Search Results for author:
Found 8 papers, 6 papers with code
Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
Vision-language models (VLMs) are trained for thousands of GPU hours on carefully curated web datasets.
Think before you speak: Training Language Models With Pause Tokens
Language models generate responses by producing a series of tokens in immediate succession: the $(K+1)^{th}$ token is an outcome of manipulating $K$ hidden vectors per layer, one vector per preceding token.
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
However, naively removing all such data could also be wasteful, as it throws away images that contain visual features (in addition to overlapping text).
Finetune like you pretrain: Improved finetuning of zero-shot vision models
In total, these benchmarks establish contrastive finetuning as a simple, intuitive, and state-of-the-art approach for supervised finetuning of image-text models like CLIP.
Test-Time Adaptation via Conjugate Pseudo-labels
In this paper, we start by presenting a surprising phenomenon: if we attempt to meta-learn the best possible TTA loss over a wide class of functions, then we recover a function that is remarkably similar to (a temperature-scaled version of) the softmax-entropy employed by TENT.
MET: Masked Encoding for Tabular Data
Typical contrastive learning based SSL methods require instance-wise data augmentations which are difficult to design for unstructured tabular data.
PAL : Pretext-based Active Learning
To counter the paucity of data, we also deploy another head on the scoring network for regularization via multi-task learning and use an unusual self-balancing hybrid scoring function.
DROCC: Deep Robust One-Class Classification
Classical approaches for one-class problems such as one-class SVM and isolation forest require careful feature engineering when applied to structured domains like images.
Ranked #3 on
Anomaly Detection
on UEA time-series datasets
