相关论文: Exploring Relational Context for Multi-Task Dense …

Many NLP tasks require processing long contexts beyond the length limit of pretrained models. In order to scale these models to longer text sequences, many efficient long-range attention variants have been proposed. Despite the abundance of…

Predictor combination aims to improve a (target) predictor of a learning task based on the (reference) predictors of potentially relevant tasks, without having access to the internals of individual predictors. We present a new predictor…

The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and…

We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense neural representations of MS-MARCO queries and passages are…

Relation extraction (RE) is a fundamental task in information extraction, whose extension to multilingual settings has been hindered by the lack of supervised resources comparable in size to large English datasets such as TACRED (Zhang et…

Recent progress has rapidly advanced our understanding of the mechanisms underlying in-context learning in modern attention-based neural networks. However, existing results focus exclusively on unimodal data; in contrast, the theoretical…

Retrieval-augmented generation (RAG) is highly sensitive to the quality of selected context, yet standard top-k retrieval often returns redundant or near-duplicate chunks that waste token budget and degrade downstream generation. We present…

This study proposes a text classification algorithm based on large language models, aiming to address the limitations of traditional methods in capturing long-range dependencies, understanding contextual semantics, and handling class…

Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce…

Multi-task reinforcement learning (MTRL) demonstrate potential for enhancing the generalization of a robot, enabling it to perform multiple tasks concurrently. However, the performance of MTRL may still be susceptible to conflicts between…

Global and local relational reasoning enable scene understanding models to perform human-like scene analysis and understanding. Scene understanding enables better semantic segmentation and object-to-object interaction detection. In the…

Modern machine learning models typically represent inputs as fixed points in a high-dimensional embedding space. While this approach has been proven powerful for a wide range of downstream tasks, it fundamentally differs from the way humans…

This work introduces a new multi-task, parameter-efficient language model (LM) tuning method that learns to transfer knowledge across different tasks via a mixture of soft prompts-small prefix embedding vectors pre-trained for different…

Recently, several studies have shown that utilizing contextual information to perceive target states is crucial for object tracking. They typically capture context by incorporating multiple video frames. However, these naive frame-context…

Causal discovery from time series is critical for many real-world applications, such as tracing the root causes of anomalies. Existing approaches typically rely on dataset-specific optimization, making it difficult to transfer their causal…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts. While context compression mitigates this issue, existing methods…

Self-supervised pre-trained transformers have improved the state of the art on a variety of speech tasks. Due to the quadratic time and space complexity of self-attention, they usually operate at the level of relatively short (e.g.,…

Objects rarely sit in isolation in everyday human environments. If we want robots to operate and perform tasks in our human environments, they must understand how the objects they manipulate will interact with structural elements of the…

This paper presents a comprehensive study on resume classification to reduce the time and labor needed to screen an overwhelming number of applications significantly, while improving the selection of suitable candidates. A total of 6,492…

Conditional inference on joint textual and visual clues is a multi-modal reasoning task that textual clues provide prior permutation or external knowledge, which are complementary with visual content and pivotal to deducing the correct…