Related papers: TAPE: Assessing Few-shot Russian Language Understa…

Large-scale cross-modal pre-training paradigms have recently shown ubiquitous success on a wide range of downstream tasks, e.g., zero-shot classification, retrieval and image captioning. However, their successes highly rely on the scale and…

Transferring knowledge from one domain to another is of practical importance for many tasks in natural language processing, especially when the amount of available data in the target domain is limited. In this work, we propose a novel…

Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on…

Handwritten text recognition in low resource scenarios, such as manuscripts with rare alphabets, is a challenging problem. The main difficulty comes from the very few annotated data and the limited linguistic information (e.g. dictionaries…

Large Language Models (LLMs) have achieved rapid progress in Chinese language understanding, yet accurately evaluating their capabilities remains challenged by benchmark saturation and prohibitive computational costs. While static…

The existing few-shot video classification methods often employ a meta-learning paradigm by designing customized temporal alignment module for similarity calculation. While significant progress has been made, these methods fail to focus on…

Large Language Models (LLMs) can reason over natural-language inputs, but their role in intrusion detection without fine-tuning remains uncertain. This study evaluates a prompt-only approach on UNSW-NB15 by converting each network flow to a…

Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, in complex tasks, GRPO frequently…

Vision and Language Models (VLMs), such as CLIP, have enabled visual recognition of a potentially unlimited set of categories described by text prompts. However, for the best visual recognition performance, these models still require tuning…

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

Self-supervised pretraining has made few-shot learning possible for many NLP tasks. But the pretraining objectives are not typically adapted specifically for in-context few-shot learning. In this paper, we propose to use self-supervision in…

Large Language Models (LLMs) have demonstrated remarkable capabilities in code understanding and generation. However, their effectiveness on non-code Software Engineering (SE) tasks remains underexplored. We present 'Software Engineering…

Hallucination detection in text generation remains an ongoing struggle for natural language processing (NLP) systems, frequently resulting in unreliable outputs in applications such as machine translation and definition modeling. Existing…

Zero-shot event-relational reasoning is an important task in natural language processing, and existing methods jointly learn a variety of event-relational prefixes and inference-form prefixes to achieve such tasks. However, training…

Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural few-shot classification models have emerged, yielding significant progress over time, both in Computer Vision…

Toxicity has become a grave problem for many online communities and has been growing across many languages, including Russian. Hate speech creates an environment of intimidation, discrimination, and may even incite some real-world violence.…

In text-audio retrieval (TAR) tasks, due to the heterogeneity of contents between text and audio, the semantic information contained in the text is only similar to certain frames within the audio. Yet, existing works aggregate the entire…

The advent of Large Language Models (LLMs) has advanced the benchmark in various Natural Language Processing (NLP) tasks. However, large amounts of labelled training data are required to train LLMs. Furthermore, data annotation and training…

Although the multilingual Neural Machine Translation(NMT), which extends Google's multilingual NMT, has ability to perform zero-shot translation and the iterative self-learning algorithm can improve the quality of zero-shot translation, it…

Multimodal data empowers machine learning models to better understand the world from various perspectives. In this work, we study the combination of \emph{text and graph} modalities, a challenging but understudied combination which is…