Europe
Implicit Bias of Mirror Flow on Separable Data
When the potential is separable, a simple formula allows to compute this function.
Scaling Sign Language Translation
Sign language translation (SL T) addresses the problem of translating information from a sign language in video to a spoken language in text. Existing studies, while showing progress, are often limited to narrow domains and/or few sign languages and struggle with open-domain tasks. In this paper, we push forward the frontier of SL T by scaling pretraining data, model size, and number of translation directions. We perform large-scale SL T pretraining on different data including 1) noisy multilingual Y ouTube SL T data, 2) parallel text corpora, and 3) SL T data augmented by translating video captions to other languages with off-the-shelf machine translation models. We unify different pretraining tasks with task-specific prompts under the encoder-decoder architecture, and initialize the SL T model with pretrained (m/By)T5 models across model sizes. SL T pretraining results on How2Sign and FLEURS-ASL#0 (ASL to 42 spoken languages) demonstrate the significance of data/model scaling and cross-lingual cross-modal transfer, as well as the feasibility of zero-shot SL T. We finetune the pretrained SL T models on 5 downstream open-domain SL T benchmarks covering 5 sign languages. Experiments show substantial quality improvements over the vanilla baselines, surpassing the previous state-of-the-art (SOT A) by wide margins.
Information-theoretic Limits of Online Classification with Noisy Labels
Learning from noisy data is a fundamental problem in many machine learning applications.
Provable Editing of Deep Neural Networks using Parametric Linear Relaxation
However, the problem of provably editing a DNN to satisfy a property remains challenging.
Improved Particle Approximation Error for Mean Field Neural Networks
Recent works (Chen et al., 2022; Suzuki et al., 2023b) have demonstrated In this work, we improve the dependence on logarithmic Sobolev inequality (LSI) constants in their particle approximation errors which can exponentially deteriorate with the regularization coefficient. One may consider adding Gaussian noise to the gradient descent to make the method more stable.
cdf6f8e9fd9aeaf79b6024caec24f15b-Paper-Datasets_and_Benchmarks_Track.pdf
To ensure quality, all charts and questions are handpicked, curated, and verified by human experts.
Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
HR-based orthogonal fine-tuning is equivalent to an adaptive low-rank adaptation.
