HandX: Scaling Bimanual Motion and Interaction Generation

HandX: Scaling Bimanual Motion and Interaction Generation | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/handx-scaling-bimanual-motion-and-interaction-generation

stale

Proof freshness: stale
Proof status: partial
Display score: 7/10
Last proof check: 2026-03-31
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 100
Source count: 4
Coverage: 83%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID handx-scaling-bimanual-motion-and-interaction-generation | Route /signal-canvas/handx-scaling-bimanual-motion-and-interaction-generation

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/handx-scaling-bimanual-motion-and-interaction-generation

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "handx-scaling-bimanual-motion-and-interaction-generation",
    "query_text": "Summarize HandX: Scaling Bimanual Motion and Interaction Generation"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "HandX: Scaling Bimanual Motion and Interaction Generation",
  "normalized_query": "2603.28766",
  "route": "/signal-canvas/handx-scaling-bimanual-motion-and-interaction-generation",
  "paper_ref": "handx-scaling-bimanual-motion-and-interaction-generation",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 8

References: 100

Proof: Verification pending

Freshness state: computing

Source paper: HandX: Scaling Bimanual Motion and Interaction Generation

PDF: https://arxiv.org/pdf/2603.28766v1

Repository: https://github.com/handx-project/HandX

Source count: 4

Coverage: 83%

Last proof check: 2026-03-31T20:30:18.829Z

Signal Canvas receipt window

Ready for execution: HandX: Scaling Bimanual Motion and Interaction Generation

/buildability/handx-scaling-bimanual-motion-and-interaction-generation

Build Nowready

Subject: HandX: Scaling Bimanual Motion and Interaction Generation

Verdict

Build Now

Verdict is Build Now because viability and implementation proof cleared the Wave 1 scaffold thresholds.

GitHub Code Pulse

Cached

Stars

136

Health

Last commit

5/29/2026

Forks

Open repository

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
We consolidate and filter existing datasets for quality, and collect a new motion-capture dataset targeting underrepresented bimanual interactions with detailed finger dynamics.
Implicationpartial
Explicitly stated in the abstract and supported by the dataset scale table (Table 1).
Verificationpartial
partial
Evidencepartial
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.
Implicationpartial
Directly stated in the abstract as a core methodological contribution.
Verificationpartial
partial
Evidencepartial
We further observe clear scaling trends: larger models trained on larger, higher-quality datasets produce more semantically coherent bimanual motion.
Implicationpartial
Explicitly stated in the abstract and supported by a figure showing a log-linear relationship between R-precision and FLOPS.
Verificationpartial
partial
Evidencepartial
HandX (Ours) 54.2 5.9 fine-grained 485.7
Implicationpartial
Direct numeric comparison provided in Table 1, showing HandX's 'fine-grained' annotations at 485.7K vs. others with 'coarse' annotations at much lower counts.
Verificationpartial
partial
Evidencepartial
We observe that simply concatenating the three types of prompts degrades performance,e.g., the generated motion may assign right-hand movements to the left hand. To address this issue, we encode three types of prompts separately and add a learnable CLS token to each...
Implicationpartial
Described in the model architecture section, stating that simple concatenation degrades performance and the proposed separate encoding addresses this.
Verificationpartial
partial
Evidencepartial
Overall, existing datasets still lack the precision, diversity, and rich inter-hand contact needed for learning fine-grained bimanual motion from text.
Implicationpartial
Directly stated as a limitation of prior work that motivates the HandX dataset.
Verificationpartial
partial
Evidencepartial
Building on the resulting data and annotations, we benchmark diffusion and autoregressive models with versatile conditioning modes.
Implicationpartial
Stated in the abstract and supported by the model architecture description showing different conditioning inputs.
Verificationpartial
partial
Evidencepartial
We propose contact precision (Cprec), contact recall (Crec), and F1 score (CF1) to evaluate hand contact accuracy.
Implicationpartial
Explicitly described in the evaluation section as newly proposed metrics.
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

HandX: Scaling Bimanual Motion and Interaction Generation

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface