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.
Compositional semantic parsing on semi-structured tables
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 8roles
method 1polarities
use method 1representative citing papers
NeuralEmu uses machine learning trained on real 5G telemetry to predict resource blocks and modulation for multiple users, cutting emulation error by 51-57% versus prior tools for web, video, and gaming metrics.
FinBERT adapts BERT to the financial domain and outperforms prior state-of-the-art methods on financial sentiment analysis tasks.
Training-free graph method with LM edge scoring and max-regret path cover recovers 95% successor edges on Glossa wrap-around layouts vs 50% for XY-cut and 88% on OmniDocBench multi-column vs 75% XY-cut.
Multi-response training retains multiple responses per prompt to reduce uncertainty about the conditional output distribution, yielding improved distributional generalization especially in high response-diversity and low prompt-redundancy regimes.
FoNE encodes numbers as single tokens via Fourier features and outperforms subword and digit-wise embeddings on addition, subtraction, and multiplication with far less data.
Presents REMOD, a graph-based supervised method for extracting semantic relations between entities in text to support modeling of online discourse and potential misinformation.
DenoGrad refines noisy tabular and time-series data by optimizing inputs via gradients from a fixed model, yielding better downstream predictions on ten real-world datasets while preserving data statistics.
citing papers explorer
-
NeuralEmu: in situ Measurement-Driven, ML-based, High-Fidelity 5G Network Emulation
NeuralEmu uses machine learning trained on real 5G telemetry to predict resource blocks and modulation for multiple users, cutting emulation error by 51-57% versus prior tools for web, video, and gaming metrics.