feat(vla): add SmolVLA conditioning and experiment artifacts
This commit is contained in:
@@ -0,0 +1,194 @@
|
||||
{
|
||||
"papers": [
|
||||
{
|
||||
"bibtex_key": "chi2023diffusion",
|
||||
"title": "Diffusion Policy: Visuomotor Policy Learning via Action Diffusion",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "ho2020denoising",
|
||||
"title": "Denoising Diffusion Probabilistic Models",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "peebles2023scalable",
|
||||
"title": "Scalable Diffusion Models with Transformers",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "lipman2023flow",
|
||||
"title": "Flow Matching for Generative Modeling",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "liu2022flow",
|
||||
"title": "Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "geng2025mean",
|
||||
"title": "Mean Flows for One-step Generative Modeling",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "geng2025improved",
|
||||
"title": "Improved Mean Flows: On the Challenges of Fastforward Generative Models",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "brohan2022rt",
|
||||
"title": "RT-1: Robotics Transformer for Real-World Control at Scale",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "brohan2023rt",
|
||||
"title": "RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "kim2024openvla",
|
||||
"title": "OpenVLA: An Open-Source Vision-Language-Action Model",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "shukor2025smolvla",
|
||||
"title": "SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "black2024pi0",
|
||||
"title": "$\\\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "pertsch2025fast",
|
||||
"title": "FAST: Efficient Action Tokenization for Vision-Language-Action Models",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "zhao2023learning",
|
||||
"title": "Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "he2016deep",
|
||||
"title": "Deep Residual Learning for Image Recognition",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "vaswani2017attention",
|
||||
"title": "Attention Is All You Need",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"bibtex_key": "kimi2026attention",
|
||||
"title": "Attention Residuals",
|
||||
"year": null,
|
||||
"abstract": "Verified from arXiv/direct web sources during drafting.",
|
||||
"authors": [
|
||||
{
|
||||
"name": "see refs.bib"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"min_cite_paper_count": 15,
|
||||
"n_total": 17,
|
||||
"note": "Manual citation pool constructed after Exa discovery; Semantic Scholar key was not visible in shell and unauthenticated S2 was rate-limited."
|
||||
}
|
||||
Reference in New Issue
Block a user