bangladesh

Objective There is dearth of information on the timeliness of antenatal care (ANC) uptake. This study aimed to determine the timely ANC uptake by a medically trained provider (MTP) as per the World Health Organization (WHO) recommendations and the country guideline. Methods Cross-sectional survey was done with 2,731 wo...

B. Sarker, Musfikur Rahman, T. Rahman et al. · 89 citations · ⚡7

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.