Related papers: Response-free item difficulty modelling for multip…

Recent advances in large language and vision-language models have enabled zero-shot inference, allowing models to solve new tasks without task-specific training. Various adaptation techniques such as prompt engineering, In-Context Learning…

Recent advancements in imitation learning have led to transformer-based behavior foundation models (BFMs) that enable multi-modal, human-like control for humanoid agents. While excelling at zero-shot generation of robust behaviors, BFMs…

Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task. Most existing works are dedicated to establishing specialized modules to identify…

Model diffing is the study of how fine-tuning changes a model's representations and internal algorithms. Many behaviors of interest are introduced during fine-tuning, and model diffing offers a promising lens to interpret such behaviors.…

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well. Machine listening research often suffers from limited labeled data problem, as human annotations are costly to acquire, and…

Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams such as continual learning. One powerful approach that has…

The Transformer model has a tendency to overfit various aspects of the training data, such as the overall sequence length. We study elementary string edit functions using a defined set of error indicators to interpret the behaviour of the…

Pre-training a model to learn transferable video-text representation for retrieval has attracted a lot of attention in recent years. Previous dominant works mainly adopt two separate encoders for efficient retrieval, but ignore local…

In NLP, a large volume of tasks involve pairwise comparison between two sequences (e.g. sentence similarity and paraphrase identification). Predominantly, two formulations are used for sentence-pair tasks: bi-encoders and cross-encoders.…

Foundation language models learn from their finetuning input context in different ways. In this paper, we reformulate inputs during finetuning for challenging translation tasks, leveraging model strengths from pretraining in novel ways to…

We propose a practical instant question answering (QA) system on product pages of ecommerce services, where for each user query, relevant community question answer (CQA) pairs are retrieved. User queries and CQA pairs differ significantly…

Recent years have witnessed a surge in the number of large language models (LLMs), yet efficiently managing and utilizing these vast resources remains a significant challenge. In this work, we explore how to learn compact representations of…

Modern object detectors have taken the advantages of backbone networks pre-trained on large scale datasets. Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain…

Extracting dense representations for terms and phrases is a task of great importance for knowledge discovery platforms targeting highly-technical fields. Dense representations are used as features for downstream components and have multiple…

Inference tasks such as answer sentence selection (AS2) or fact verification are typically solved by fine-tuning transformer-based models as individual sentence-pair classifiers. Recent studies show that these tasks benefit from modeling…

We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve…

Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling de novo algorithm discovery without relying on human-written code. However, applying this paradigm to Transformer is…

The ability for robots to transfer their learned knowledge to new tasks -- where data is scarce -- is a fundamental challenge for successful robot learning. While fine-tuning has been well-studied as a simple but effective transfer approach…

Fine-tuning is a popular way of exploiting knowledge contained in a pre-trained convolutional network for a new visual recognition task. However, the orthogonal setting of transferring knowledge from a pretrained network to a visually…