Related papers: Fine-Tuning Over Architectural Complexity: Broad-C…

Accurate recognition of personally identifiable information (PII) is central to automated text anonymization. This paper investigates the effectiveness of cross-domain model transfer, multi-domain data fusion, and sample-efficient learning…

While fine-tuning of pre-trained language models generally helps to overcome the lack of labelled training samples, it also displays model performance instability. This instability mainly originates from randomness in initialisation or data…

While Large Language Models show remarkable performance in natural language understanding, their resource-intensive nature makes them less accessible. In contrast, smaller language models such as MiniCPM offer more sustainable scalability,…

Conventionally, supervised fine-tuning (SFT) is treated as a simple imitation learning process that only trains a policy to imitate expert behavior on demonstration datasets. In this work, we challenge this view by establishing a…

Entity tracking requires maintaining and updating latent states for entities and attributes over long sequences. Recent task-specific attention operators can compress deep Transformer stacks into a few layers by performing multi-hop state…

Fine-grained classification is a challenging problem, due to subtle differences among highly-confused categories. Most approaches address this difficulty by learning discriminative representation of individual input image. On the other…

The recently proposed end-to-end transformer detectors, such as DETR and Deformable DETR, have a cascade structure of stacking 6 decoder layers to update object queries iteratively, without which their performance degrades seriously. In…

The rapidly evolving industry demands high accuracy of the models without the need for time-consuming and computationally expensive experiments required for fine-tuning. Moreover, a model and training pipeline, which was once carefully…

Fine-grained entity typing (FET) is an essential task in natural language processing that aims to assign semantic types to entities in text. However, FET poses a major challenge known as the noise labeling problem, whereby current methods…

The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…

While specialized detectors for AI-Generated Images (AIGI) achieve near-perfect accuracy on curated benchmarks, they suffer from a dramatic performance collapse in realistic, in-the-wild scenarios. In this work, we demonstrate that…

Personalized diffusion models (PDMs) have become prominent for adapting pre-trained text-to-image models to generate images of specific subjects using minimal training data. However, PDMs are susceptible to minor adversarial perturbations,…

The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images. However, most prior efforts focus on generating images for general categories, e.g., 1000 classes in ImageNet-1k. A…

Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or heuristic perceptual priors, which often lead to a trade-off between fidelity and visual…

Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…

In this paper, we present novel synthetic training data called self-blended images (SBIs) to detect deepfakes. SBIs are generated by blending pseudo source and target images from single pristine images, reproducing common forgery artifacts…

Text de-identification techniques are often used to mask personally identifiable information (PII) from documents. Their ability to conceal the identity of the individuals mentioned in a text is, however, hard to measure. Recent work has…

In the last decade, computer vision has witnessed the establishment of various training and learning approaches. Techniques like adversarial learning, contrastive learning, diffusion denoising learning, and ordinary reconstruction learning…

We introduce ReFinED, an efficient end-to-end entity linking model which uses fine-grained entity types and entity descriptions to perform linking. The model performs mention detection, fine-grained entity typing, and entity disambiguation…

Probabilistic cataloging (PCAT) outperforms traditional cataloging methods on single-band optical data in crowded fields (Portillo et al. 2017). We extend our work to multiple bands, achieving greater sensitivity ($\sim$ 0.4 mag) and…