Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
Title resolution pending
9 Pith papers cite this work. Polarity classification is still indexing.
verdicts
UNVERDICTED 9representative citing papers
A double-soft-belt finger module adds translation, pitch, and roll to parallel grippers for improved in-hand manipulation at low cost.
PeerBTS augments any strategyproof peer-selection rule with a peer-prediction lottery to reward evaluation effort while preserving Bayes-Nash incentive compatibility.
Tube Diffusion Policy learns observation-conditioned feedback flows around nominal action chunks to enable fast reactive control in visual-tactile contact-rich manipulation.
A neural-mean Vecchia Gaussian process delivers competitive predictions on 2007-2016 Argo temperature data using a single global model instead of moving-window regression and separate parametric means.
Network analysis of Sarafu transactions shows modular localized circulation supported by cycles, with disassortative sub-networks, preferential attachment, and central roles for community institutions, early adopters, and women.
DiffUNet^2 is a bidirectional conditional diffusion model integrated with visual tools for probabilistic exploration of scientific time series across five evaluated datasets.
Explicit best constant computed for polyharmonic Sobolev inequality via radial regularity and classification results.
Engineering choices for tools, safety guardrails, and human oversight determine whether an internal coding agent delivers value in practice more than the underlying model quality.
citing papers explorer
-
A document is worth a structured record: Principled inductive bias design for document recognition
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
-
Belt-Finger: An Affordable Soft Belt-Driven Gripper for Dexterous In-Hand Manipulation
A double-soft-belt finger module adds translation, pitch, and roll to parallel grippers for improved in-hand manipulation at low cost.
-
PeerBTS: Incentivizing Effort in Strategyproof Peer Selection
PeerBTS augments any strategyproof peer-selection rule with a peer-prediction lottery to reward evaluation effort while preserving Bayes-Nash incentive compatibility.
-
Tube Diffusion Policy: Reactive Visual-Tactile Policy Learning for Contact-rich Manipulation
Tube Diffusion Policy learns observation-conditioned feedback flows around nominal action chunks to enable fast reactive control in visual-tactile contact-rich manipulation.
-
A Neural-Mean Vecchia Gaussian Process for Unified Argo Modeling
A neural-mean Vecchia Gaussian process delivers competitive predictions on 2007-2016 Argo temperature data using a single global model instead of moving-window regression and separate parametric means.
-
Circulation of a digital community currency
Network analysis of Sarafu transactions shows modular localized circulation supported by cycles, with disassortative sub-networks, preferential attachment, and central roles for community institutions, early adopters, and women.
-
DiffUNet^2: Bidirectional Prediction, Probabilistic Generation and Collaborative Visual Discovery for Scientific Data
DiffUNet^2 is a bidirectional conditional diffusion model integrated with visual tools for probabilistic exploration of scientific time series across five evaluated datasets.
-
Minimizers and best constants for a weighted critical Sobolev inequality involving the polyharmonic operator
Explicit best constant computed for polyharmonic Sobolev inequality via radial regularity and classification results.
-
Building an Internal Coding Agent at Zup: Lessons and Open Questions
Engineering choices for tools, safety guardrails, and human oversight determine whether an internal coding agent delivers value in practice more than the underlying model quality.