HandX: Scaling Bimanual Motion and Interaction Generation
HandX presents a comprehensive foundation for bimanual hand motion synthesis including a new dataset, annotation method, and evaluation metrics for dexterous motion generation. (6 upvotes on HuggingFace)
Published on Mar 30
Authors:
,
,
,
,
,
,
,
,
,
Abstract
HandX presents a comprehensive foundation for bimanual hand motion synthesis including a new dataset, annotation method, and evaluation metrics for dexterous motion generation.
AI-generated summary
Synthesizing human motion has advanced rapidly, yet realistic hand motion and bimanual interaction remain underexplored. Whole-body models often miss the fine-grained cues that drive dexterous behavior, finger articulation, contact timing, and inter-hand coordination, and existing resources lack high-fidelity bimanual sequences that capture nuanced finger dynamics and collaboration. To fill this gap, we present HandX, a unified foundation spanning data, annotation, and evaluation. We consolidate and filter existing datasets for quality, and collect a new motion-capture dataset targeting underrepresented bimanual interactions with detailed finger dynamics. For scalable annotation, we introduce a decoupled strategy that extracts representative motion features, e.g., contact events and finger flexion, and then leverages reasoning from large language models to produce fine-grained, semantically rich descriptions aligned with these features. Building on the resulting data and annotations, we benchmark diffusion and autoregressive models with versatile conditioning modes. Experiments demonstrate high-quality dexterous motion generation, supported by our newly proposed hand-focused metrics. We further observe clear scaling trends: larger models trained on larger, higher-quality datasets produce more semantically coherent bimanual motion. Our dataset is released to support future research.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2603.28766
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/2603.28766 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/2603.28766 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/2603.28766 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.
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
researchpaperarxiv
Setting up a hugo static site hosted with Porkbun
<h2> Content generation </h2> <p>This is a static site generated with <a href="https://gohugo.io/getting-started/quick-start/" rel="noopener noreferrer">hugo</a> with the PaperMod theme. I wanted an easy to use static site generator. I considered <a href="https://jekyllrb.com/" rel="noopener noreferrer">Jekyll</a> and believe it to be a good choice for static sites. There seemed to be slightly more themes I liked with hugo so I went with that. That's a pretty superficial choice but I also don't plan on hacking on the site generation itself so I was agnostic to the Go versus Ruby choice.</p> <h2> Domain hosting </h2> <p>This site uses <a href="https://porkbun.com" rel="noopener noreferrer">porkbun</a> for a domain host. I chose it not least because I do enjoy porkbuns. They also listed stat
UTEP research seeks to make AI speech more natural - KTSM 9 News
<a href="https://news.google.com/rss/articles/CBMilgFBVV95cUxOUXU5QnZjNHp2OUY2MHpadVUydlBrVlVETzdZQmxFX2FaTEo0WjhUT29FckJMY1FXXy1zZFdrY3FScDRScnBsbDRSakhtXzdhdWFLa0N4TFdvMFFRVHF1VG5xdGw3VlNxeXBITThfY3Y0SDBDbDBIcXRoRklGLUpFVFpoSUc3YUdzZnE1Nk1CX0x3U1dlaEHSAZsBQVVfeXFMUFlfcVVpLWNYd3oxTnB3cmt4YXprOWl6UFhQTS02WUNra21hTFllc19BUm5sTEViamlzS2lheFAzR2g0UWZVaHRmZmhsWV9RU0NuR2t2VnhaZENHZUlVWjRPbFNPV1JHZVNLV1RkMl90QUt1YTJSMEVHQUhCQktBc00xRDhrMl9INEFEUFY0dkVjV0NEOUFYdmNwd00?oc=5" target="_blank">UTEP research seeks to make AI speech more natural</a> <font color="#6f6f6f">KTSM 9 News</font>
Exclusive | Caltech Researchers Claim Radical Compression of High-Fidelity AI Models - WSJ
<a href="https://news.google.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?oc=5" target="_blank">Exclusive | Caltech Researchers Claim Radical Compression of High-Fidelity AI Models</a> <font color="#6f6f6f">WSJ</font>
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Research Papers
Why Drug Toxicity Can’t Be Predicted in Isolation — Building EIRION with Graph Neural Networks
How we built a graph neural network that finally sees the whole play — not just the audition Every year, drugs that passed early safety tests go on to harm people in ways nobody predicted. Not because the chemistry was wrong. Not because the researchers were careless. But because we kept evaluating drugs the way a talent agent judges an actor from a solo audition tape. Isolated. Out of context. No script. No co-stars. No stage. In real theatre, a performance is never just about one actor. It depends on who they share the stage with, which scene they appear in, what the story demands at that moment. A brilliant performer in the wrong play, surrounded by the wrong cast, in the wrong context — can still wreck the whole production. That is exactly how drug toxicity works. And that is exactly t
It's Not Smarter Models — It's Cheaper Memory: TurboQuant's Real Impact, Wall Street Panic & Academic Storm
<blockquote> <p><strong>One-line summary:</strong> TurboQuant is a genuinely important engineering breakthrough — but Google's marketing, academic ethics controversy, and Wall Street's overreaction made the story far more dramatic than the technology itself.</p> </blockquote> <h2> 0. What This Article Answers </h2> <p>Google Research published TurboQuant at ICLR 2026 (<a href="https://arxiv.org/abs/2504.19874" rel="noopener noreferrer">arXiv 2504.19874</a>), claiming 6x memory compression, 8x speedup, and zero accuracy loss for LLM KV caches.</p> <p>Then, in the same week:</p> <ol> <li>Global memory stocks lost over <strong>$90 billion</strong> in market cap</li> <li>An ETH Zürich researcher publicly accused the paper of <strong>academic plagiarism and experimental fraud</strong> </li> <li
OptiMer: Optimal Distribution Vector Merging Is Better than Data Mixing for Continual Pre-Training
OptiMer enables flexible continual pre-training by decoupling data mixture ratio selection from training through post-hoc Bayesian optimization of distribution vectors extracted from individual dataset models. (1 upvotes on HuggingFace)
CARLA-Air: Fly Drones Inside a CARLA World -- A Unified Infrastructure for Air-Ground Embodied Intelligence
CARLA-Air integrates high-fidelity driving and multirotor flight simulation within a unified Unreal Engine framework, supporting joint air-ground agent modeling with photorealistic environments and multi-modal sensing capabilities. (1 upvotes on HuggingFace)
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!