Related papers: Aging with GRACE: Lifelong Model Editing with Disc…

Instruction-based image editing models have recently achieved impressive performance, enabling complex edits to an input image from a multi-instruction prompt. However, these models apply each instruction in the prompt with a fixed…

Diffusion-based point editing methods have gained significant traction in image editing tasks due to their ability to manipulate image semantics and fine details by applying localized perturbations on the manifold of noise latent. However,…

We present TRACE, a mesh-guided 3DGS editing framework that achieves automated, high-fidelity scene transformation. By anchoring video diffusion with explicit 3D geometry, TRACE uniquely enables fine-grained, part-level manipulatio--such as…

Instruction-based image editing models offer increased personalization opportunities in generative tasks. However, properly evaluating their results is challenging, and most of the existing metrics lag in terms of alignment with human…

Parameter-Efficient Fine-Tuning (PEFT) effectively adapts pre-trained transformers to downstream tasks. However, the optimization of tasks performance often comes at the cost of generalizability in fine-tuned models. To address this issue,…

Continuous-time dynamic graph modeling is a crucial task for many real-world applications, such as financial risk management and fraud detection. Though existing dynamic graph modeling methods have achieved satisfactory results, they still…

Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning…

Large Language Models~(LLMs) have demonstrated incredible capabilities in understanding, generating, and manipulating languages. Through human-model interactions, LLMs can automatically understand human-issued instructions and output the…

Text style transfer is the task that generates a sentence by preserving the content of the input sentence and transferring the style. Most existing studies are progressing on non-parallel datasets because parallel datasets are limited and…

Neural language models often fail to generate diverse and informative texts, limiting their applicability in real-world problems. While previous approaches have proposed to address these issues by identifying and penalizing undesirable…

Large-scale pretrained models have proven immensely valuable in handling data-intensive modalities like text and image. However, fine-tuning these models for certain specialized modalities, such as protein sequence and cosmic ray, poses…

Parameter-Efficient Fine-Tuning (PEFT) has become a key strategy for adapting large language models, with recent advances in sparse tuning reducing overhead by selectively updating key parameters or subsets of data. Existing approaches…

Fine-tuning over large pretrained language models (PLMs) has established many state-of-the-art results. Despite its superior performance, such fine-tuning can be unstable, resulting in significant variance in performance and potential risks…

Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models…

Text-to-image diffusion models often make implicit assumptions about the world when generating images. While some assumptions are useful (e.g., the sky is blue), they can also be outdated, incorrect, or reflective of social biases present…

Recent work has witnessed a paradigm shift from Seq2Seq to Seq2Edit in the field of text editing, with the aim of addressing the slow autoregressive inference problem posed by the former. Despite promising results, Seq2Edit approaches still…

Fixed representational capacity is a fundamental constraint in continual learning: practitioners must guess an appropriate model width before training, without knowing how many distinct concepts the data contains. We propose LACE…

Generative models have recently demonstrated strong potential in multi-behavior recommendation systems, leveraging the expressive power of transformers and tokenization to generate personalized item sequences. However, their adoption is…

Lifelong sequence generation (LSG), a problem in continual learning, aims to continually train a model on a sequence of generation tasks to learn constantly emerging new generation patterns while avoiding the forgetting of previous…

We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…