Related papers: PLAID: An Efficient Engine for Late Interaction Re…
Currently, pre-trained models can be considered the default choice for a wide range of NLP tasks. Despite their SoTA results, there is practical evidence that these models may require a different number of computing layers for different…
Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…
Developing robotic manipulation policies is iterative and hypothesis-driven: researchers test tactile sensing, gripper geometries, and sensor placements through real-world data collection and training. Yet even minor end-effector changes…
Retrieving relevant evidence from visually rich documents such as textbooks, technical reports, and manuals is challenging due to long context, complex layouts, and weak lexical overlap between user questions and supporting pages. We…
We address the important problem of generalizing robotic rearrangement to clutter without any explicit object models. We first generate over 650K cluttered scenes - orders of magnitude more than prior work - in diverse everyday…
Large Language Model (LLM)-based passage expansion has shown promise for enhancing first-stage retrieval, but often underperforms with dense retrievers due to semantic drift and misalignment with their pretrained semantic space. Beyond…
Dynamic early exiting has been proven to improve the inference speed of the pre-trained language model like BERT. However, all samples must go through all consecutive layers before early exiting and more complex samples usually go through…
Self-attention is a key enabler of state-of-art accuracy for various transformer-based Natural Language Processing models. This attention mechanism calculates a correlation score for each word with respect to the other words in a sentence.…
While numerous methods achieving remarkable performance exist in the Object Detection literature, addressing data distribution shifts remains challenging. Continual Learning (CL) offers solutions to this issue, enabling models to adapt to…
With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the model throughput and efficiency, especially for the long…
Pre-trained language models achieve superior performance but are computationally expensive. Techniques such as pruning and knowledge distillation have been developed to reduce their sizes and latencies. In this work, we propose a structured…
In this paper, we report our methods and experiments for the TREC Conversational Assistance Track (CAsT) 2022. In this work, we aim to reproduce multi-stage retrieval pipelines and explore one of the potential benefits of involving…
In the world of deep learning, Transformer models have become very significant, leading to improvements in many areas from understanding language to recognizing images, covering a wide range of applications. Despite their success, the…
High throughput serving of large language models (LLMs) requires batching sufficiently many requests at a time. However, existing systems struggle because the key-value cache (KV cache) memory for each request is huge and grows and shrinks…
Language identification is the task of automatically determining the identity of a language conveyed by a spoken segment. It has a profound impact on the multilingual interoperability of an intelligent speech system. Despite language…
The Text-to-Video Retrieval (T2VR) task aims to retrieve unlabeled videos by textual queries with the same semantic meanings. Recent CLIP-based approaches have explored two frameworks: Two-Tower versus Single-Tower framework, yet the former…
Recently, large pre-trained models have significantly improved the performance of various Natural LanguageProcessing (NLP) tasks but they are expensive to serve due to long serving latency and large memory usage. To compress these models,…
Neural information retrieval systems typically use a cascading pipeline, in which a first-stage model retrieves a candidate set of documents and one or more subsequent stages re-rank this set using contextualized language models such as…
This work investigates an important phenomenon in centroid-based deep clustering (DC) algorithms: Performance quickly saturates after a period of rapid early gains. Practitioners commonly address early saturation with periodic reclustering,…
Conversational recommender systems proactively query users with relevant "key terms" and leverage the feedback to elicit users' preferences for personalized recommendations. Conversational contextual bandits, a prevalent approach in this…