Search Results for author:
Found 15 papers, 1 papers with code
Strategies to Improve Few-shot Learning for Intent Classification and Slot-Filling
Intent classification (IC) and slot filling (SF) are two fundamental tasks in modern Natural Language Understanding (NLU) systems.
Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models
Recent text-to-image generative models such as Stable Diffusion are extremely adept at mimicking and generating copyrighted content, raising concerns amongst artists that their unique styles may be improperly copied.
Topic Segmentation of Semi-Structured and Unstructured Conversational Datasets using Language Models
However, current works on topic segmentation often focus on segmentation of structured texts.
On Surgical Fine-tuning for Language Encoders
We show evidence that for different downstream language tasks, fine-tuning only a subset of layers is sufficient to obtain performance that is close to and often better than fine-tuning all the layers in the language encoder.
Localizing and Editing Knowledge in Text-to-Image Generative Models
We adapt Causal Mediation Analysis for text-to-image models and trace knowledge about distinct visual attributes to various (causal) components in the (i) UNet and (ii) text-encoder of the diffusion model.
EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods
From both the human study and automated evaluation, we find that: (i) Instruct-Pix2Pix, Null-Text and SINE are the top-performing methods averaged across different edit types, however {\it only} Instruct-Pix2Pix and Null-Text are able to preserve original image properties; (ii) Most of the editing methods fail at edits involving spatial operations (e. g., changing the position of an object).
Augmenting CLIP with Improved Visio-Linguistic Reasoning
On the challenging Winoground compositional reasoning benchmark, our method improves the absolute visio-linguistic performance of different CLIP models by up to 7%, while on the ARO dataset, our method improves the visio-linguistic performance by upto 3%.
Strong Baselines for Parameter Efficient Few-Shot Fine-tuning
Through our controlled empirical study, we have two main findings: (i) Fine-tuning just the LayerNorm parameters (which we call LN-Tune) during few-shot adaptation is an extremely strong baseline across ViTs pre-trained with both self-supervised and supervised objectives, (ii) For self-supervised ViTs, we find that simply learning a set of scaling parameters for each attention matrix (which we call AttnScale) along with a domain-residual adapter (DRA) module leads to state-of-the-art performance (while being $\sim\!$ 9$\times$ more parameter-efficient) on MD.
Topic Segmentation in the Wild: Towards Segmentation of Semi-structured & Unstructured Chats
Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks.
On Hard Episodes in Meta-Learning
To address the issue of sub-par performance on hard episodes, we investigate and benchmark different meta-training strategies based on adversarial training and curriculum learning.
Semi-Supervised Few-Shot Intent Classification and Slot Filling
Intent classification (IC) and slot filling (SF) are two fundamental tasks in modern Natural Language Understanding (NLU) systems.
Influence Functions in Deep Learning Are Fragile
Influence functions approximate the effect of training samples in test-time predictions and have a wide variety of applications in machine learning interpretability and uncertainty estimation.
Privacy Leakage Avoidance with Switching Ensembles
We consider membership inference attacks, one of the main privacy issues in machine learning.
On Second-Order Group Influence Functions for Black-Box Predictions
Often we want to identify an influential group of training samples in a particular test prediction for a given machine learning model.
Membership Model Inversion Attacks for Deep Networks
With the increasing adoption of AI, inherent security and privacy vulnerabilities formachine learning systems are being discovered.
