Related papers: Break-for-Make: Modular Low-Rank Adaptations for C…

Partial domain adaptation which assumes that the unknown target label space is a subset of the source label space has attracted much attention in computer vision. Despite recent progress, existing methods often suffer from three key…

Massive Open Online Courses (MOOCs) have greatly contributed to making education more accessible. However, many MOOCs maintain a rigid, one-size-fits-all structure that fails to address the diverse needs and backgrounds of individual…

The rapid advancements in large language models (LLMs) have revolutionized natural language processing, creating an increased need for efficient, task-specific fine-tuning methods. Traditional fine-tuning of LLMs involves updating a large…

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to…

Multimodal Large Language Models (MLLMs) have achieved success across various domains. However, their applicability tends to degrade when confronted with different types of data inputs, especially for MLLMs that have been fine-tuned for…

The deployment of large language models (LLMs) is often constrained by their substantial computational and memory demands. While structured pruning presents a viable approach by eliminating entire network components, existing methods suffer…

Analogies help learners understand unfamiliar concepts by relating them to known concepts. Despite recent advances, large language models (LLMs) continue to struggle to generate analogies of comparable quality to those produced by humans.…

Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical focus. Existing retrieval-augmented approaches such as LaMP and PGraphRAG enrich profiles with…

Adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models to the downstream tasks. However, after reviewing existing adapters, we find they generally fail to fully…

Large language model (LLM) agents have emerged as powerful tools for complex tasks, yet their ability to adapt to individual users remains fundamentally limited. We argue this limitation stems from a critical architectural conflation:…

Personalized large language models (LLMs) aim to tailor interactions, content, and recommendations to individual user preferences. While parameter-efficient fine-tuning (PEFT) methods excel in performance and generalization, they are costly…

Adapting LLMs to specific stylistic characteristics, like brand voice or authorial tones, is crucial for enterprise communication but challenging to achieve from corpora which lacks instruction-response formatting without compromising…

Decomposing models into multiple components is critically important in many applications such as language modeling (LM) as it enables adapting individual components separately and biasing of some components to the user's personal…

In addressing the computational and memory demands of fine-tuning Large Language Models(LLMs), we propose LoRA-SP(Streamlined Partial Parameter Adaptation), a novel approach utilizing randomized half-selective parameter freezing within the…

Integrating multiple personalized concepts into a single image has recently become a significant area of focus within Text-to-Image (T2I) generation. However, existing methods often underperform on complex multi-object scenes due to…

With the advent of large-scale pre-trained models, interest in adapting and exploiting them for continual learning scenarios has grown. In this paper, we propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that…

Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data. We argue this not only risks reinforcing exposure to sensitive data, but also fundamentally…

Prompt-guided generative AI models have rapidly expanded across vision and language domains, producing realistic and diverse outputs from textual inputs. The growing variety of such models, trained with different data and architectures,…

Continual learning methods based on pre-trained models (PTM) have recently gained attention which adapt to successive downstream tasks without catastrophic forgetting. These methods typically refrain from updating the pre-trained parameters…

Diffusion-based generative models have significantly advanced text-to-image generation but encounter challenges when processing lengthy and intricate text prompts describing complex scenes with multiple objects. While excelling in…