Search Results for author:
Found 11 papers, 5 papers with code
A Scaling Law for Syn-to-Real Transfer: How Much Is Your Pre-training Effective?
Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks.
A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?
Synthetic-to-real transfer learning is a framework in which a synthetically generated dataset is used to pre-train a model to improve its performance on real vision tasks.
Real-time dynamics of Chern-Simons fluctuations near a critical point
We interpret this maximum in terms of the growth of critical fluctuations near the critical point, and draw analogies between the massive Schwinger model, QCD near the critical point, and ferroelectrics near the Curie point.
High Energy Physics - Phenomenology High Energy Physics - Lattice Nuclear Theory Quantum Physics
Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score
Motivated by the fact that detecting these rare relations can be critical in real-world applications, this paper introduces a novel integrated framework of classification and ranking to resolve the class imbalance problem in scene graph parsing.
A POS Tagging Model Adapted to Learner English
Based on the discussion of possible causes of POS tagging errors in learner English, we show that deep neural models are particularly suitable for this.
Alpha-divergence bridges maximum likelihood and reinforcement learning in neural sequence generation
Neural sequence generation is commonly approached by using maximum- likelihood (ML) estimation or reinforcement learning (RL).
Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions
In this paper, we propose the first comprehensive system that can handle unconstrained spoken language and is able to effectively resolve ambiguity in spoken instructions.
Japanese Sentence Compression with a Large Training Dataset
In English, high-quality sentence compression models by deleting words have been trained on automatically created large training datasets.
Neural Sequence Model Training via $α$-divergence Minimization
We propose a new neural sequence model training method in which the objective function is defined by $\alpha$-divergence.
Controlling Output Length in Neural Encoder-Decoders
Neural encoder-decoder models have shown great success in many sequence generation tasks.
